Skip to content

Latest commit

 

History

History
114 lines (107 loc) · 37.7 KB

benchmark_results.md

File metadata and controls

114 lines (107 loc) · 37.7 KB
performance tested on Ascend 910(8p) with graph mode
model name params(M) cards batch size resolution jit level graph compile ms/step img/s acc@top1 acc@top5 recipe weight
bit_resnet50 25.55 8 32 224x224 O2 146s 74.52 3413.33 76.81 93.17 yaml weights
cmt_small 26.09 8 128 224x224 O2 1268s 500.64 2048.01 83.24 96.41 yaml weights
coat_tiny 5.50 8 32 224x224 O2 543s 254.95 1003.92 79.67 94.88 yaml weights
convit_tiny 5.71 8 256 224x224 O2 133s 231.62 8827.59 73.66 91.72 yaml weights
convnext_tiny 28.59 8 16 224x224 O2 127s 66.79 1910.45 81.91 95.79 yaml weights
convnextv2_tiny 28.64 8 128 224x224 O2 237s 400.20 2560.00 82.43 95.98 yaml weights
crossvit_9 8.55 8 256 240x240 O2 206s 550.79 3719.30 73.56 91.79 yaml weights
densenet121 8.06 8 32 224x224 O2 191s 43.28 5914.97 75.64 92.84 yaml weights
dpn92 37.79 8 32 224x224 O2 293s 78.22 3272.82 79.46 94.49 yaml weights
dpn92 37.79 8 32 224x224 O2 293s 78.22 3272.82 79.46 94.49 yaml weights
efficientnet_b0 5.33 8 128 224x224 O2 203s 172.78 5926.61 76.89 93.16 yaml weights
ghostnet_050 2.60 8 128 224x224 O2 383s 211.13 4850.09 66.03 86.64 yaml weights
googlenet 6.99 8 32 224x224 O2 72s 21.40 11962.62 72.68 90.89 yaml weights
halonet_50t 22.79 8 64 256x256 O2 261s 421.66 6437.82 79.53 94.79 yaml weights
hrnet_w32 41.30 128 8 224x224 O2 1312s 279.10 3668.94 80.64 95.44 yaml weights
inception_v3 27.20 8 32 299x299 O2 120s 76.42 3349.91 79.11 94.40 yaml weights
inception_v4 42.74 8 32 299x299 O2 177s 76.19 3360.02 80.88 95.34 yaml weights
mixnet_s 4.17 8 128 224x224 O2 556s 252.49 4055.61 75.52 92.52 yaml weights
mnasnet_075 3.20 8 256 224x224 O2 140s 165.43 12379.86 71.81 90.53 yaml weights
mobilenet_v1_025 0.47 8 64 224x224 O2 89s 42.43 12066.93 53.87 77.66 yaml weights
mobilenet_v2_075 2.66 8 256 224x224 O2 164s 155.94 13133.26 69.98 89.32 yaml weights
mobilenet_v3_small_100 2.55 8 75 224x224 O2 145s 48.14 12463.65 68.10 87.86 yaml weights
mobilenet_v3_large_100 5.51 8 75 224x224 O2 271s 47.49 12634.24 75.23 92.31 yaml weights
mobilevit_xx_small 1.27 64 8 256x256 O2 301s 53.52 9566.52 68.91 88.91 yaml weights
nasnet_a_4x1056 5.33 8 256 224x224 O2 656s 330.89 6189.37 73.65 91.25 yaml weights
pit_ti 4.85 8 128 224x224 O2 192s 271.50 3771.64 72.96 91.33 yaml weights
poolformer_s12 11.92 8 128 224x224 O2 118s 220.13 4651.80 77.33 93.34 yaml weights
pvt_tiny 13.23 8 128 224x224 O2 192s 229.63 4459.35 74.81 92.18 yaml weights
pvt_v2_b0 3.67 8 128 224x224 O2 269s 269.38 3801.32 71.50 90.60 yaml weights
regnet_x_800mf 7.26 8 64 224x224 O2 99s 42.49 12049.89 76.04 92.97 yaml weights
