update results and add benchmark artifacts

-- updated the results-imagenet.csv to contain latest results of simplenet variants so far
-- added the benchmark results for inference with fp32, NHWC for both pytorch 1.10 and 1.11
for better comparison, accuracies have been added to the benchmark results.

The hardware and software stack used to run benchmark is as follows:
OS: Ubuntu 20.04.4
kernel version: 5.13.0-51-generic
Driver version: 515.86.01
Python version: 3.9.7 (anaconda installation)
GPU: GTX1080
CPU: 4790K
RAM: 32Gig

ImageNet/training_scripts/imagenet_training/model_list_normal.txt

@@ -0,0 +1,46 @@
+mobilenetv3_rw
+tf_mobilenetv3_large_100
+mobilenetv2_100
+tf_mobilenetv3_large_minimal_100
+mobilenetv2_110d
+mobilenetv3_large_100
+tf_mobilenetv3_large_075
+efficientnet_lite0
+tf_efficientnet_lite0
+densenet121
+tv_densenet121
+mnasnet_100
+dla34
+tinynet_b
+tf_mixnet_s
+ghostnet_100
+crossvit_9_240
+regnetx_006
+vit_base_patch32_224_sam
+resnest14d
+tv_resnet34
+swsl_resnet18
+resnet26
+resnet34
+legacy_seresnet18
+resnet18
+gluon_resnet18_v1b
+resnet18d
+deit_tiny_patch16_224
+mixer_l16_224
+vit_tiny_r_s16_p8_224
+repvgg_b0
+vgg13_bn
+vgg16
+vgg11_bn
+vgg13
+vgg11
+vgg19
+vgg16_bn
+vgg19_bn
+simplenetv1_5m_m1
+simplenetv1_5m_m2
+simplenetv1_9m_m1
+simplenetv1_9m_m2
+simplenetv1_small_m1_075
+simplenetv1_small_m2_075

ImageNet/training_scripts/imagenet_training/model_list_normal_known.txt

@@ -0,0 +1,37 @@
+simplenetv1_5m_m1
+simplenetv1_5m_m2
+simplenetv1_9m_m1
+simplenetv1_9m_m2
+simplenetv1_small_m1_075
+simplenetv1_small_m2_075
+mobilenetv3_large_100
+mobilenetv2_100
+densenet121
+tf_mobilenetv3_large_100
+efficientnet_lite0
+resnet26
+resnet34
+mobilenetv2_110d
+tinynet_b
+tf_efficientnet_lite0
+mnasnet_100
+dla34
+ghostnet_100
+crossvit_9_240
+regnetx_006
+vit_base_patch32_224_sam
+tf_mobilenetv3_large_075
+tf_mobilenetv3_large_minimal_100
+deit_tiny_patch16_224
+vit_tiny_r_s16_p8_224
+repvgg_b0
+vgg19_bn
+vgg19
+vgg13_bn
+vgg16_bn
+vgg16
+vgg11_bn
+vgg13
+vgg11
+resnet18
+

ImageNet/training_scripts/imagenet_training/model_list_small.txt

@@ -0,0 +1,16 @@
+tf_mobilenetv3_small_100
+dla60x_c
+mobilenetv3_small_100
+mnasnet_small
+dla46x_c
+mobilenetv2_050
+tf_mobilenetv3_small_075
+mobilenetv3_small_075
+dla46_c
+lcnet_050
+tf_mobilenetv3_small_minimal_100
+mobilenetv3_small_050
+simplenetv1_small_m1_05
+simplenetv1_small_m2_05
+simplenetv1_small_m1_075
+simplenetv1_small_m2_075

