跳转至

模型仓库

performance tested on Ascend 910(8p) with graph mode
model top-1 (%) top-5 (%) params(M) batch size cards ms/step jit_level recipe download
bit_resnet50 76.81 93.17 25.55 32 8 74.52 O2 yaml weights
cmt_small 83.24 96.41 26.09 128 8 500.64 O2 yaml weights
coat_tiny 79.67 94.88 5.50 32 8 207.74 O2 yaml weights
convit_tiny 73.66 91.72 5.71 256 8 231.62 O2 yaml weights
convnext_tiny 81.91 95.79 28.59 16 8 66.79 O2 yaml weights
convnextv2_tiny 82.43 95.98 28.64 128 8 400.20 O2 yaml weights
crossvit_9 73.56 91.79 8.55 256 8 550.79 O2 yaml weights
densenet121 75.64 92.84 8.06 32 8 43.28 O2 yaml weights
dpn92 79.46 94.49 37.79 32 8 78.22 O2 yaml weights
edgenext_xx_small 71.02 89.99 1.33 256 8 191.24 O2 yaml weights
efficientnet_b0 76.89 93.16 5.33 128 8 172.78 O2 yaml weights
ghostnet_050 66.03 86.64 2.60 128 8 211.13 O2 yaml weights
googlenet 72.68 90.89 6.99 32 8 21.40 O2 yaml weights
halonet_50t 79.53 94.79 22.79 64 8 421.66 O2 yaml weights
hrnet_w32 80.64 95.44 41.30 128 8 279.10 O2 yaml weights
inception_v3 79.11 94.40 27.20 32 8 76.42 O2 yaml weights
inception_v4 80.88 95.34 42.74 32 8 76.19 O2 yaml weights
mixnet_s 75.52 92.52 4.17 128 8 252.49 O2 yaml weights
mnasnet_075 71.81 90.53 3.20 256 8 165.43 O2 yaml weights
mobilenet_v1_025 53.87 77.66 0.47 64 8 42.43 O2 yaml weights
mobilenet_v2_075 69.98 89.32 2.66 256 8 155.94 O2 yaml weights
mobilenet_v3_small_100 68.10 87.86 2.55 75 8 48.14 O2 yaml weights
mobilenet_v3_large_100 75.23 92.31 5.51 75 8 47.49 O2 yaml weights
mobilevit_xx_small 68.91 88.91 1.27 64 8 53.52 O2 yaml weights
nasnet_a_4x1056 73.65 91.25 5.33 256 8 330.89 O2 yaml weights
pit_ti 72.96 91.33 4.85 128 8 271.50 O2 yaml weights
poolformer_s12 77.33 93.34 11.92 128 8 220.13 O2 yaml weights
pvt_tiny 74.81 92.18 13.23 128 8 229.63 O2 yaml weights
pvt_v2_b0 71.50 90.60 3.67 128 8 269.38 O2 yaml weights
regnet_x_800mf 76.04 92.97 7.26 64 8 42.49 O2 yaml weights
repmlp_t224 76.71 93.30 38.30 128 8 578.23 O2 yaml weights
repvgg_a0 72.19 90.75 9.13 32 8 20.58 O2 yaml weights
repvgg_a1 74.19 91.89 14.12 32 8 20.70 O2 yaml weights
res2net50 79.35 94.64 25.76 32 8 39.68 O2 yaml weights
resnest50 80.81 95.16 27.55 128 8 244.92 O2 yaml weights
resnet50 76.69 93.50 25.61 32 8 31.41 O2 yaml weights
resnetv2_50 76.90 93.37 25.60 32 8 32.66 O2 yaml weights
resnext50_32x4d 78.53 94.10 25.10 32 8 37.22 O2 yaml weights
rexnet_09 77.06 93.41 4.13 64 8 130.10 O2 yaml weights
seresnet18 71.81 90.49 11.80 64 8 44.40 O2 yaml weights
shufflenet_v1_g3_05 57.05 79.73 0.73 64 8 40.62 O2 yaml weights
shufflenet_v2_x0_5 60.53 82.11 1.37 64 8 41.87 O2 yaml weights
skresnet18 73.09 91.20 11.97 64 8 45.84 O2 yaml weights
squeezenet1_0 59.01 81.01 1.25 32 8 22.36 O2 yaml weights
swin_tiny 80.82 94.80 33.38 256 8 454.49 O2 yaml weights
swinv2_tiny_window8 81.42 95.43 28.78 128 8 317.19 O2 yaml weights
vgg13 72.87 91.02 133.04 32 8 55.20 O2 yaml weights
vgg19 75.21 92.56 143.66 32 8 67.42 O2 yaml weights
