Detectron training schedule #327

mkocabas · 2018-03-10T10:03:02Z

I have started a training with image-net weights to test the training-schedule branch. I will update this issue regularly to report the findings.

Training setting is:
dataset : COCO
batch-size : 1
GPU : 1 x GTX1080Ti (I can switch to a P100 in the following days.)

The text was updated successfully, but these errors were encountered:

mkocabas · 2018-03-11T09:48:45Z

Epoch 00002: saving model to ./snapshots/resnet50_coco_02.h5
Loading and preparing results...
DONE (t=21.74s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=104.13s).
Accumulating evaluation results...
DONE (t=45.75s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.002
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.005
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.001
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.005
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.003
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.003
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.053
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.110
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.121
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.029
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.112
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.191
Epoch 3/144
10000/10000 [==============================] - 2317s 232ms/step - loss: 3.1109 - regression_loss: 2.2298 - classification_loss: 0.8811

Epoch 00003: saving model to ./snapshots/resnet50_coco_03.h5
Loading and preparing results...
DONE (t=15.26s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=87.05s).
Accumulating evaluation results...
DONE (t=33.70s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.004
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.008
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.003
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.002
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.006
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.005
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.063
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.134
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.144
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.044
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.135
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.227
Epoch 4/144
10000/10000 [==============================] - 2303s 230ms/step - loss: 2.9268 - regression_loss: 2.1220 - classification_loss: 0.8048

Epoch 00004: saving model to ./snapshots/resnet50_coco_04.h5
Loading and preparing results...
DONE (t=14.48s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=83.72s).
Accumulating evaluation results...
DONE (t=31.03s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.004
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.008
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.003
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.004
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.006
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.005
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.065
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.123
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.130
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.019
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.128
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.213
Epoch 5/144
10000/10000 [==============================] - 2309s 231ms/step - loss: 2.8028 - regression_loss: 2.0540 - classification_loss: 0.7488
Epoch 00005: saving model to ./snapshots/resnet50_coco_05.h5
Loading and preparing results...
DONE (t=3.64s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=26.98s).
Accumulating evaluation results...
DONE (t=3.74s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.003
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.006
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.002
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.001
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.003
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.004
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.004
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.008
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.010
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.008
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.011
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.010
Epoch 6/144
10000/10000 [==============================] - 2314s 231ms/step - loss: 2.7722 - regression_loss: 2.0240 - classification_loss: 0.7482

Epoch 00006: saving model to ./snapshots/resnet50_coco_06.h5
Loading and preparing results...
DONE (t=6.09s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=48.02s).
Accumulating evaluation results...
DONE (t=15.48s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.008
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.014
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.007
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.007
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.013
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.010
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.082
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.134
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.136
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.037
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.136
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.217
Epoch 7/144
10000/10000 [==============================] - 2301s 230ms/step - loss: 2.6505 - regression_loss: 1.9545 - classification_loss: 0.6960

Epoch 00007: saving model to ./snapshots/resnet50_coco_07.h5
Loading and preparing results...
DONE (t=27.78s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=132.05s).
Accumulating evaluation results...
DONE (t=59.59s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.018
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.032
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.017
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.010
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.023
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.021
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.121
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.258
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.295
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.133
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.337
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.423
Epoch 8/144
10000/10000 [==============================] - 2322s 232ms/step - loss: 2.6217 - regression_loss: 1.9250 - classification_loss: 0.6966
Epoch 00008: saving model to ./snapshots/resnet50_coco_08.h5
Loading and preparing results...
DONE (t=20.77s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=112.51s).
Accumulating evaluation results...
DONE (t=55.75s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.021
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.038
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.022
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.011
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.026
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.028
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.129
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.262
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.289
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.111
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.318
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.438
Epoch 9/144
10000/10000 [==============================] - 2637s 264ms/step - loss: 2.5497 - regression_loss: 1.9000 - classification_loss: 0.6497 - ETA: 32:39 - loss: 2.6171 - regression_loss: 1.9622 - classification_loss: 0.654
Epoch 00009: saving model to ./snapshots/resnet50_coco_09.h5
Loading and preparing results...
DONE (t=24.63s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=119.16s).
Accumulating evaluation results...
DONE (t=51.94s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.025
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.044
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.025
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.015
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.031
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.030
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.137
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.279
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.316
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.140
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.351
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.455
Epoch 10/144
10000/10000 [==============================] - 2300s 230ms/step - loss: 2.5003 - regression_loss: 1.8702 - classification_loss: 0.6301

Epoch 00010: saving model to ./snapshots/resnet50_coco_10.h5
Loading and preparing results...
DONE (t=26.29s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=123.64s).
Accumulating evaluation results...
DONE (t=50.10s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.028
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.050
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.028
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.017
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.032
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.036
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.140
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.283
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.323
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.150
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.363
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.455
Epoch 11/144
10000/10000 [==============================] - 2317s 232ms/step - loss: 2.4756 - regression_loss: 1.8655 - classification_loss: 0.6101

Epoch 00011: saving model to ./snapshots/resnet50_coco_11.h5
Loading and preparing results...
DONE (t=23.79s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=116.43s).
Accumulating evaluation results...
DONE (t=44.67s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.037
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.064
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.038
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.018
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.044
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.045
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.155
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.304
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.345
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.153
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.386
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.488
Epoch 12/144
10000/10000 [==============================] - 2314s 231ms/step - loss: 2.4246 - regression_loss: 1.8341 - classification_loss: 0.5906
Epoch 00012: saving model to ./snapshots/resnet50_coco_12.h5
Loading and preparing results...
DONE (t=20.27s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=101.43s).
Accumulating evaluation results...
DONE (t=36.76s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.035
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.061
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.037
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.021
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.041
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.044
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.145
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.285
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.318
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.157
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.351
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.440
Epoch 13/144
10000/10000 [==============================] - 2318s 232ms/step - loss: 2.3977 - regression_loss: 1.7938 - classification_loss: 0.6039