ImageNet/training_scripts/imagenet_training/results/add_acc_to_benchmarks.py

@@ -0,0 +1,32 @@
+import pandas as pd
+import argparse
+
+parser = argparse.ArgumentParser(description="A small utility to merge model accuracy with timm benchmarks")
+parser.add_argument(
+    "--imagenet-results",
+    default="./results-imagenet.csv",
+    type=str,
+    metavar="FILENAME",
+    help="the imagenet results csv file to get the accuracies from",
+)
+parser.add_argument(
+    "--bench-csv",
+    default="./benchmark_inference_GTX1080_fp32_small_torch1.10.csv",
+    type=str,
+    metavar="FILENAME",
+    help="the csv file for which you want to add accuracy",
+)
+
+
+def add_acc_to_csv(imagenet_results, csv_filename):
+    df_imagenet_results = pd.read_csv(imagenet_results)
+    df_imagenet_accs = df_imagenet_results[["model", "top1", "top5"]]
+    df_csv = pd.read_csv(csv_filename)
+    df_csv_acc = pd.merge(df_csv, df_imagenet_accs, on=["model"])
+    df_csv_acc.to_csv(csv_filename.replace(".csv", "_with_accuracy.csv"), index=False)
+    print(f"{csv_filename} is done")
+
+
+if __name__ == "__main__":
+    args = parser.parse_args()
+    add_acc_to_csv(args.imagenet_results, args.bench_csv)

ImageNet/training_scripts/imagenet_training/results/benchmark_inference_GTX1080_fp32_normal_known_torch1.10.csv

@@ -0,0 +1,37 @@
+model,infer_samples_per_sec,infer_step_time,infer_batch_size,infer_img_size,infer_gmacs,infer_macts,param_count
+vit_tiny_r_s16_p8_224,1809.8,141.431,256,224,0.44,2.06,6.34
+simplenetv1_small_m1_075,1498.12,170.855,256,224,0.83,1.56,3.29
+simplenetv1_small_m2_075,1222.18,209.433,256,224,1.02,1.79,3.29
+simplenetv1_5m_m1,1034.1,247.529,256,224,1.46,2.09,5.75
+deit_tiny_patch16_224,910.68,281.08,256,224,1.26,5.97,5.72
+resnet18,832.07,307.634,256,224,1.82,2.48,11.69
+simplenetv1_5m_m2,818.45,312.755,256,224,1.81,2.39,5.75
+vit_base_patch32_224_sam,550.96,464.615,256,224,4.41,5.01,88.22
+crossvit_9_240,540.26,473.812,256,240,1.85,9.52,8.55
+tinynet_b,530.52,482.515,256,188,0.21,4.44,3.73
+resnet26,519.5,492.742,256,224,2.36,7.35,16.0
+tf_mobilenetv3_large_075,505.34,506.555,256,224,0.16,4.0,3.99
+regnetx_006,475.48,538.373,256,224,0.61,3.98,6.2
+resnet34,456.22,561.098,256,224,3.67,3.74,21.8
+simplenetv1_9m_m1,455.52,561.959,256,224,2.96,3.41,9.51
+dla34,441.47,579.845,256,224,3.07,5.02,15.74
+repvgg_b0,434.24,589.509,256,224,3.41,6.15,15.82
+ghostnet_100,406.6,629.583,256,224,0.15,3.55,5.18
+tf_mobilenetv3_large_minimal_100,406.07,630.397,256,224,0.22,4.4,3.92
+mobilenetv3_large_100,399.88,640.158,256,224,0.23,4.41,5.48
+tf_mobilenetv3_large_100,387.42,660.742,256,224,0.23,4.41,5.48
+simplenetv1_9m_m2,387.08,661.332,256,224,3.74,3.86,9.51
+mobilenetv2_100,294.32,869.767,256,224,0.31,6.68,3.5
+densenet121,271.19,943.952,256,224,2.87,6.9,7.98
+vgg11,265.22,965.196,256,224,7.61,7.44,132.86
+mnasnet_100,261.47,979.059,256,224,0.33,5.46,4.38
+vgg11_bn,252.21,507.471,128,224,7.62,7.44,132.87
+mobilenetv2_110d,230.59,1110.181,256,224,0.45,8.71,4.52
+efficientnet_lite0,223.51,1145.336,256,224,0.4,6.74,4.65
+tf_efficientnet_lite0,219.46,1166.486,256,224,0.4,6.74,4.65
+vgg13,140.34,912.059,128,224,11.31,12.25,133.05
+vgg13_bn,132.22,968.059,128,224,11.33,12.25,133.05
+vgg16,115.5,1108.21,128,224,15.47,13.56,138.36
+vgg16_bn,109.38,1170.163,128,224,15.5,13.56,138.37
+vgg19,98.14,1304.284,128,224,19.63,14.86,143.67
+vgg19_bn,93.53,1368.463,128,224,19.66,14.86,143.68