repmlp_t224 38.30 8 128 224x224 O2 289s 578.23 1770.92 76.71 93.30 yaml weights
repvgg_a0 9.13 8 32 224x224 O2 50s
 20.58 12439.26 72.19 90.75 yaml weights
repvgg_a1 14.12 8 32 224x224 O2 29s 20.70 12367.15 74.19 91.89 yaml weights
res2net50 25.76 8 32 224x224 O2 119s 39.68 6451.61 79.35 94.64 yaml weights
resnest50 27.55 8 128 224x224 O2 83s 244.92 4552.73 80.81 95.16 yaml weights
resnet50 25.61 8 32 224x224 O2 43s 31.41 8150.27 76.69 93.50 yaml weights
resnetv2_50 25.60 8 32 224x224 O2 52s 32.66 7838.33 76.90 93.37 yaml weights
resnext50_32x4d 25.10 8 32 224x224 O2 49s 37.22 6878.02 78.53 94.10 yaml weights
rexnet_09 4.13 8 64 224x224 O2 462s 130.10 3935.43 77.06 93.41 yaml weights
seresnet18 11.80 8 64 224x224 O2 43s 44.40 11531.53 71.81 90.49 yaml weights
shufflenet_v1_g3_05 0.73 8 64 224x224 O2 169s 40.62 12604.63 57.05 79.73 yaml weights
shufflenet_v2_x0_5 1.37 8 64 224x224 O2 62s 41.87 12228.33 60.53 82.11 yaml weights
skresnet18 11.97 8 64 224x224 O2 60s 45.84 11169.28 73.09 91.20 yaml weights
squeezenet1_0 1.25 8 32 224x224 O2 45s 22.36 11449.02 58.67 80.61 yaml weights
swin_tiny 33.38 8 256 224x224 O2 226s 454.49 4506.15 80.82 94.80 yaml weights
swinv2_tiny_window8 28.78 8 128 256x256 O2 273s 317.19 3228.35 81.42 95.43 yaml weights
vgg13 133.04 8 32 224x224 O2 23s 55.20 4637.68 72.87 91.02 yaml weights
vgg19 143.66 8 32 224x224 O2 22s 67.42 3797.09 75.21 92.56 yaml weights
visformer_tiny 10.33 8 128 224x224 O2 137s 217.92 4698.97 78.28 94.15 yaml weights
volo_d1 27 8 128 224x224 O2 275s 270.79 3781.53 82.59 95.99 yaml weights
xception 22.91 8 32 299x299 O2 161s 96.78 2645.17 79.01 94.25 yaml weights
xcit_tiny_12_p16_224 7.00 8 128 224x224 O2 382s 252.98 4047.75 77.67 93.79 yaml weights
performance tested on Ascend Atlas 800T A2 machines with graph mode
model name params(M) cards batch size resolution jit level graph compile ms/step img/s acc@top1 acc@top5 recipe weight
convit_tiny 5.71 8 256 224x224 O2 153s 226.51 9022.03 73.79 91.70 yaml weights
convnext_tiny 28.59 8 16 224x224 O2 137s 48.7 2612.24 81.28 95.61 yaml weights
convnextv2_tiny 28.64 8 128 224x224 O2 268s 257.2 3984.44 82.39 95.95 yaml weights
crossvit_9 8.55 8 256 240x240 O2 221s 514.36 3984.44 73.38 91.51 yaml weights
densenet121 8.06 8 32 224x224 O2 300s 47,34 5446.81 75.67 92.77 yaml weights
densenet121 8.06 8 32 224x224 O2 300s 47,34 5446.81 75.67 92.77 yaml weights
efficientnet_b0 5.33 8 128 224x224 O2 353s 172.64 5931.42 76.88 93.28 yaml weights
googlenet 6.99 8 32 224x224 O2 113s 23.5 10893.62 72.89 90.89 yaml weights
googlenet 6.99 8 32 224x224 O2 113s 23.5 10893.62 72.89 90.89 yaml weights
inception_v3 27.20 8 32 299x299 O2 172s 70.83 3614.29 79.25 94.47 yaml weights