Epoch 00013: saving model to ./snapshots/resnet50_coco_13.h5
Loading and preparing results...
DONE (t=27.21s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=119.76s).
Accumulating evaluation results...
DONE (t=54.21s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.041
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.071
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.043
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.021
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.044
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.052
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.159
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.313
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.363
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.180
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.408
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.502
Epoch 14/144
10000/10000 [==============================] - 2319s 232ms/step - loss: 2.3509 - regression_loss: 1.7823 - classification_loss: 0.5686

Epoch 00014: saving model to ./snapshots/resnet50_coco_14.h5
Loading and preparing results...
DONE (t=26.27s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=125.17s).
Accumulating evaluation results...
DONE (t=47.70s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.050
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.085
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.052
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.026
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.057
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.060
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.163
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.319
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.374
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.189
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.423
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.507
Epoch 15/144
10000/10000 [==============================] - 2316s 232ms/step - loss: 2.3316 - regression_loss: 1.7596 - classification_loss: 0.5720

Epoch 00015: saving model to ./snapshots/resnet50_coco_15.h5
Loading and preparing results...
DONE (t=16.75s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=105.06s).
Accumulating evaluation results...
DONE (t=35.95s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.052
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.088
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.056
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.029
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.060
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.066
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.164
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.313
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.355
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.155
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.401
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.507
Epoch 16/144
10000/10000 [==============================] - 2314s 231ms/step - loss: 2.2786 - regression_loss: 1.7342 - classification_loss: 0.5443
Epoch 00016: saving model to ./snapshots/resnet50_coco_16.h5
Loading and preparing results...
DONE (t=28.10s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=127.25s).
Accumulating evaluation results...
DONE (t=46.34s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.061
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.102
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.064
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.029
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.069
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.075
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.171
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.329
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.386
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.199
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.433
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.518
Epoch 17/144
10000/10000 [==============================] - 2321s 232ms/step - loss: 2.2666 - regression_loss: 1.7299 - classification_loss: 0.5367

Epoch 00017: saving model to ./snapshots/resnet50_coco_17.h5
Loading and preparing results...
DONE (t=18.41s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=104.45s).
Accumulating evaluation results...
DONE (t=36.99s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.059
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.099
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.062
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.033
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.076
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.077
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.170
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.317
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.363
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.161
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.408
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.515
Epoch 18/144
10000/10000 [==============================] - 2317s 232ms/step - loss: 2.2625 - regression_loss: 1.7269 - classification_loss: 0.5357

Epoch 00018: saving model to ./snapshots/resnet50_coco_18.h5
Loading and preparing results...
DONE (t=22.16s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=118.54s).
Accumulating evaluation results...
DONE (t=42.31s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.067
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.112
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.070
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.034
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.080
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.078
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.178
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.336
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.393
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.202
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.444
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.524
Epoch 19/144
10000/10000 [==============================] - 2322s 232ms/step - loss: 2.2549 - regression_loss: 1.7154 - classification_loss: 0.5395

Epoch 00019: saving model to ./snapshots/resnet50_coco_19.h5
Loading and preparing results...
DONE (t=24.19s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=110.37s).
Accumulating evaluation results...
DONE (t=45.92s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.069
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.117
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.073
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.033
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.079
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.086
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.176
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.337
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.392
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.201
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.439
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.528
Epoch 20/144
10000/10000 [==============================] - 2321s 232ms/step - loss: 2.2149 - regression_loss: 1.6986 - classification_loss: 0.5163
Epoch 00020: saving model to ./snapshots/resnet50_coco_20.h5
Loading and preparing results...
DONE (t=24.45s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=118.79s).
Accumulating evaluation results...
DONE (t=40.73s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.076
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.129
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.080
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.035
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.085
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.093
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.182
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.343
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.400
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.210
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.443
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.532
Epoch 21/144
10000/10000 [==============================] - 2319s 232ms/step - loss: 2.2228 - regression_loss: 1.7005 - classification_loss: 0.5224

Epoch 00021: saving model to ./snapshots/resnet50_coco_21.h5
Loading and preparing results...
DONE (t=18.70s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=106.55s).
Accumulating evaluation results...
DONE (t=36.06s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.077
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.129
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.081
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.037
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.092
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.094
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.178
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.338
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.390
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.194
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.438
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.537
Epoch 22/144
10000/10000 [==============================] - 2318s 232ms/step - loss: 2.1960 - regression_loss: 1.6878 - classification_loss: 0.5082

Epoch 00022: saving model to ./snapshots/resnet50_coco_22.h5
Loading and preparing results...
DONE (t=25.44s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=121.76s).
Accumulating evaluation results...
DONE (t=42.62s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.082
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.136
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.087
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.038
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.094
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.101
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.186
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.349
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.409
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.217
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.455
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.545
Epoch 23/144
10000/10000 [==============================] - 2318s 232ms/step - loss: 2.1866 - regression_loss: 1.6872 - classification_loss: 0.4993
Epoch 00023: saving model to ./snapshots/resnet50_coco_23.h5
Loading and preparing results...
DONE (t=26.03s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=127.11s).
Accumulating evaluation results...
DONE (t=42.67s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.086
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.142
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.091
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.039
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.095
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.106
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.188
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.351
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.410
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.227
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.457
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.537
Epoch 00024: saving model to ./snapshots/resnet50_coco_24.h5
Loading and preparing results...
DONE (t=18.67s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=109.31s).
Accumulating evaluation results...
DONE (t=35.58s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.090
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.148
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.095
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.042
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.108
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.111
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.192
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.355
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.409
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.213
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.455
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.552
Epoch 25/144
10000/10000 [==============================] - 2309s 231ms/step - loss: 2.1262 - regression_loss: 1.6423 - classification_loss: 0.4839