ImageNet/training_scripts/imagenet_training/results/benchmark_inference_GTX1080_fp32_normal_known_torch1.10_with_accuracy.csv

@@ -0,0 +1,37 @@
+model,infer_samples_per_sec,infer_step_time,infer_batch_size,infer_img_size,infer_gmacs,infer_macts,param_count,top1,top5
+vit_tiny_r_s16_p8_224,1809.8,141.431,256,224,0.44,2.06,6.34,71.792,90.822
+simplenetv1_small_m1_075,1498.12,170.855,256,224,0.83,1.56,3.29,67.764,87.66
+simplenetv1_small_m2_075,1222.18,209.433,256,224,1.02,1.79,3.29,68.15,87.762
+simplenetv1_5m_m1,1034.1,247.529,256,224,1.46,2.09,5.75,71.37,90.1
+deit_tiny_patch16_224,910.68,281.08,256,224,1.26,5.97,5.72,72.172,91.114
+resnet18,832.07,307.634,256,224,1.82,2.48,11.69,69.744,89.082
+simplenetv1_5m_m2,818.45,312.755,256,224,1.81,2.39,5.75,71.936,90.3
+vit_base_patch32_224_sam,550.96,464.615,256,224,4.41,5.01,88.22,73.694,91.01
+crossvit_9_240,540.26,473.812,256,240,1.85,9.52,8.55,73.96,91.968
+tinynet_b,530.52,482.515,256,188,0.21,4.44,3.73,74.976,92.184
+resnet26,519.5,492.742,256,224,2.36,7.35,16.0,75.3,92.578
+tf_mobilenetv3_large_075,505.34,506.555,256,224,0.16,4.0,3.99,73.436,91.344
+regnetx_006,475.48,538.373,256,224,0.61,3.98,6.2,73.86,91.672
+resnet34,456.22,561.098,256,224,3.67,3.74,21.8,75.114,92.284
+simplenetv1_9m_m1,455.52,561.959,256,224,2.96,3.41,9.51,73.376,91.048
+dla34,441.47,579.845,256,224,3.07,5.02,15.74,74.62,92.072
+repvgg_b0,434.24,589.509,256,224,3.41,6.15,15.82,75.16,92.418
+ghostnet_100,406.6,629.583,256,224,0.15,3.55,5.18,73.974,91.46
+tf_mobilenetv3_large_minimal_100,406.07,630.397,256,224,0.22,4.4,3.92,72.25,90.63
+mobilenetv3_large_100,399.88,640.158,256,224,0.23,4.41,5.48,75.766,92.544
+tf_mobilenetv3_large_100,387.42,660.742,256,224,0.23,4.41,5.48,75.518,92.604
+simplenetv1_9m_m2,387.08,661.332,256,224,3.74,3.86,9.51,74.17,91.614
+mobilenetv2_100,294.32,869.767,256,224,0.31,6.68,3.5,72.97,91.02
+densenet121,271.19,943.952,256,224,2.87,6.9,7.98,75.584,92.652
+vgg11,265.22,965.196,256,224,7.61,7.44,132.86,69.028,88.626
+mnasnet_100,261.47,979.059,256,224,0.33,5.46,4.38,74.658,92.112
+vgg11_bn,252.21,507.471,128,224,7.62,7.44,132.87,70.36,89.802
+mobilenetv2_110d,230.59,1110.181,256,224,0.45,8.71,4.52,75.038,92.184
+efficientnet_lite0,223.51,1145.336,256,224,0.4,6.74,4.65,75.476,92.512
+tf_efficientnet_lite0,219.46,1166.486,256,224,0.4,6.74,4.65,74.832,92.174
+vgg13,140.34,912.059,128,224,11.31,12.25,133.05,69.926,89.246
+vgg13_bn,132.22,968.059,128,224,11.33,12.25,133.05,71.594,90.376
+vgg16,115.5,1108.21,128,224,15.47,13.56,138.36,71.59,90.382
+vgg16_bn,109.38,1170.163,128,224,15.5,13.56,138.37,73.35,91.504
+vgg19,98.14,1304.284,128,224,19.63,14.86,143.67,72.366,90.87
+vgg19_bn,93.53,1368.463,128,224,19.66,14.86,143.68,74.214,91.848

