Skip to content

Model Zoo

Model Context Top-1 (%) Top-5 (%) Params(M) Recipe Download
bit_resnet50 D910x8-G 76.81 93.17 25.55 yaml weights
bit_resnet50x3 D910x8-G 80.63 95.12 217.31 yaml weights
bit_resnet101 D910x8-G 77.93 93.75 44.54 yaml weights
cmt_small D910x8-G 83.24 96.41 26.09 yaml weights
coat_lite_tiny D910x8-G 77.35 93.43 5.72 yaml weights
coat_lite_mini D910x8-G 78.51 93.84 11.01 yaml weights
coat_tiny D910x8-G 79.67 94.88 5.50 yaml weights
coat_mini D910x8-G 81.08 95.34 10.34 yaml weights
convit_tiny D910x8-G 73.66 91.72 5.71 yaml weights
convit_tiny_plus D910x8-G 77.00 93.60 9.97 yaml weights
convit_small D910x8-G 81.63 95.59 27.78 yaml weights
convit_small_plus D910x8-G 81.80 95.42 48.98 yaml weights
convit_base D910x8-G 82.10 95.52 86.54 yaml weights
convit_base_plus D910x8-G 81.96 95.04 153.13 yaml weights
convnext_tiny D910x64-G 81.91 95.79 28.59 yaml weights
convnext_small D910x64-G 83.40 96.36 50.22 yaml weights
convnext_base D910x64-G 83.32 96.24 88.59 yaml weights
convnextv2_tiny D910x8-G 82.43 95.98 28.64 yaml weights
crossvit_9 D910x8-G 73.56 91.79 8.55 yaml weights
crossvit_15 D910x8-G 81.08 95.33 27.27 yaml weights
crossvit_18 D910x8-G 81.93 95.75 43.27 yaml weights
densenet121 D910x8-G 75.64 92.84 8.06 yaml weights
densenet161 D910x8-G 79.09 94.66 28.90 yaml weights
densenet169 D910x8-G 77.26 93.71 14.31 yaml weights
densenet201 D910x8-G 78.14 94.08 20.24 yaml weights
dpn92 D910x8-G 79.46 94.49 37.79 yaml weights
dpn98 D910x8-G 79.94 94.57 61.74 yaml weights
dpn107 D910x8-G 80.05 94.74 87.13 yaml weights
dpn131 D910x8-G 80.07 94.72 79.48 yaml weights
edgenext_xx_small D910x8-G 71.02 89.99 1.33 yaml weights
edgenext_x_small D910x8-G 75.14 92.50 2.34 yaml weights
edgenext_small D910x8-G 79.15 94.39 5.59 yaml weights
edgenext_base D910x8-G 82.24 95.94 18.51 yaml weights
efficientnet_b0 D910x64-G 76.89 93.16 5.33 yaml weights
efficientnet_b1 D910x64-G 78.95 94.34 7.86 yaml weights
ghostnet_050 D910x8-G 66.03 86.64 2.60 yaml weights
ghostnet_100 D910x8-G 73.78 91.66 5.20 yaml weights
ghostnet_130 D910x8-G 75.50 92.56 7.39 yaml weights
googlenet D910x8-G 72.68 90.89 6.99 yaml weights
halonet_50t D910X8-G 79.53 94.79 22.79 yaml weights
hrnet_w32 D910x8-G 80.64 95.44 41.30 yaml weights
hrnet_w48 D910x8-G 81.19 95.69 77.57 yaml weights
inception_v3 D910x8-G 79.11 94.40 27.20 yaml weights
inception_v4 D910x8-G 80.88 95.34 42.74 yaml weights
mixnet_s D910x8-G 75.52 92.52 4.17 yaml weights
mixnet_m D910x8-G 76.64 93.05 5.06 yaml weights
mixnet_l D910x8-G 78.73 94.31 7.38 yaml weights
mnasnet_050 D910x8-G 68.07 88.09 2.14 yaml weights
mnasnet_075 D910x8-G 71.81 90.53 3.20 yaml weights
mnasnet_100 D910x8-G 74.28 91.70 4.42 yaml weights
mnasnet_130 D910x8-G 75.65 92.64 6.33 yaml weights
mnasnet_140 D910x8-G 76.01 92.83 7.16 yaml weights
mobilenet_v1_025 D910x8-G 53.87 77.66 0.47 yaml weights