Epoch 00025: saving model to ./snapshots/resnet50_coco_25.h5
Loading and preparing results...
DONE (t=24.82s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=126.99s).
Accumulating evaluation results...
DONE (t=40.75s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.100
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.163
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.106
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.044
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.116
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.125
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.196
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.362
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.424
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.227
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.473
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.564
Epoch 00026: saving model to ./snapshots/resnet50_coco_26.h5
^[Loading and preparing results...
DONE (t=23.42s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=123.44s).
Accumulating evaluation results...
DONE (t=40.23s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.102
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.166
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.108
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.046
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.122
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.126
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.197
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.361
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.419
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.218
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.469
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.558
Epoch 27/144
10000/10000 [==============================] - 2301s 230ms/step - loss: 2.1063 - regression_loss: 1.6288 - classification_loss: 0.477$

Epoch 00027: saving model to ./snapshots/resnet50_coco_27.h5
Loading and preparing results...
DONE (t=20.22s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=117.86s).
Accumulating evaluation results...
DONE (t=39.87s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.103
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.168
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.109
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.045
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.116
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.125
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.198
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.364
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.422
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.222
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.470
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.566
Epoch 28/144
10000/10000 [==============================] - 2308s 231ms/step - loss: 2.0913 - regression_loss: 1.6164 - classification_loss: 0.4749
Epoch 00028: saving model to ./snapshots/resnet50_coco_28.h5
Loading and preparing results...
DONE (t=25.33s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=119.71s).
Accumulating evaluation results...
DONE (t=39.98s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.106
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.173
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.112
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.046
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.119
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.133
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.197
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.365
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.423
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.232
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.475
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.552
Epoch 29/144
10000/10000 [==============================] - 2303s 230ms/step - loss: 2.0960 - regression_loss: 1.6287 - classification_loss: 0.4674

Epoch 00029: saving model to ./snapshots/resnet50_coco_29.h5
Loading and preparing results...
DONE (t=16.57s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=99.23s).
Accumulating evaluation results...
DONE (t=30.29s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.108
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.178
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.114
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.049
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.123
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.133
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.199
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.361
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.410
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.219
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.457
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.537
Epoch 30/144
10000/10000 [==============================] - 2324s 232ms/step - loss: 2.0917 - regression_loss: 1.6216 - classification_loss: 0.4701

Epoch 00030: saving model to ./snapshots/resnet50_coco_30.h5
Loading and preparing results...
DONE (t=23.02s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=112.69s).
Accumulating evaluation results...
DONE (t=43.60s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.110
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.181
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.116
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.049
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.125
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.135
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.199
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.363
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.421
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.223
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.469
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.555
Epoch 31/144
10000/10000 [==============================] - 6602s 660ms/step - loss: 2.0839 - regression_loss: 1.6225 - classification_loss: 0.4614

Epoch 00031: saving model to ./snapshots/resnet50_coco_31.h5
Loading and preparing results...
DONE (t=19.17s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=103.66s).
Accumulating evaluation results...
DONE (t=34.44s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.113
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.184
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.118
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.051
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.126
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.142
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.201
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.363
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.417
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.224
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.461
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.557
Epoch 00032: saving model to ./snapshots/resnet50_coco_32.h5
Loading and preparing results...
DONE (t=23.64s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=113.27s).
Accumulating evaluation results...
DONE (t=35.76s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.117
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.191
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.124
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.052
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.131
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.146
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.203
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.374
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.435
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.238
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.487
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.570
Epoch 33/144
10000/10000 [==============================] - 2316s 232ms/step - loss: 2.0651 - regression_loss: 1.6121 - classification_loss: 0.4530

Epoch 00033: saving model to ./snapshots/resnet50_coco_33.h5
Loading and preparing results...
DONE (t=23.59s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=110.76s).
Accumulating evaluation results...
DONE (t=36.23s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.120
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.196
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.125
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.053
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.138
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.151
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.206
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.375
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.430
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.229
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.480
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.572
Epoch 34/144
10000/10000 [==============================] - 2315s 231ms/step - loss: 2.0466 - regression_loss: 1.5970 - classification_loss: 0.4495

Epoch 00034: saving model to ./snapshots/resnet50_coco_34.h5
Loading and preparing results...
DONE (t=23.81s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=108.46s).
Accumulating evaluation results...
DONE (t=35.14s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.125
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.204
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.132
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.053
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.139
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.156
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.207
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.377
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.440
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.244
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.492
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.574
Epoch 35/144
10000/10000 [==============================] - 2319s 232ms/step - loss: 2.0621 - regression_loss: 1.6092 - classification_loss: 0.4529

Epoch 00035: saving model to ./snapshots/resnet50_coco_35.h5
Loading and preparing results...
DONE (t=16.73s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=99.75s).
Accumulating evaluation results...
DONE (t=29.68s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.123
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.200
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.130
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.053
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.141
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.152
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.208
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.375
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.430
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.239
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.478
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.558
Epoch 36/144
10000/10000 [==============================] - 2320s 232ms/step - loss: 2.0321 - regression_loss: 1.5914 - classification_loss: 0.4406

Epoch 00036: saving model to ./snapshots/resnet50_coco_36.h5
Loading and preparing results...
DONE (t=19.43s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=108.65s).
Accumulating evaluation results...
DONE (t=33.29s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.125
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.206
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.131
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.056
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.147
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.158
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.211
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.380
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.441
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.236
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.493
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.585
Epoch 37/144
10000/10000 [==============================] - 2325s 233ms/step - loss: 2.0005 - regression_loss: 1.5581 - classification_loss: 0.4424

Epoch 00037: saving model to ./snapshots/resnet50_coco_37.h5
Loading and preparing results...
DONE (t=18.64s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=97.24s).
Accumulating evaluation results...
DONE (t=28.53s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.126
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.206
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.133
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.054
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.144
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.160
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.210
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.373
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.425
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.221
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.471
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.568
Epoch 38/144
10000/10000 [==============================] - 2322s 232ms/step - loss: 2.0016 - regression_loss: 1.5675 - classification_loss: 0.4342

