search

open-mmlab / mmpretrain

OpenMMLab Pre-training Toolbox and Benchmark
https://mmpretrain.readthedocs.io/en/latest/
Apache License 2.0
3.38k stars 1.05k forks source link

Please sort model zoo based on accuracy #907

Closed waqarsqureshi closed 2 years ago

waqarsqureshi commented 2 years ago

Please arrange model zoo based on accuracy

Model Zoo

waqarsqureshi commented 2 years ago

<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.0 Transitional//EN">

Model | Params(M) | Flops(G) | Top-1 (%) | Top-5 (%) | Config | Download -- | -- | -- | -- | -- | -- | -- ConvNeXt-XL* | 350.2 | 60.93 | 86.97 | 98.2 | config | model ConvNeXt-L* | 197.77 | 34.37 | 86.61 | 98.04 | config | model ConvNeXt-B* | 88.59 | 15.36 | 85.81 | 97.86 | config | model ViT-L/16* | 304.72 | 116.68 | 85.63 | 97.63 | config | model DeiT-base distilled 384px* | 86.86 | 49.37 | 85.55 | 97.35 | config | model ViT-B/16* | 86.86 | 33.03 | 85.43 | 97.77 | config | model EfficientNet-B8 (AA + AdvProp)* | 87.41 | 1.09 | 85.38 | 97.28 | config | model EfficientNet-B7 (AA + AdvProp)* | 66.35 | 0.72 | 85.14 | 97.23 | config | model EfficientNet-B6 (AA + AdvProp)* | 43.04 | 0.41 | 84.74 | 97.14 | config | model EfficientNet-B7 (AA)* | 66.35 | 0.72 | 84.38 | 96.88 | config | model ConvNeXt-L* | 197.77 | 34.37 | 84.3 | 96.89 | config | model EfficientNet-B5 (AA + AdvProp)* | 30.39 | 0.24 | 84.21 | 96.98 | config | model EfficientNet-B6 (AA)* | 43.04 | 0.41 | 84.05 | 96.82 | config | model ViT-B/32* | 88.3 | 8.56 | 84.01 | 97.08 | config | model VAN-L* | 44.77 | 8.99 | 83.86 | 96.73 | config | model ConvNeXt-B* | 88.59 | 15.36 | 83.85 | 96.74 | config | model Conformer-base-p16* | 83.29 | 22.89 | 83.82 | 96.59 | config | model EfficientNet-B5 (AA)* | 30.39 | 0.24 | 83.82 | 96.76 | config | model HRNet-W48 (ssld)* | 77.47 | 17.36 | 83.63 | 96.79 | config | model SVT-large* | 99.27 | 14.82 | 83.6 | 96.5 | config | model Swin-Transformer base | 87.77 | 15.14 | 83.36 | 96.44 | config | model \| log DeiT-base distilled* | 86.57 | 16.86 | 83.33 | 96.49 | config | model Conformer-small-p16* | 37.67 | 10.31 | 83.32 | 96.46 | config | model EfficientNet-B4 (AA + AdvProp)* | 19.34 | 0.12 | 83.25 | 96.44 | config | model EfficientNet-B5* | 30.39 | 0.24 | 83.18 | 96.47 | config | model SVT-base* | 56.07 | 8.35 | 83.13 | 96.29 | config | model ConvNeXt-S* | 50.22 | 8.69 | 83.13 | 96.44 | config | model PCPVT-large* | 60.99 | 9.51 | 83.09 | 96.59 | config | model DeiT-base 384px* | 86.86 | 49.37 | 83.04 | 96.31 | config | model Swin-Transformer small | 49.61 | 8.52 | 83.02 | 96.29 | config | model \| log EfficientNet-B4 (AA)* | 19.34 | 0.12 | 82.95 | 96.26 | config | model VAN-B* | 26.58 | 5.03 | 82.8 | 96.21 | config | model T2T-ViT_t-24 | 64 | 12.69 | 82.71 | 96.09 | config | model \| log ResNeSt-269* | 110.93 | 22.58 | 82.7 | 96.28 | config | model PCPVT-base* | 43.83 | 6.45 | 82.66 | 96.26 | config | model T2T-ViT_t-19 | 39.08 | 7.8 | 82.63 | 96.18 | config | model \| log EfficientNet-B4* | 19.34 | 0.12 | 82.57 | 96.09 | config | model ResNeSt-200* | 70.2 | 17.53 | 82.41 | 96.22 | config | model ResNeSt-101* | 48.28 | 10.27 | 82.32 | 96.24 | config | model ConvNeXt-T* | 28.59 | 4.46 | 82.05 | 95.86 | config | model Conformer-small-p32* | 38.85 | 7.09 | 81.96 | 96.02 | config | model T2T-ViT_t-14 | 21.47 | 4.34 | 81.83 | 95.84 | config | model \| log RepVGG-D2se* | 133.33 (train) \| 120.39 (deploy) | 36.56 (train) \| 32.85 (deploy) | 81.81 | 95.94 | config (train) \| config (deploy) | model EfficientNet-B3 (AA + AdvProp)* | 12.23 | 0.06 | 81.81 | 95.69 | config | model SVT-small* | 24.06 | 2.82 | 81.77 | 95.57 | config | model DeiT-base | 86.57 | 16.86 | 81.76 | 95.81 | config | model \| log EfficientNet-B3 (AA)* | 12.23 | 0.06 | 81.58 | 95.67 | config | model Transformer in Transformer small* | 23.76 | 3.36 | 81.52 | 95.73 | config | model WRN-50* | 68.88 | 11.44 | 81.45 | 95.53 | config | model Conformer-tiny-p16* | 23.52 | 4.9 | 81.31 | 95.6 | config | model Swin-Transformer tiny | 28.29 | 4.36 | 81.18 | 95.61 | config | model \| log DeiT-small distilled* | 22.05 | 4.24 | 81.17 | 95.4 | config | model PCPVT-small* | 24.11 | 3.67 | 81.14 | 95.69 | config | model ResNeSt-50* | 27.48 | 5.41 | 81.13 | 95.59 | config | model HRNet-W18 (ssld)* | 21.3 | 4.33 | 81.06 | 95.7 | config | model EfficientNet-B3* | 12.23 | 0.06 | 81.01 | 95.34 | config | model VAN-S* | 13.86 | 2.52 | 81.01 | 95.63 | config | model DeiT-small | 22.05 | 4.24 | 80.69 | 95.06 | config | model \| log RepVGG-B3* | 123.09 (train) \| 110.96 (deploy) | 29.17 (train) \| 26.22 (deploy) | 80.52 | 95.26 | config (train) \| config (deploy) | model EfficientNet-B2 (AA + AdvProp)* | 9.11 | 0.03 | 80.45 | 95.07 | config | model RepVGG-B3g4* | 83.83 (train) \| 75.63 (deploy) | 17.9 (train) \| 16.08 (deploy) | 80.22 | 95.1 | config (train) \| config (deploy) | model EfficientNet-B2 (AA)* | 9.11 | 0.03 | 80.21 | 94.96 | config | model ResNet-50 (rsb-a1) | 25.56 | 4.12 | 80.12 | 94.78 | config | model \| log CSPDarkNet50* | 27.64 | 5.04 | 80.05 | 95.07 | config | model CSPResNeXt50* | 20.57 | 3.11 | 79.96 | 94.96 | config | model RegNetX-12GF | 46.11 | 12.15 | 79.67 | 95.03 | config | model \| log EfficientNet-B2* | 9.11 | 0.03 | 79.64 | 94.8 | config | model CSPResNet50* | 21.62 | 3.48 | 79.55 | 94.68 | config | model EfficientNet-B1 (AA + AdvProp)* | 7.79 | 0.03 | 79.52 | 94.43 | config | model HRNet-W64* | 128.06 | 29 | 79.46 | 94.65 | config | model ResNetV1D-152 | 60.21 | 11.82 | 79.41 | 94.7 | config | model \| log RepVGG-B2g4* | 61.76 (train) \| 55.78 (deploy) | 12.63 (train) \| 11.34 (deploy) | 79.38 | 94.68 | config (train) \| config (deploy) | model RegNetX-6.4GF | 26.21 | 6.51 | 79.38 | 94.65 | config | model \| log HRNet-W48* | 77.47 | 17.36 | 79.32 | 94.52 | config | model ResNeXt-32x8d-101 | 88.79 | 16.5 | 79.23 | 94.58 | config | model \| log Res2Net-50-26w-8s* | 48.4 | 8.39 | 79.2 | 94.36 | config | model EfficientNet-B1 (AA)* | 7.79 | 0.03 | 79.2 | 94.42 | config | model Res2Net-101-26w-4s* | 45.21 | 8.12 | 79.19 | 94.44 | config | model RegNetX-8.0GF | 39.57 | 8.03 | 79.12 | 94.51 | config | model \| log HRNet-W40* | 57.55 | 12.77 | 78.94 | 94.47 | config | model ResNetV1D-101 | 44.57 | 8.09 | 78.93 | 94.48 | config | model \| log ResNeXt-32x4d-152 | 59.95 | 11.8 | 78.93 | 94.41 | config | model \| log HRNet-W44* | 67.06 | 14.96 | 78.88 | 94.37 | config | model WRN-101* | 126.89 | 22.81 | 78.84 | 94.28 | config | model RepVGG-B2* | 89.02 (train) \| 80.32 (deploy) | 20.46 (train) \| 18.39 (deploy) | 78.78 | 94.42 | config (train) \| config (deploy) | model ResNeXt-32x4d-101 | 44.18 | 8.03 | 78.71 | 94.12 | config | model \| log EfficientNet-B1* | 7.79 | 0.03 | 78.68 | 94.28 | config | model ResNet-152 | 60.19 | 11.58 | 78.63 | 94.16 | config | model \| log RegNetX-4.0GF | 22.12 | 4 | 78.6 | 94.17 | config | model \| log