Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Calculating training speeds #4

Open
michaelbornholdt opened this issue Jul 23, 2021 · 0 comments
Open

Calculating training speeds #4

michaelbornholdt opened this issue Jul 23, 2021 · 0 comments

Comments

@michaelbornholdt
Copy link
Contributor

"model": {
            "name": "efficientnet",
            "crop_generator": "sampled_crop_generator",
            "metrics": ["accuracy", "top_k"],
            "epochs": 10,
            "initialization":"ImageNet",
            "params": {
                "learning_rate": 0.005,
                "batch_size": 32,
                "conv_blocks": 0,
                "feature_dim": 256,
                "pooling": "avg"
            },
 "validation": {
            "frequency": 2,
            "top_k": 5,
            "batch_size": 32,
            "frame": "val",
            "sample_first_crops": true
        }

Output

Epoch 00001: LearningRateScheduler setting learning rate to 0.001.
2021-07-22 11:02:41.058623: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcublas.so.10.0
2021-07-22 11:02:44.932000: I tensorflow/stream_executor/platform/default/dso_loader.cc:44] Successfully opened dynamic library libcudnn.so.7
     1/171641 [..............................] - ETA: 2337:41:53 - loss: 6.7107 - acc: 0.0000e+00 - top_5: 0.0000e+00COMET INFO: Ignoring automatic log_metric('batch_batch') because 'keras:batch_batch' is in COMET_LOGGING_METRICS_IGNORE
COMET INFO: Ignoring automatic log_metric('batch_size') because 'keras:batch_size' is in COMET_LOGGING_METRICS_IGNORE
  9913/171641 [>.............................] - ETA: 7:12:14 - loss: 6.0701 - acc: 0.0171 - top_5: 0.0646/home/ubuntu/dp/DeepProfiler/deepprofiler/imaging/cropping.py:48: RuntimeWarning:

invalid value encountered in true_divide

108305/171641 [=================>............] - ETA: 2:42:55 - loss: nan - acc: 0.0029 - top_5: 0.00592021-07-22 15:41:05,745 - WARNING - Retrying (Retry(total=2, connect=None, read=None, redirect=None, status=None)) after connection broken by 'ReadTimeoutError("HTTPSConnectionPool(host='www.comet.ml', port=443): Read timed out. (read timeout=10)",)': /clientlib/status-report/update
122029/171641 [====================>.........] - ETA: 2:07:29 - loss: nan - acc: 0.0027 - top_5: 0.00522021-07-22 16:16:04,505 - WARNING - Retrying (Retry(total=2, connect=None, read=None, redirect=None, status=None)) after connection broken by 'ReadTimeoutError("HTTPSConnectionPool(host='www.comet.ml', port=443): Read timed out. (read timeout=10)",)': /clientlib/status-report/update
132062/171641 [======================>.......] - ETA: 1:41:48 - loss: nan - acc: 0.0026 - top_5: 0.00482021-07-22 16:42:11,980 - WARNING - Retrying (Retry(total=2, connect=None, read=None, redirect=None, status=None)) after connection broken by 'ReadTimeoutError("HTTPSConnectionPool(host='www.comet.ml', port=443): Read timed out. (read timeout=10)",)': /clientlib/status-report/update
132149/171641 [======================>.......] - ETA: 1:41:35 - loss: nan - acc: 0.0026 - top_5: 0.00482021-07-22 16:42:26,080 - WARNING - Retrying (Retry(total=1, connect=None, read=None, redirect=None, status=None)) after connection broken by 'ReadTimeoutError("HTTPSConnectionPool(host='www.comet.ml', port=443): Read timed out. (read timeout=10)",)': /clientlib/status-report/update
132267/171641 [======================>.......] - ETA: 1:41:17 - loss: nan - acc: 0.0026 - top_5: 0.00482021-07-22 16:42:44,112 - WARNING - Retrying (Retry(total=0, connect=None, read=None, redirect=None, status=None)) after connection broken by 'ReadTimeoutError("HTTPSConnectionPool(host='www.comet.ml', port=443): Read timed out. (read timeout=10)",)': /clientlib/status-report/update
171641/171641 [==============================] - 26822s 156ms/step - loss: nan - acc: 0.0024 - top_5: 0.0037
Epoch 2/10

Epoch 00002: LearningRateScheduler setting learning rate to 0.00125.
171641/171641 [==============================] - 26525s 155ms/step - loss: nan - acc: 0.0015 - top_5: 0.0000e+00 - val_loss: nan - val_acc: 0.0018 - val_top_5: 0.0000e+00
Epoch 3/10

Epoch 00003: LearningRateScheduler setting learning rate to 0.0016666666666666668.
171641/171641 [==============================] - 26190s 153ms/step - loss: nan - acc: 0.0015 - top_5: 0.0000e+00 - val_loss: nan - val_acc: 0.0018 - val_top_5: 0.0000e+00
Epoch 4/10

Epoch 00004: LearningRateScheduler setting learning rate to 0.0025.
 18718/171641 [==>...........................] - ETA: 6:33:07 - loss: nan - acc: 0.0014 - top_5: 0.0000e+002021-07-23 09:56:18,385 - WARNING - Retrying (Retry(total=2, connect=None, read=None, redirect=None, status=None)) after connection broken by 'ReadTimeoutError("HTTPSConnectionPool(host='www.comet.ml', port=443): Read timed out. (read timeout=10)",)': /clientlib/status-report/update
 18811/171641 [==>...........................] - ETA: 6:32:51 - loss: nan - acc: 0.0014 - top_5: 0.0000e+002021-07-23 09:56:32,497 - WARNING - Retrying (Retry(total=1, connect=None, read=None, redirect=None, status=None)) after connection broken by 'ReadTimeoutError("HTTPSConnectionPool(host='www.comet.ml', port=443): Read timed out. (read timeout=10)",)': /clientlib/status-report/update
 23932/171641 [===>..........................] - ETA: 6:16:03 - loss: nan - acc: 0.0014 - top_5: 0.0000e+00

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
None yet
Projects
None yet
Development

No branches or pull requests

1 participant