Benchmark Results

Model Context Top-1 (%) Top-5 (%) Params(M) Recipe Download
bit_resnet50 D910x8-G 76.81 93.17 25.55 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
densenet_121 D910x8-G 75.64 92.84 8.06 yaml weights
densenet_161 D910x8-G 79.09 94.66 28.90 yaml weights
densenet_169 D910x8-G 77.26 93.71 14.31 yaml weights
densenet_201 D910x8-G 78.14 94.08 20.24 yaml weights
edgenext_small D910x8-G 79.15 94.39 5.59 yaml weights
MnasNet-B1-0_75 D910x8-G 71.81 90.53 3.20 yaml weights
MnasNet-B1-1_0 D910x8-G 74.28 91.70 4.42 yaml weights
MnasNet-B1-1_4 D910x8-G 76.01 92.83 7.16 yaml weights
MobileNet_v1_025 D910x8-G 54.64 78.29 0.47 yaml weights
MobileNet_v1_050 D910x8-G 66.39 86.71 1.34 yaml weights
MobileNet_v1_075 D910x8-G 70.66 89.49 2.60 yaml weights
MobileNet_v1_100 D910x8-G 71.83 90.26 4.25 yaml weights
MobileNet_v2_075 D910x8-G 69.76 89.28 2.66 yaml weights
MobileNet_v2_100 D910x8-G 72.02 90.92 3.54 yaml weights
MobileNet_v2_140 D910x8-G 74.97 92.32 6.15 yaml weights
MobileNetV3_small_100 D910x8-G 67.34 87.49 2.55 yaml weights
MobileNetV3_large_100 D910x8-G 75.14 92.33 5.51 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
regnet_x_800mf D910x8-G 76.04 92.97 7.26 yaml weights
repmlp_t224 D910x8-G 76.68 93.30 38.30 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 81.26 95.41 45.35 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
rexnet_x09 D910x8-G 77.07 93.41 4.13 yaml weights
rexnet_x10 D910x8-G 77.38 93.60 4.84 yaml weights
rexnet_x13 D910x8-G 79.06 94.28 7.61 yaml weights
rexnet_x15 D910x8-G 79.94 94.74 9.79 yaml weights
rexnet_x20 D910x8-G 80.6 94.99 16.45 yaml weights
shufflenet_v1_g3_x0_5 D910x8-G 57.05 79.73 0.73 yaml weights
shufflenet_v1_g3_x1_0 D910x8-G 67.77 87.73 1.89 yaml weights
shufflenet_v1_g3_x1_5 D910x8-G 71.53 90.17 3.48 yaml weights
shufflenet_v1_g3_x2_0 D910x8-G 74.02 91.74 5.50 yaml weights
shufflenet_v2_x0_5 D910x8-G 60.68 82.44 1.37 yaml weights
shufflenet_v2_x1_0 D910x8-G 69.51 88.67 2.29 yaml weights
shufflenet_v2_x1_5 D910x8-G 72.59 90.79 3.53 yaml weights
shufflenet_v2_x2_0 D910x8-G 75.14 92.13 7.44 yaml weights
squeezenet_1.0 GPUx8-G 59.49 81.22 1.25 yaml weights
squeezenet_1.1 GPUx8-G 58.99 80.99 1.24 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 81.73 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

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.