visformer_tiny 78.28 94.15 10.33 128 8 217.92 O2 yaml weights
vit_b_32_224 75.86 92.08 87.46 512 8 454.57 O2 yaml weights
volo_d1 82.59 95.99 27 128 8 270.79 O2 yaml weights
xception 79.01 94.25 22.91 32 8 92.78 O2 yaml weights
xcit_tiny_12_p16_224 77.67 93.79 7.00 128 8 252.98 O2 yaml weights
performance tested on Ascend 910*(8p) with graph mode
model top-1 (%) top-5 (%) params(M) batch size cards ms/step jit_level recipe download
convit_tiny 73.79 91.70 5.71 256 8 226.51 O2 yaml weights
convnext_tiny 81.28 95.61 28.59 16 8 48.7 O2 yaml weights
convnextv2_tiny 82.39 95.95 28.64 128 8 257.2 O2 yaml weights
crossvit_9 73.38 91.51 8.55 256 8 514.36 O2 yaml weights
densenet121 75.67 92.77 8.06 32 8 47.34 O2 yaml weights
edgenext_xx_small 70.64 89.75 1.33 256 8 239.38 O2 yaml weights
efficientnet_b0 76.88 93.28 5.33 128 8 172.64 O2 yaml weights
googlenet 72.89 90.89 6.99 32 8 23.5 O2 yaml weights
hrnet_w32 80.66 95.30 41.30 128 8 238.03 O2 yaml weights
inception_v3 79.25 94.47 27.20 32 8 70.83 O2 yaml weights
inception_v4 80.98 95.25 42.74 32 8 80.97 O2 yaml weights
mixnet_s 75.58 95.54 4.17 128 8 228.03 O2 yaml weights
mnasnet_075 71.77 90.52 3.20 256 8 175.85 O2 yaml weights
mobilenet_v1_025 54.05 77.74 0.47 64 8 47.47 O2 yaml weights
mobilenet_v2_075 69.73 89.35 2.66 256 8 174.65 O2 yaml weights
mobilenet_v3_small_100 68.07 87.77 2.55 75 8 52.38 O2 yaml weights
mobilenet_v3_large_100 75.59 92.57 5.51 75 8 55.89 O2 yaml weights
mobilevit_xx_small 67.11 87.85 1.27 64 8 67.24 O2 yaml weights
nasnet_a_4x1056 74.12 91.36 5.33 256 8 364.35 O2 yaml weights
pit_ti 73.26 91.57 4.85 128 8 266.47 O2 yaml weights
poolformer_s12 77.49 93.55 11.92 128 8 211.81 O2 yaml weights
pvt_tiny 74.88 92.12 13.23 128 8 237.5 O2 yaml weights
pvt_v2_b0 71.25 90.50 3.67 128 8 255.76 O2 yaml weights
regnet_x_800mf 76.11 93.00 7.26 64 8 50.74 O2 yaml weights
repvgg_a0 72.29 90.78 9.13 32 8 24.12 O2 yaml weights
repvgg_a1 73.68 91.51 14.12 32 8 28.29 O2 yaml weights
res2net50 79.33 94.64 25.76 32 8 39.6 O2 yaml weights
resnet50 76.76 93.31 25.61 32 8 31.9 O2 yaml weights
resnetv2_50 77.03 93.29 25.60 32 8 32.19 O2 yaml weights
resnext50_32x4d 78.64 94.18 25.10 32 8 44.61 O2 yaml weights
rexnet_09 76.14 92.96 4.13 64 8 115.61 O2 yaml weights
seresnet18 72.05 90.59 11.80 64 8 51.09 O2 yaml weights
shufflenet_v1_g3_05 57.08 79.89 0.73 64 8 47.77 O2 yaml weights
shufflenet_v2_x0_5 60.65 82.26 1.37 64 8 47.32 O2 yaml weights
skresnet18 72.85 90.83 11.97 64 8 49.83 O2 yaml weights
squeezenet1_0 58.75 80.76 1.25 32 8 23.48 O2 yaml weights
swin_tiny 80.90 94.90 33.38 256 8 466.6 O2 yaml weights
swinv2_tiny_window8 81.38 95.46 28.78 128 8 335.18 O2 yaml weights
vgg13 72.81 91.02 133.04 32 8 30.52 O2 yaml weights
vgg19 75.24 92.55 143.66 32 8 39.17 O2 yaml weights
visformer_tiny 78.40 94.30 10.33 128 8 201.14 O2 yaml weights
xcit_tiny_12_p16_224 77.27 93.56 7.00 128 8 229.25 O2 yaml weights

Notes

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