Epoch 00038: saving model to ./snapshots/resnet50_coco_38.h5
Loading and preparing results...
DONE (t=21.29s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=107.70s).
Accumulating evaluation results...
DONE (t=32.05s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.132
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.216
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.139
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.059
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.145
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.164
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.214
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.384
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.445
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.260
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.495
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.578
Epoch 39/144
10000/10000 [==============================] - 2319s 232ms/step - loss: 1.9844 - regression_loss: 1.5537 - classification_loss: 0.4307

Epoch 00039: saving model to ./snapshots/resnet50_coco_39.h5
Loading and preparing results...
DONE (t=21.51s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=107.38s).
Accumulating evaluation results...
DONE (t=32.51s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.133
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.216
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.141
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.058
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.155
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.168
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.214
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.385
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.447
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.244
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.500
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.589
Epoch 40/144
10000/10000 [==============================] - 2321s 232ms/step - loss: 2.0092 - regression_loss: 1.5675 - classification_loss: 0.4416

Epoch 00040: saving model to ./snapshots/resnet50_coco_40.h5
Loading and preparing results...
DONE (t=20.31s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=103.47s).
Accumulating evaluation results...
DONE (t=31.19s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.132
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.216
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.139
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.057
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.153
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.169
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.214
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.383
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.443
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.244
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.491
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.582
Epoch 41/144
10000/10000 [==============================] - 2319s 232ms/step - loss: 1.9997 - regression_loss: 1.5578 - classification_loss: 0.4419

Epoch 00041: saving model to ./snapshots/resnet50_coco_41.h5
Loading and preparing results...
DONE (t=20.80s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=105.95s).
Accumulating evaluation results...
DONE (t=32.30s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.132
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.215
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.140
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.056
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.152
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.163
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.213
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.384
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.444
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.257
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.496
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.583
Epoch 42/144
10000/10000 [==============================] - 2319s 232ms/step - loss: 1.9909 - regression_loss: 1.5624 - classification_loss: 0.4285

Epoch 00042: saving model to ./snapshots/resnet50_coco_42.h5
Loading and preparing results...
DONE (t=19.05s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=108.15s).
Accumulating evaluation results...
DONE (t=32.80s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.138
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.223
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.147
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.061
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.159
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.175
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.218
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.390
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.452
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.265
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.501
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.597

Epoch 00042: ReduceLROnPlateau reducing learning rate to 6.249999860301614e-05.
Epoch 43/144
10000/10000 [==============================] - 2424s 242ms/step - loss: 1.9695 - regression_loss: 1.5447 - classification_loss: 0.4248
[A^[[A^[[A^[[A^[[A^[[A^[[A^[[A^[[A^[[A^[[A^[[A^[[A^[[A^[[A^[[A^[[A^[[A^[[A
Epoch 00043: saving model to ./snapshots/resnet50_coco_43.h5
Loading and preparing results...
DONE (t=18.67s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=108.96s).
Accumulating evaluation results...
DONE (t=32.93s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.137
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.223
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.144
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.061
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.162
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.174
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.216
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.385
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.446
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.244
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.497
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.593
Epoch 44/144
10000/10000 [==============================] - 2331s 233ms/step - loss: 1.9714 - regression_loss: 1.5436 - classification_loss: 0.4278

Epoch 00044: saving model to ./snapshots/resnet50_coco_44.h5
Loading and preparing results...
DONE (t=18.67s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=97.01s).
Accumulating evaluation results...
DONE (t=27.63s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.141
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.229
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.147
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.061
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.159
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.174
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.217
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.387
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.442
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.247
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.494
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.575
Epoch 45/144
10000/10000 [==============================] - 2319s 232ms/step - loss: 1.9794 - regression_loss: 1.5512 - classification_loss: 0.4283

Epoch 00045: saving model to ./snapshots/resnet50_coco_45.h5
Loading and preparing results...
DONE (t=17.33s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=103.49s).
Accumulating evaluation results...
DONE (t=31.41s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.138
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.225
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.145
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.060
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.164
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.178
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.214
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.383
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.442
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.241
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.493
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.585
Epoch 46/144
10000/10000 [==============================] - 2319s 232ms/step - loss: 1.9806 - regression_loss: 1.5570 - classification_loss: 0.4236
Epoch 00046: saving model to ./snapshots/resnet50_coco_46.h5
Loading and preparing results...
DONE (t=15.25s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=92.96s).
Accumulating evaluation results...
DONE (t=28.83s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.141
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.231
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.149
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.061
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.160
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.175
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.217
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.383
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.435
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.237
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.484
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.569

Epoch 00046: ReduceLROnPlateau reducing learning rate to 6.249999860301614e-05.
Epoch 47/144
10000/10000 [==============================] - 2326s 233ms/step - loss: 1.9749 - regression_loss: 1.5563 - classification_loss: 0.4186

Epoch 00047: saving model to ./snapshots/resnet50_coco_47.h5
Loading and preparing results...
DONE (t=21.46s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=112.31s).
Accumulating evaluation results...
DONE (t=33.98s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.145
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.236
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.152
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.063
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.167
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.182
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.220
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.391
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.451
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.257
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.503
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.602
Epoch 47/144
10000/10000 [==============================] - 2326s 233ms/step - loss: 1.9749 - regression_loss: 1.5563 - classification_loss: 0.4186

Epoch 00047: saving model to ./snapshots/resnet50_coco_47.h5
Loading and preparing results...
DONE (t=21.46s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=112.31s).
Accumulating evaluation results...
DONE (t=33.98s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.145
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.236
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.152
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.063
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.167
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.182
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.220
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.391
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.451
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.257
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.503
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.602
Epoch 48/144
10000/10000 [==============================] - 2604s 260ms/step - loss: 1.9396 - regression_loss: 1.5217 - classification_loss: 0.4179