ImageNet/training_scripts/imagenet_training/results/benchmark_inference_GTX1080_fp32_normal_known_torch1.11.csv

@@ -0,0 +1,37 @@
+model,infer_samples_per_sec,infer_step_time,infer_batch_size,infer_img_size,infer_gmacs,infer_macts,param_count
+vit_tiny_r_s16_p8_224,1882.23,135.988,256,224,0.44,2.06,6.34
+simplenetv1_small_m1_075,1516.74,168.762,256,224,0.83,1.56,3.29
+simplenetv1_small_m2_075,1260.89,203.01,256,224,1.02,1.79,3.29
+simplenetv1_5m_m1,1107.7,231.088,256,224,1.46,2.09,5.75
+deit_tiny_patch16_224,991.41,258.198,256,224,1.26,5.97,5.72
+resnet18,876.92,291.907,256,224,1.82,2.48,11.69
+simplenetv1_5m_m2,835.17,306.502,256,224,1.81,2.39,5.75
+crossvit_9_240,602.13,425.137,256,240,1.85,9.52,8.55
+vit_base_patch32_224_sam,571.37,448.024,256,224,4.41,5.01,88.22
+tinynet_b,530.15,482.86,256,188,0.21,4.44,3.73
+resnet26,524.36,488.193,256,224,2.36,7.35,16.0
+tf_mobilenetv3_large_075,505.13,506.778,256,224,0.16,4.0,3.99
+resnet34,491.96,520.334,256,224,3.67,3.74,21.8
+regnetx_006,478.41,535.075,256,224,0.61,3.98,6.2
+dla34,472.49,541.773,256,224,3.07,5.02,15.74
+simplenetv1_9m_m1,459.21,557.458,256,224,2.96,3.41,9.51
+repvgg_b0,455.36,562.169,256,224,3.41,6.15,15.82
+ghostnet_100,407.03,628.922,256,224,0.15,3.55,5.18
+tf_mobilenetv3_large_minimal_100,406.84,629.211,256,224,0.22,4.4,3.92
+mobilenetv3_large_100,402.08,636.663,256,224,0.23,4.41,5.48
+simplenetv1_9m_m2,389.94,656.492,256,224,3.74,3.86,9.51
+tf_mobilenetv3_large_100,388.3,659.264,256,224,0.23,4.41,5.48
+mobilenetv2_100,295.68,865.772,256,224,0.31,6.68,3.5
+densenet121,293.94,870.881,256,224,2.87,6.9,7.98
+mnasnet_100,262.25,976.131,256,224,0.33,5.46,4.38
+vgg11,260.38,983.145,256,224,7.61,7.44,132.86
+vgg11_bn,248.92,514.193,128,224,7.62,7.44,132.87
+mobilenetv2_110d,230.8,1109.144,256,224,0.45,8.71,4.52
+efficientnet_lite0,224.81,1138.729,256,224,0.4,6.74,4.65
+tf_efficientnet_lite0,219.93,1163.953,256,224,0.4,6.74,4.65
+vgg13,154.03,830.996,128,224,11.31,12.25,133.05
+vgg13_bn,144.39,886.483,128,224,11.33,12.25,133.05
+vgg16,123.7,1034.687,128,224,15.47,13.56,138.36
+vgg16_bn,117.06,1093.467,128,224,15.5,13.56,138.37
+vgg19,103.71,1234.193,128,224,19.63,14.86,143.67
+vgg19_bn,98.59,1298.317,128,224,19.66,14.86,143.68