Model Zoo Summary¶
In this page, we list all algorithms we support. You can click the link to jump to the corresponding model pages.
And we also list all checkpoints we provide. You can sort or search checkpoints in the table and click the corresponding link to model pages for more details.
All supported algorithms¶
Number of papers: 49
Algorithm: 49
Number of checkpoints: 335
[Algorithm] MobileNetV2: Inverted Residuals and Linear Bottlenecks (1 ckpts)
[Algorithm] Searching for MobileNetV3 (6 ckpts)
[Algorithm] Deep Residual Learning for Image Recognition (25 ckpts)
[Algorithm] Res2Net: A New Multi-scale Backbone Architecture (3 ckpts)
[Algorithm] Aggregated Residual Transformations for Deep Neural Networks (4 ckpts)
[Algorithm] Squeeze-and-Excitation Networks (2 ckpts)
[Algorithm] ShuffleNet: An Extremely Efficient Convolutional Neural Network for Mobile Devices (1 ckpts)
[Algorithm] ShuffleNet V2: Practical Guidelines for Efficient CNN Architecture Design (1 ckpts)
[Algorithm] Swin Transformer: Hierarchical Vision Transformer using Shifted Windows (14 ckpts)
[Algorithm] Very Deep Convolutional Networks for Large-Scale Image (8 ckpts)
[Algorithm] RepVGG: Making VGG-style ConvNets Great Again (12 ckpts)
[Algorithm] Transformer in Transformer (1 ckpts)
[Algorithm] An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale (8 ckpts)
[Algorithm] Tokens-to-Token ViT: Training Vision Transformers from Scratch on ImageNet (3 ckpts)
[Algorithm] TinyViT: Fast Pretraining Distillation for Small Vision Transformers (8 ckpts)
[Algorithm] MLP-Mixer: An all-MLP Architecture for Vision (2 ckpts)
[Algorithm] Conformer: Local Features Coupling Global Representations for Visual Recognition (4 ckpts)
[Algorithm] Designing Network Design Spaces (16 ckpts)
[Algorithm] Training data-efficient image transformers & distillation through attention (9 ckpts)
[Algorithm] Twins: Revisiting the Design of Spatial Attention in Vision Transformers (6 ckpts)
[Algorithm] EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks (32 ckpts)
[Algorithm] A ConvNet for the 2020s (23 ckpts)
[Algorithm] Deep High-Resolution Representation Learning for Visual Recognition (9 ckpts)
[Algorithm] RepMLP: Re-parameterizing Convolutions into Fully-connected Layers for Image Recognition (2 ckpts)
[Algorithm] Wide Residual Networks (3 ckpts)
[Algorithm] Visual Attention Network (4 ckpts)
[Algorithm] CSPNet: A New Backbone that can Enhance Learning Capability of CNN (3 ckpts)
[Algorithm] Patches Are All You Need? (3 ckpts)
[Algorithm] Densely Connected Convolutional Networks (4 ckpts)
[Algorithm] MetaFormer is Actually What You Need for Vision (5 ckpts)
[Algorithm] Rethinking the Inception Architecture for Computer Vision (1 ckpts)
[Algorithm] MViTv2: Improved Multiscale Vision Transformers for Classification and Detection (4 ckpts)
[Algorithm] EdgeNeXt: Efficiently Amalgamated CNN-Transformer Architecture for Mobile Vision Applications (6 ckpts)