Epoch 00048: saving model to ./snapshots/resnet50_coco_48.h5
Loading and preparing results...
DONE (t=19.50s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=112.51s).
Accumulating evaluation results...
DONE (t=32.47s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.148
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.239
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.157
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.065
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.168
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.189
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.221
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.394
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.457
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.270
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.506
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.598
Epoch 49/144
10000/10000 [==============================] - 2322s 232ms/step - loss: 1.9254 - regression_loss: 1.5141 - classification_loss: 0.4112

Epoch 00049: saving model to ./snapshots/resnet50_coco_49.h5
Loading and preparing results...
DONE (t=21.17s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=101.65s).
Accumulating evaluation results...
DONE (t=36.27s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.148
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.239
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.155
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.065
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.170
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.185
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.220
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.395
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.456
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.268
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.508
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.599
Epoch 50/144
10000/10000 [==============================] - 2311s 231ms/step - loss: 1.9369 - regression_loss: 1.5225 - classification_loss: 0.4144
Epoch 50/144
10000/10000 [==============================] - 2311s 231ms/step - loss: 1.9369 - regression_loss: 1.5225 - classification_loss: 0.4144

Epoch 00050: saving model to ./snapshots/resnet50_coco_50.h5
Loading and preparing results...
DONE (t=21.16s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=105.13s).
Accumulating evaluation results...
DONE (t=31.04s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.150
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.241
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.158
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.067
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.170
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.192
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.222
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.395
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.455
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.260
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.508
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.601
Epoch 51/144
10000/10000 [==============================] - 2324s 232ms/step - loss: 1.9292 - regression_loss: 1.5160 - classification_loss: 0.4132

Epoch 00051: saving model to ./snapshots/resnet50_coco_51.h5
Loading and preparing results...
DONE (t=20.14s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=103.80s).
Accumulating evaluation results...
DONE (t=29.95s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.149
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.242
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.158
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.065
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.172
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.187
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.223
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.393
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.453
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.270
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.499
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.603
Epoch 52/144
10000/10000 [==============================] - 2329s 233ms/step - loss: 1.9113 - regression_loss: 1.5019 - classification_loss: 0.4094

Epoch 00052: saving model to ./snapshots/resnet50_coco_52.h5
Loading and preparing results...
DONE (t=15.94s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=93.20s).
Accumulating evaluation results...
DONE (t=26.17s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.150
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.244
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.159
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.064
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.169
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.193
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.222
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.391
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.443
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.254
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.491
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.584
Epoch 53/144
10000/10000 [==============================] - 2314s 231ms/step - loss: 1.9256 - regression_loss: 1.5138 - classification_loss: 0.4118
Epoch 00053: saving model to ./snapshots/resnet50_coco_53.h5
Loading and preparing results...
DONE (t=22.51s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=114.99s).
Accumulating evaluation results...
DONE (t=33.74s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.153
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.249
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.161
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.067
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.172
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.192
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.223
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.396
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.459
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.279
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.511
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.602
Epoch 54/144
10000/10000 [==============================] - 2315s 231ms/step - loss: 1.9096 - regression_loss: 1.5026 - classification_loss: 0.4069

Epoch 00054: saving model to ./snapshots/resnet50_coco_54.h5
Loading and preparing results...
DONE (t=15.85s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=94.60s).
Accumulating evaluation results...
DONE (t=26.70s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.154
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.248
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.162
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.067
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.176
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.194
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.224
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.393
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.450
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.252
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.497
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.595
Epoch 55/144
10000/10000 [==============================] - 2314s 231ms/step - loss: 1.9081 - regression_loss: 1.5017 - classification_loss: 0.4064

Epoch 00055: saving model to ./snapshots/resnet50_coco_55.h5
Loading and preparing results...
DONE (t=17.04s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=103.21s).
Accumulating evaluation results...
DONE (t=30.73s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.156
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.252
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.165
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.068
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.178
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.198
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.225
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.396
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.452
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.267
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.501
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.593
Epoch 56/144
10000/10000 [==============================] - 2334s 233ms/step - loss: 1.9143 - regression_loss: 1.5057 - classification_loss: 0.4087
Epoch 00056: saving model to ./snapshots/resnet50_coco_56.h5
Loading and preparing results...
DONE (t=20.86s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=104.42s).
Accumulating evaluation results...
DONE (t=29.20s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.155
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.251
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.164
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.067
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.177
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.198
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.224
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.396
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.457
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.269
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.507
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.593
Epoch 57/144
10000/10000 [==============================] - 2325s 233ms/step - loss: 1.9253 - regression_loss: 1.5230 - classification_loss: 0.4023

Epoch 00057: saving model to ./snapshots/resnet50_coco_57.h5
Loading and preparing results...
DONE (t=18.01s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=103.83s).
Accumulating evaluation results...
DONE (t=29.99s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.158
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.255
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.166
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.068
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.184
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.204
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.226
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.398
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.460
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.271
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.508
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.609
Epoch 58/144
10000/10000 [==============================] - 2325s 233ms/step - loss: 1.9203 - regression_loss: 1.5184 - classification_loss: 0.4019

Epoch 00058: saving model to ./snapshots/resnet50_coco_58.h5
Loading and preparing results...
DONE (t=17.96s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=104.09s).
Accumulating evaluation results...
DONE (t=29.07s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.160
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.256
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.168
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.069
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.182
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.204
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.227
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.401
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.461
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.271
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.513
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.605

Epoch 00058: ReduceLROnPlateau reducing learning rate to 6.249999860301614e-05.
Epoch 59/144
10000/10000 [==============================] - 2319s 232ms/step - loss: 1.9131 - regression_loss: 1.5096 - classification_loss: 0.4035
Epoch 00059: saving model to ./snapshots/resnet50_coco_59.h5
Loading and preparing results...
DONE (t=17.06s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=100.44s).
Accumulating evaluation results...
DONE (t=28.86s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.159
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.255
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.168
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.070
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.185
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.208
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.226
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.399
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.459
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.266
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.509
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.609
Epoch 60/144
10000/10000 [==============================] - 2322s 232ms/step - loss: 1.8745 - regression_loss: 1.4752 - classification_loss: 0.3993