mobilenet_v1_050 D910x8-G 65.94 86.51 1.34 yaml weights
mobilenet_v1_075 D910x8-G 70.44 89.49 2.60 yaml weights
mobilenet_v1_100 D910x8-G 72.95 91.01 4.25 yaml weights
mobilenet_v2_075 D910x8-G 69.98 89.32 2.66 yaml weights
mobilenet_v2_100 D910x8-G 72.27 90.72 3.54 yaml weights
mobilenet_v2_140 D910x8-G 75.56 92.56 6.15 yaml weights
mobilenet_v3_small_100 D910x8-G 68.10 87.86 2.55 yaml weights
mobilenet_v3_large_100 D910x8-G 75.23 92.31 5.51 yaml weights
mobilevit_xx_small D910x8-G 68.91 88.91 1.27 yaml weights
mobilevit_x_small D910x8-G 74.99 92.32 2.32 yaml weights
mobilevit_small D910x8-G 78.47 94.18 5.59 yaml weights
nasnet_a_4x1056 D910x8-G 73.65 91.25 5.33 yaml weights
pit_ti D910x8-G 72.96 91.33 4.85 yaml weights
pit_xs D910x8-G 78.41 94.06 10.61 yaml weights
pit_s D910x8-G 80.56 94.80 23.46 yaml weights
pit_b D910x8-G 81.87 95.04 73.76 yaml weights
poolformer_s12 D910x8-G 77.33 93.34 11.92 yaml weights
pvt_tiny D910x8-G 74.81 92.18 13.23 yaml weights
pvt_small D910x8-G 79.66 94.71 24.49 yaml weights
pvt_medium D910x8-G 81.82 95.81 44.21 yaml weights
pvt_large D910x8-G 81.75 95.70 61.36 yaml weights
pvt_v2_b0 D910x8-G 71.50 90.60 3.67 yaml weights
pvt_v2_b1 D910x8-G 78.91 94.49 14.01 yaml weights
pvt_v2_b2 D910x8-G 81.99 95.74 25.35 yaml weights
pvt_v2_b3 D910x8-G 82.84 96.24 45.24 yaml weights
pvt_v2_b4 D910x8-G 83.14 96.27 62.56 yaml weights
regnet_x_200mf D910x8-G 68.74 88.38 2.68 yaml weights
regnet_x_400mf D910x8-G 73.16 91.35 5.16 yaml weights
regnet_x_600mf D910x8-G 74.34 92.00 6.20 yaml weights
regnet_x_800mf D910x8-G 76.04 92.97 7.26 yaml weights
regnet_y_200mf D910x8-G 70.30 89.61 3.16 yaml weights
regnet_y_400mf D910x8-G 73.91 91.84 4.34 yaml weights
regnet_y_600mf D910x8-G 75.69 92.50 6.06 yaml weights
regnet_y_800mf D910x8-G 76.52 93.10 6.26 yaml weights
regnet_y_16gf D910x8-G 82.92 96.29 83.71 yaml weights
repmlp_t224 D910x8-G 76.71 93.30 38.30 yaml weights
repvgg_a0 D910x8-G 72.19 90.75 9.13 yaml weights
repvgg_a1 D910x8-G 74.19 91.89 14.12 yaml weights
repvgg_a2 D910x8-G 76.63 93.42 28.25 yaml weights
repvgg_b0 D910x8-G 74.99 92.40 15.85 yaml weights
repvgg_b1 D910x8-G 78.81 94.37 57.48 yaml weights
repvgg_b2 D910x64-G 79.29 94.66 89.11 yaml weights
repvgg_b3 D910x64-G 80.46 95.34 123.19 yaml weights
repvgg_b1g2 D910x8-G 78.03 94.09 45.85 yaml weights
repvgg_b1g4 D910x8-G 77.64 94.03 40.03 yaml weights
repvgg_b2g4 D910x8-G 78.8 94.36 61.84 yaml weights
res2net50 D910x8-G 79.35 94.64 25.76 yaml weights
res2net101 D910x8-G 79.56 94.70 45.33 yaml weights
res2net50_v1b D910x8-G 80.32 95.09 25.77 yaml weights
res2net101_v1b D910x8-G 81.14 95.41 45.35 yaml weights
resnest50 D910x8-G 80.81 95.16 27.55 yaml weights
resnest101 D910x8-G 82.90 96.12 48.41 yaml weights
resnet18 D910x8-G 70.21 89.62 11.70 yaml weights
resnet34 D910x8-G 74.15 91.98 21.81 yaml weights