inception_v4 42.74 8 32 299x299 O2 263s 80.97 3161.66 80.98 95.25 yaml weights
mixnet_s 4.17 8 128 224x224 O2 706s 228.03 4490.64 75.58 95.54 yaml weights
mnasnet_075 3.20 8 256 224x224 O2 144s 175.85 11646.29 71.77 90.52 yaml weights
mobilenet_v1_025 0.47 8 64 224x224 O2 195s 47.47 10785.76 54.05 77.74 yaml weights
mobilenet_v2_075 2.66 8 256 224x224 O2 233s 174.65 11726.31 69.73 89.35 yaml weights
mobilenet_v3_small_100 2.55 8 75 224x224 O2 184s 52.38 11454.75 68.07 87.77 yaml weights
mobilenet_v3_large_100 5.51 8 75 224x224 O2 354s 55.89 10735.37 75.59 92.57 yaml weights
mobilevit_xx_small 1.27 8 64 256x256 O2 437s 67.24 7614.52 67.11 87.85 yaml weights
nasnet_a_4x1056 5.33 8 256 224x224 O2 800s 364.35 5620.97 74.12 91.36 yaml weights
pit_ti 4.85 8 128 224x224 O2 212s 266.47 3842.83 73.26 91.57 yaml weights
poolformer_s12 11.92 8 128 224x224 O2 177s 211.81 4834.52 77.49 93.55 yaml weights
pvt_tiny 13.23 8 128 224x224 O2 212s 237.5 4311.58 74.88 92.12 yaml weights
pvt_v2_b0 3.67 8 128 224x224 O2 323s 255.76 4003.75 71.25 90.50 yaml weights
regnet_x_800mf 7.26 8 64 224x224 O2 228s 50.74 10090.66 76.11 93.00 yaml weights
repmlp_t224 38.30 8 128 224x224 O2 289s 578.23 1770.92 76.71 93.30 yaml weights
repvgg_a0 9.13 8 32 224x224 O2 76s 24.12 10613.60 72.29 90.78 yaml weights
repvgg_a1 14.12 8 32 224x224 O2 81s 28.29 9096.13 73.68 91.51 yaml weights
res2net50 25.76 8 32 224x224 O2 174s 39.6 6464.65 79.33 94.64 yaml weights
resnet50 25.61 8 32 224x224 O2 77s 31.9 8025.08 76.76 93.31 yaml weights
resnetv2_50 25.60 8 32 224x224 O2 120s 32.19 7781.16 77.03 93.29 yaml weights
resnext50_32x4d 25.10 8 32 224x224 O2 156s 44.61 5738.62 78.64 94.18 yaml weights
rexnet_09 4.13 8 64 224x224 O2 515s 115.61 3290.28 76.14 92.96 yaml weights
seresnet18 11.80 8 64 224x224 O2 90s 51.09 10021.53 72.05 90.59 yaml weights
shufflenet_v1_g3_05 0.73 8 64 224x224 O2 191s 47.77 10718.02 57.08 79.89 yaml weights
shufflenet_v2_x0_5 1.37 8 64 224x224 O2 100s 47.32 10819.95 60.65 82.26 yaml weights
skresnet18 11.97 8 64 224x224 O2 134s 49.83 10274.93 72.85 90.83 yaml weights
squeezenet1_0 1.25 8 32 224x224 O2 64s 23.48 10902.90 58.75 80.76 yaml weights
swin_tiny 33.38 8 256 224x224 O2 266s 466.6 4389.20 80.90 94.90 yaml weights
swinv2_tiny_window8 28.78 8 128 256x256 O2 385s 335.18 3055.07 81.38 95.46 yaml weights
vgg13 133.04 8 32 224x224 O2 41s 30.52 8387.94 72.81 91.02 yaml weights
vgg19 143.66 8 32 224x224 O2 53s 39.17 6535.61 75.24 92.55 yaml weights
visformer_tiny 10.33 8 128 224x224 O2 169s 201.14 5090.98 78.40 94.30 yaml weights
xcit_tiny_12_p16_224 7.00 8 128 224x224 O2 330s 229.25 4466.74 77.27 93.56 yaml weights

Notes

  • top-1 and top-5: Accuracy reported on the validation set of ImageNet-1K.