Epoch 00060: saving model to ./snapshots/resnet50_coco_60.h5
Loading and preparing results...
DONE (t=20.03s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=97.71s).
Accumulating evaluation results...
DONE (t=34.10s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.161
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.260
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.170
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.071
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.182
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.208
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.227
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.400
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.460
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.275
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.508
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.605
Epoch 61/144
10000/10000 [==============================] - 2322s 232ms/step - loss: 1.8774 - regression_loss: 1.4802 - classification_loss: 0.3971

Epoch 00061: saving model to ./snapshots/resnet50_coco_61.h5
Loading and preparing results...
DONE (t=15.88s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=95.92s).
Accumulating evaluation results...
DONE (t=26.99s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.164
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.263
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.173
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.071
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.190
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.214
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.229
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.401
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.460
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.265
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.509
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.609
Epoch 62/144
10000/10000 [==============================] - 2323s 232ms/step - loss: 1.8831 - regression_loss: 1.4830 - classification_loss: 0.4000
Epoch 00062: saving model to ./snapshots/resnet50_coco_62.h5
Loading and preparing results...
DONE (t=19.19s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=94.17s).
Accumulating evaluation results...
DONE (t=31.98s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.163
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.261
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.173
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.071
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.187
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.213
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.227
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.398
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.457
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.268
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.505
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.605
Epoch 63/144
10000/10000 [==============================] - 2321s 232ms/step - loss: 1.8604 - regression_loss: 1.4653 - classification_loss: 0.3951

Epoch 00063: saving model to ./snapshots/resnet50_coco_63.h5
Loading and preparing results...
DONE (t=18.33s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=104.54s).
Accumulating evaluation results...
DONE (t=30.21s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.164
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.263
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.174
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.071
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.187
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.211
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.229
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.403
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.466
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.279
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.517
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.611
Epoch 64/144
10000/10000 [==============================] - 2316s 232ms/step - loss: 1.8826 - regression_loss: 1.4861 - classification_loss: 0.3965

Epoch 00064: saving model to ./snapshots/resnet50_coco_64.h5
Loading and preparing results...
DONE (t=18.43s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=104.58s).
Accumulating evaluation results...
DONE (t=30.22s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.163
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.264
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.172
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.070
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.187
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.210
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.229
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.402
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.465
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.275
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.516
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.609
Epoch 65/144
10000/10000 [==============================] - 2318s 232ms/step - loss: 1.8862 - regression_loss: 1.4906 - classification_loss: 0.3956

Epoch 00065: saving model to ./snapshots/resnet50_coco_65.h5
Loading and preparing results...
DONE (t=13.76s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=85.49s).
Accumulating evaluation results...
DONE (t=22.95s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.163
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.263
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.173
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.070
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.183
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.210
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.228
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.397
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.449
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.246
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.496
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.597
Epoch 66/144
10000/10000 [==============================] - 2316s 232ms/step - loss: 1.8708 - regression_loss: 1.4778 - classification_loss: 0.3930
Epoch 00066: saving model to ./snapshots/resnet50_coco_66.h5
Loading and preparing results...
DONE (t=19.52s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=99.45s).
Accumulating evaluation results...
DONE (t=28.19s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.166
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.265
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.175
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.072
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.186
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.214
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.230
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.402
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.462
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.270
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.511
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.613

Epoch 00066: ReduceLROnPlateau reducing learning rate to 6.249999860301614e-05.
Epoch 67/144
10000/10000 [==============================] - 2323s 232ms/step - loss: 1.8671 - regression_loss: 1.4753 - classification_loss: 0.3917

Epoch 00067: saving model to ./snapshots/resnet50_coco_67.h5
Loading and preparing results...
DONE (t=18.51s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=105.85s).
Accumulating evaluation results...
DONE (t=30.79s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.169
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.273
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.178
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.074
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.193
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.219
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.232
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.407
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.470
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.279
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.523
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.617
Epoch 68/144
10000/10000 [==============================] - 2324s 232ms/step - loss: 1.8555 - regression_loss: 1.4653 - classification_loss: 0.3901

Epoch 00068: saving model to ./snapshots/resnet50_coco_68.h5
Loading and preparing results...
DONE (t=15.68s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=94.50s).
Accumulating evaluation results...
DONE (t=26.04s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.168
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.272
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.176
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.072
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.188
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.214
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.230
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.404
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.462
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.277
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.515
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.602
Epoch 69/144
10000/10000 [==============================] - 2318s 232ms/step - loss: 1.8733 - regression_loss: 1.4819 - classification_loss: 0.3914

Epoch 00069: saving model to ./snapshots/resnet50_coco_69.h5
Loading and preparing results...
DONE (t=16.45s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=97.61s).
Accumulating evaluation results...
DONE (t=27.40s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.170
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.273
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.180
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.073
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.195
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.224
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.232
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.406
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.464
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.274
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.514
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.612
Epoch 70/144
10000/10000 [==============================] - 2331s 233ms/step - loss: 1.8648 - regression_loss: 1.4774 - classification_loss: 0.3874

Epoch 00070: saving model to ./snapshots/resnet50_coco_70.h5
Loading and preparing results...
DONE (t=20.06s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=97.82s).
Accumulating evaluation results...
DONE (t=34.27s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.171
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.275
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.180
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.075
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.193
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.224
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.231
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.406
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.467
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.282
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.519
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.612
Epoch 71/144
10000/10000 [==============================] - 2322s 232ms/step - loss: 1.8712 - regression_loss: 1.4809 - classification_loss: 0.3903