resnet50 D910x8-G 76.69 93.50 25.61 yaml weights
resnet101 D910x8-G 78.24 94.09 44.65 yaml weights
resnet152 D910x8-G 78.72 94.45 60.34 yaml weights
resnetv2_50 D910x8-G 76.90 93.37 25.60 yaml weights
resnetv2_101 D910x8-G 78.48 94.23 44.55 yaml weights
resnext50_32x4d D910x8-G 78.53 94.10 25.10 yaml weights
resnext101_32x4d D910x8-G 79.83 94.80 44.32 yaml weights
resnext101_64x4d D910x8-G 80.30 94.82 83.66 yaml weights
resnext152_64x4d D910x8-G 80.52 95.00 115.27 yaml weights
rexnet_09 D910x8-G 77.06 93.41 4.13 yaml weights
rexnet_10 D910x8-G 77.38 93.60 4.84 yaml weights
rexnet_13 D910x8-G 79.06 94.28 7.61 yaml weights
rexnet_15 D910x8-G 79.95 94.74 9.79 yaml weights
rexnet_20 D910x8-G 80.64 94.99 16.45 yaml weights
seresnet18 D910x8-G 71.81 90.49 11.80 yaml weights
seresnet34 D910x8-G 75.38 92.50 21.98 yaml weights
seresnet50 D910x8-G 78.32 94.07 28.14 yaml weights
seresnext26_32x4d D910x8-G 77.17 93.42 16.83 yaml weights
seresnext50_32x4d D910x8-G 78.71 94.36 27.63 yaml weights
shufflenet_v1_g3_05 D910x8-G 57.05 79.73 0.73 yaml weights
shufflenet_v1_g3_10 D910x8-G 67.77 87.73 1.89 yaml weights
shufflenet_v2_x0_5 D910x8-G 60.53 82.11 1.37 yaml weights
shufflenet_v2_x1_0 D910x8-G 69.47 88.88 2.29 yaml weights
shufflenet_v2_x1_5 D910x8-G 72.79 90.93 3.53 yaml weights
shufflenet_v2_x2_0 D910x8-G 75.07 92.08 7.44 yaml weights
skresnet18 D910x8-G 73.09 91.20 11.97 yaml weights
skresnet34 D910x8-G 76.71 93.10 22.31 yaml weights
skresnext50_32x4d D910x8-G 79.08 94.60 37.31 yaml weights
squeezenet1_0 D910x8-G 59.01 81.01 1.25 yaml weights
squeezenet1_0 GPUx8-G 58.83 81.08 1.25 yaml weights
squeezenet1_1 D910x8-G 58.44 80.84 1.24 yaml weights
squeezenet1_1 GPUx8-G 59.18 81.41 1.24 yaml weights
swin_tiny D910x8-G 80.82 94.80 33.38 yaml weights
swinv2_tiny_window8 D910x8-G 81.42 95.43 28.78 yaml weights
vgg11 D910x8-G 71.86 90.50 132.86 yaml weights
vgg13 D910x8-G 72.87 91.02 133.04 yaml weights
vgg16 D910x8-G 74.61 91.87 138.35 yaml weights
vgg19 D910x8-G 75.21 92.56 143.66 yaml weights
visformer_tiny D910x8-G 78.28 94.15 10.33 yaml weights
visformer_tiny_v2 D910x8-G 78.82 94.41 9.38 yaml weights
visformer_small D910x8-G 81.76 95.88 40.25 yaml weights
visformer_small_v2 D910x8-G 82.17 95.90 23.52 yaml weights
vit_b_32_224 D910x8-G 75.86 92.08 87.46 yaml weights
vit_l_16_224 D910x8-G 76.34 92.79 303.31 yaml weights
vit_l_32_224 D910x8-G 73.71 90.92 305.52 yaml weights
volo_d1 D910x8-G 82.59 95.99 27 yaml weights
xception D910x8-G 79.01 94.25 22.91 yaml weights
xcit_tiny_12_p16_224 D910x8-G 77.67 93.79 7.00 yaml weights

Notes

  • Context: Training context denoted as {device}x{pieces}-{MS mode}, where mindspore mode can be G - graph mode or F - pynative mode with ms function. For example, D910x8-G is for training on 8 pieces of Ascend 910 NPU using graph mode.
  • Top-1 and Top-5: Accuracy reported on the validation set of ImageNet-1K.