HRNet-W32* | 41.23 | 8.99 | 78.44 | 94.19 | config | model RepVGG-B1* | 57.42 (train) \| 51.83 (deploy) | 13.16 (train) \| 11.82 (deploy) | 78.37 | 94.11 | config (train) \| config (deploy) | model SE-ResNet-101 | 49.33 | 7.86 | 78.26 | 94.07 | config | model \| log HRNet-W30* | 37.71 | 8.17 | 78.19 | 94.22 | config | model ResNet-101 | 44.55 | 7.85 | 78.18 | 94.03 | config | model \| log Res2Net-50-14w-8s* | 25.06 | 4.22 | 78.14 | 93.85 | config | model RegNetX-3.2GF | 15.3 | 3.21 | 78.09 | 94.08 | config | model \| log ResNeXt-32x4d-50 | 25.03 | 4.27 | 77.9 | 93.66 | config | model \| log RepVGG-B1g2* | 45.78 (train) \| 41.36 (deploy) | 9.82 (train) \| 8.82 (deploy) | 77.79 | 93.88 | config (train) \| config (deploy) | model SE-ResNet-50 | 28.09 | 4.13 | 77.74 | 93.84 | config | model \| log DenseNet161* | 28.68 | 7.82 | 77.61 | 93.83 | config | model RepVGG-B1g4* | 39.97 (train) \| 36.13 (deploy) | 8.15 (train) \| 7.32 (deploy) | 77.58 | 93.84 | config (train) \| config (deploy) | model ResNetV1D-50 | 25.58 | 4.36 | 77.54 | 93.57 | config | model \| log EfficientNet-B0 (AA + AdvProp)* | 5.29 | 0.02 | 77.53 | 93.61 | config | model DenseNet201* | 20.01 | 4.37 | 77.32 | 93.64 | config | model EfficientNet-B0 (AA)* | 5.29 | 0.02 | 77.26 | 93.41 | config | model RegNetX-1.6GF | 9.19 | 1.63 | 76.84 | 93.31 | config | model \| log HRNet-W18* | 21.3 | 4.33 | 76.75 | 93.44 | config | model EfficientNet-B0* | 5.29 | 0.02 | 76.74 | 93.17 | config | model Mixer-B/16* | 59.88 | 12.61 | 76.68 | 92.25 | config | model RepVGG-A2* | 28.21 (train) \| 25.5 (deploy) | 5.7 (train) \| 5.12 (deploy) | 76.48 | 93.01 | config (train) \| config (deploy) | model DenseNet169* | 14.15 | 3.42 | 76.08 | 93.11 | config | model VAN-T* | 4.11 | 0.88 | 75.41 | 93.02 | config | model RepVGG-B0* | 15.82 (train) \| 14.34 (deploy) | 3.42 (train) \| 3.06 (deploy) | 75.14 | 92.42 | config (train) \| config (deploy) | model DenseNet121* | 7.98 | 2.88 | 74.96 | 92.21 | config | model RegNetX-800MF | 7.26 | 0.81 | 74.76 | 92.32 | config | model \| log VGG-19-BN | 143.68 | 19.7 | 74.7 | 92.24 | config | model \| log DeiT-tiny distilled* | 5.72 | 1.08 | 74.51 | 91.9 | config | model DeiT-tiny | 5.72 | 1.08 | 74.5 | 92.24 | config | model \| log RepVGG-A1* | 14.09 (train) \| 12.79 (deploy) | 2.64 (train) \| 2.37 (deploy) | 74.47 | 91.85 | config (train) \| config (deploy) | model ResNet-34 | 21.8 | 3.68 | 73.85 | 91.53 | config | model \| log VGG-16-BN | 138.37 | 15.53 | 73.72 | 91.68 | config | model \| log RegNetX-400MF | 5.16 | 0.41 | 72.56 | 90.78 | config | model \| log VGG-19 | 143.67 | 19.67 | 72.41 | 90.8 | config | model \| log RepVGG-A0* | 9.11（train) \| 8.31 (deploy) | 1.52 (train) \| 1.36 (deploy) | 72.41 | 90.5 | config (train) \| config (deploy) | model Mixer-L/16* | 208.2 | 44.57 | 72.34 | 88.02 | config | model VGG-13-BN | 133.05 | 11.36 | 72.15 | 90.71 | config | model \| log MobileNet V2 | 3.5 | 0.319 | 71.86 | 90.42 | config | model \| log VGG-16 | 138.36 | 15.5 | 71.62 | 90.49 | config | model \| log VGG-11-BN | 132.87 | 7.64 | 70.75 | 90.12 | config | model \| log ResNet-18 | 11.69 | 1.82 | 70.07 | 89.44 | config | model \| log VGG-13 | 133.05 | 11.34 | 70.02 | 89.46 | config | model \| log ShuffleNetV2 1.0x | 2.28 | 0.149 | 69.55 | 88.92 | config | model \| log VGG-11 | 132.86 | 7.63 | 68.75 | 88.87 | config | model \| log ShuffleNetV1 1.0x (group=3) | 1.87 | 0.146 | 68.13 | 87.81 | config | model \| log