Epoch 00071: saving model to ./snapshots/resnet50_coco_71.h5
Loading and preparing results...
DONE (t=20.45s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=103.78s).
Accumulating evaluation results...
DONE (t=28.88s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.171
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.273
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.180
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.074
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.192
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.220
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.231
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.407
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.468
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.282
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.518
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.610

Epoch 00071: ReduceLROnPlateau reducing learning rate to 6.249999860301614e-05.
Epoch 72/144
10000/10000 [==============================] - 2322s 232ms/step - loss: 1.8300 - regression_loss: 1.4456 - classification_loss: 0.3844

Epoch 00072: saving model to ./snapshots/resnet50_coco_72.h5
Loading and preparing results...
DONE (t=18.03s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=103.99s).
Accumulating evaluation results...
DONE (t=29.80s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.173
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.277
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.182
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.074
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.193
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.223
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.231
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.407
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.468
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.281
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.520
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.614
Epoch 73/144
10000/10000 [==============================] - 2334s 233ms/step - loss: 1.8240 - regression_loss: 1.4422 - classification_loss: 0.3818

Epoch 00073: saving model to ./snapshots/resnet50_coco_73.h5
Loading and preparing results...
DONE (t=19.73s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=110.25s).
Accumulating evaluation results...
DONE (t=32.49s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.174
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.280
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.182
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.076
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.197
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.224
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.232
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.410
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.473
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.286
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.522
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.617
Epoch 74/144
10000/10000 [==============================] - 2319s 232ms/step - loss: 1.8407 - regression_loss: 1.4559 - classification_loss: 0.3848
Epoch 00074: saving model to ./snapshots/resnet50_coco_74.h5
Loading and preparing results...
DONE (t=16.85s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=99.72s).
Accumulating evaluation results...
DONE (t=25.03s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.172
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.276
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.181
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.074
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.191
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.223
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.232
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.403
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.455
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.264
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.500
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.604
Epoch 75/144
10000/10000 [==============================] - 2331s 233ms/step - loss: 1.8280 - regression_loss: 1.4459 - classification_loss: 0.3821

Epoch 00075: saving model to ./snapshots/resnet50_coco_75.h5
Loading and preparing results...
DONE (t=17.26s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=103.74s).
Accumulating evaluation results...
DONE (t=29.06s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.175
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.280
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.184
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.076
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.195
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.229
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.234
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.410
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.470
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.282
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.516
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.617
Epoch 76/144
10000/10000 [==============================] - 2321s 232ms/step - loss: 1.8315 - regression_loss: 1.4461 - classification_loss: 0.3854

Epoch 00076: saving model to ./snapshots/resnet50_coco_76.h5
Loading and preparing results...
DONE (t=19.65s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=95.87s).
Accumulating evaluation results...
DONE (t=32.55s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.173
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.279
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.182
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.076
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.195
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.227
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.231
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.404
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.465
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.279
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.514
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.614

Epoch 00076: ReduceLROnPlateau reducing learning rate to 6.249999860301614e-05.
Epoch 77/144
10000/10000 [==============================] - 2320s 232ms/step - loss: 1.8294 - regression_loss: 1.4477 - classification_loss: 0.3816
Epoch 00077: saving model to ./snapshots/resnet50_coco_77.h5
Loading and preparing results...
DONE (t=16.13s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=94.20s).
Accumulating evaluation results...
DONE (t=24.63s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.177
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.284
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.187
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.077
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.198
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.233
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.231
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.404
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.461
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.270
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.507
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.609
Epoch 78/144
10000/10000 [==============================] - 3226s 323ms/step - loss: 1.8381 - regression_loss: 1.4555 - classification_loss: 0.3827

Epoch 00078: saving model to ./snapshots/resnet50_coco_78.h5
Loading and preparing results...
DONE (t=21.73s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=120.19s).
Accumulating evaluation results...
DONE (t=33.28s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.178
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.285
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.186
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.076
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.199
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.230
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.234
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.407
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.469
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.281
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.517
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.612

Epoch 00078: ReduceLROnPlateau reducing learning rate to 6.249999860301614e-05.
Epoch 79/144
10000/10000 [==============================] - 2327s 233ms/step - loss: 1.8329 - regression_loss: 1.4518 - classification_loss: 0.3811

Epoch 00079: saving model to ./snapshots/resnet50_coco_79.h5
Loading and preparing results...
DONE (t=18.08s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=105.11s).
Accumulating evaluation results...
DONE (t=30.30s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.179
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.286
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.189
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.078
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.201
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.231
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.234
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.411
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.472
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.290
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.521
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.617
Epoch 00080: saving model to ./snapshots/resnet50_coco_80.h5
Loading and preparing results...
DONE (t=19.48s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=106.01s).
Accumulating evaluation results...
DONE (t=30.43s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.178
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.285
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.189
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.078
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.201
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.236
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.235
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.408
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.468
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.278
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.517
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.615

Epoch 00080: ReduceLROnPlateau reducing learning rate to 6.249999860301614e-05.
Epoch 81/144
10000/10000 [==============================] - 2323s 232ms/step - loss: 1.8248 - regression_loss: 1.4466 - classification_loss: 0.3782

Epoch 00081: saving model to ./snapshots/resnet50_coco_81.h5
Loading and preparing results...
DONE (t=19.65s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=102.48s).
Accumulating evaluation results...
DONE (t=30.37s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.178
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.286
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.189
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.080
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.201
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.233
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.234
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.411
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.471
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.283
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.520
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.613
Epoch 82/144
10000/10000 [==============================] - 2317s 232ms/step - loss: 1.8413 - regression_loss: 1.4610 - classification_loss: 0.3803

Epoch 00082: saving model to ./snapshots/resnet50_coco_82.h5
Loading and preparing results...
DONE (t=15.97s)
creating index...
index created!
Running per image evaluation...
Evaluate annotation type *bbox*
DONE (t=93.80s).
Accumulating evaluation results...
DONE (t=25.52s).
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.178
 Average Precision  (AP) @[ IoU=0.50      | area=   all | maxDets=100 ] = 0.284
 Average Precision  (AP) @[ IoU=0.75      | area=   all | maxDets=100 ] = 0.188
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.077
 Average Precision  (AP) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.203
 Average Precision  (AP) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.234
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=  1 ] = 0.234
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets= 10 ] = 0.408
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=   all | maxDets=100 ] = 0.467
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= small | maxDets=100 ] = 0.276
 Average Recall     (AR) @[ IoU=0.50:0.95 | area=medium | maxDets=100 ] = 0.515
 Average Recall     (AR) @[ IoU=0.50:0.95 | area= large | maxDets=100 ] = 0.618

Epoch 00082: ReduceLROnPlateau reducing learning rate to 6.249999860301614e-05.

hgaiser · 2018-03-14T17:23:35Z

Hmm so it appears to be stuck around 0.180 mAP. Weird.. don't know why.

mkocabas · 2018-03-15T11:58:34Z

Yes. My take on is that: adopting detectron schedule directly can't be a good solution. We somehow inspect our SGD progress and devise a new schedule accordingly. Recently, detectron training logs were released, we can inspect them to take lessons.

hgaiser · 2018-03-15T19:29:41Z

Hmm interesting, hadn't looked at those logs yet. They only have a log shared for ResNeXt101, but still, the regression loss appears to be approx. 0.045403 at the end and the classification loss appears to be 0.069822. That's quite different from what we have (around 1.0 for regression and 0.2 for classification). Any thoughts on this difference?

I have the feeling that we at least normalize the regression incorrectly. I think we should divide the result by 4, since there are 4 values. In other words, we should compute the mean of the loss of every value that contributes (only positive anchors). Right now we only divide by the number of positive anchors.

mkocabas · 2018-03-16T09:12:42Z

@hgaiser, Sorry for the late reply. I downloaded all the logs, you can find the RetinaNet R50 log in this link. As you've said there's a problem with our normalization part, and also they calculate the loss in each FPN layer separately as you've discussed earlier.

You're right about regression, yet classification is different too. So, we should inspect the loss in detail, I can take a look at that in the upcoming days.

And here are the first and last batch output of the log in the link:

json_stats: {"eta": "1 day, 19:34:11", "fl_fpn3": 0.277938, "fl_fpn4": 0.251201, "fl_fpn5": 0.260509, "fl_fpn6": 0.266378, "fl_fpn7": 0.153842, "iter": 20, "loss": 1.674090, "lr": 0.003600, "mb_qsize": 57, "mem": 6927, "retnet_bg_num": 59370159.500000, "retnet_fg_num": 304.937500, "retnet_loss_bbox_fpn3": 0.082358, "retnet_loss_bbox_fpn4": 0.097458, "retnet_loss_bbox_fpn5": 0.103961, "retnet_loss_bbox_fpn6": 0.110748, "retnet_loss_bbox_fpn7": 0.061829, "time": 1.743187}

json_stats: {"eta": "0:00:00", "fl_fpn3": 0.055898, "fl_fpn4": 0.043042, "fl_fpn5": 0.033849, "fl_fpn6": 0.028231, "fl_fpn7": 0.015677, "iter": 89999, "loss": 0.265475, "lr": 0.000100, "mb_qsize": 64, "mem": 6953, "retnet_bg_num": 59366096.500000, "retnet_fg_num": 327.937500, "retnet_loss_bbox_fpn3": 0.026807, "retnet_loss_bbox_fpn4": 0.020230, "retnet_loss_bbox_fpn5": 0.018113, "retnet_loss_bbox_fpn6": 0.013119, "retnet_loss_bbox_fpn7": 0.009029, "time": 0.483498}

YJHMITWEB · 2018-06-24T22:28:51Z

Do you guys have figured out what makes the loss value different from Detectron?
I've seen the Detection schedule they released, found out that both classification and regerssion loss start at a much smaller value in the beginning than this repo, and end up with about 0.04~0.06.
I'm also curious about why you use Adam optimizer and set the learning_rate at 1e-5 since they use SGD with lr=0.01? And also, according to their schedule, 12.19 epochs on COCO will make the model completly converge and get the best result, how about this repo?

LaCandela · 2019-10-18T14:50:01Z

I would also be interested in a training log for a fully converged model implemented in this repo. Is there a hope to see one?

hgaiser · 2019-10-24T10:27:31Z

I would also be interested in a training log for a fully converged model implemented in this repo. Is there a hope to see one?

No hope there. The current model is trained over many different runs, so there is no single log. It is also pretty difficult in my opinion because of the training optimizer and settings used. We would greatly benefit if someone takes the time to investigate how to train a COCO model more quickly.

mkocabas changed the title ~~Detectron training schedule tests~~ Detectron training schedule Mar 10, 2018

hgaiser added the enhancement label Mar 22, 2018

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

Detectron training schedule #327

Detectron training schedule #327

mkocabas commented Mar 10, 2018

mkocabas commented Mar 11, 2018 •

edited

Loading

hgaiser commented Mar 14, 2018

mkocabas commented Mar 15, 2018

hgaiser commented Mar 15, 2018

mkocabas commented Mar 16, 2018

YJHMITWEB commented Jun 24, 2018

LaCandela commented Oct 18, 2019

hgaiser commented Oct 24, 2019

Detectron training schedule #327

Detectron training schedule #327

Comments

mkocabas commented Mar 10, 2018

mkocabas commented Mar 11, 2018 • edited Loading

hgaiser commented Mar 14, 2018

mkocabas commented Mar 15, 2018

hgaiser commented Mar 15, 2018

mkocabas commented Mar 16, 2018

YJHMITWEB commented Jun 24, 2018

LaCandela commented Oct 18, 2019

hgaiser commented Oct 24, 2019

mkocabas commented Mar 11, 2018 •

edited

Loading