[Algorithm] An Improved One millisecond Mobile Backbone (5 ckpts)
[Algorithm] EfficientFormer: Vision Transformers at MobileNet Speed (3 ckpts)
[Algorithm] Swin Transformer V2: Scaling Up Capacity and Resolution (12 ckpts)
[Algorithm] DeiT III: Revenge of the ViT (16 ckpts)
[Algorithm] HorNet: Efficient High-Order Spatial Interactions with Recursive Gated Convolutions (9 ckpts)
[Algorithm] MobileViT Light-weight, General-purpose, and Mobile-friendly Vision Transformer (3 ckpts)
[Algorithm] DaViT: Dual Attention Vision Transformers (3 ckpts)
[Algorithm] Scaling Up Your Kernels to 31x31: Revisiting Large Kernel Design in CNNs (6 ckpts)
[Algorithm] Residual Attention: A Simple but Effective Method for Multi-Label Recognition (1 ckpts)
[Algorithm] BEiT: BERT Pre-Training of Image Transformers (1 ckpts)
[Algorithm] BEiT v2: Masked Image Modeling with Vector-Quantized Visual Tokenizers (1 ckpts)
[Algorithm] EVA: Exploring the Limits of Masked Visual Representation Learning at Scale (10 ckpts)
[Algorithm] Reversible Vision Transformers (2 ckpts)
[Algorithm] Learning Transferable Visual Models From Natural Language Supervision (14 ckpts)
[Algorithm] MixMIM: Mixed and Masked Image Modeling for Efficient Visual Representation Learning (1 ckpts)
[Algorithm] EfficientNetV2: Smaller Models and Faster Training (15 ckpts)
All checkpoints¶
ImageNet-1k¶
Model |
Params (M) |
Flops (G) |
Top-1 (%) |
Top-5 (%) |
Readme |
|---|---|---|---|---|---|
mobilenet-v2_8xb32_in1k |
3.50 |
0.32 |
71.86 |
90.42 |
|
mobilenet-v3-small-050_3rdparty_in1k |
1.59 |
0.02 |
57.91 |
80.19 |
|
mobilenet-v3-small-075_3rdparty_in1k |
2.04 |
0.04 |
65.23 |
85.44 |
|
mobilenet-v3-small_8xb128_in1k |
2.54 |
0.06 |
66.68 |
86.74 |
|
mobilenet-v3-small_3rdparty_in1k |
2.54 |
0.06 |
67.66 |
87.41 |
|
mobilenet-v3-large_8xb128_in1k |
5.48 |
0.23 |
73.49 |
91.31 |
|
mobilenet-v3-large_3rdparty_in1k |
5.48 |
0.23 |
74.04 |
91.34 |
|
resnet18_8xb32_in1k |
11.69 |
1.82 |
69.90 |
89.43 |
|
resnet34_8xb32_in1k |
2.18 |
3.68 |
73.62 |
91.59 |
|
resnet50_8xb32_in1k |
25.56 |
4.12 |
76.55 |
93.06 |
|
resnet101_8xb32_in1k |
44.55 |
7.85 |
77.97 |
94.06 |
|
resnet152_8xb32_in1k |
60.19 |
11.58 |
78.48 |
94.13 |
|
resnetv1d50_8xb32_in1k |
25.58 |
4.36 |
77.54 |
93.57 |
|
resnetv1d101_8xb32_in1k |
44.57 |
8.09 |
78.93 |
94.48 |
|
resnetv1d152_8xb32_in1k |
60.21 |
11.82 |
79.41 |
94.70 |
|
resnet50_8xb32-fp16_in1k |
25.56 |
4.12 |
76.30 |
93.07 |
|
resnet50_8xb256-rsb-a1-600e_in1k |
25.56 |
4.12 |
80.12 |
94.78 |
|
resnet50_8xb256-rsb-a2-300e_in1k |
25.56 |
4.12 |
79.55 |
94.37 |
|
resnet50_8xb256-rsb-a3-100e_in1k |
25.56 |
4.12 |
78.30 |
93.80 |
|
resnetv1c50_8xb32_in1k |
25.58 |
4.36 |
77.01 |
93.58 |
|
resnetv1c101_8xb32_in1k |
44.57 |
8.09 |
78.30 |
94.27 |
|
resnetv1c152_8xb32_in1k |
60.21 |
11.82 |
78.76 |
94.41 |
|
res2net50-w14-s8_3rdparty_8xb32_in1k |
25.06 |
4.22 |
78.14 |
93.85 |
|
res2net50-w26-s8_3rdparty_8xb32_in1k |
48.40 |
8.39 |
79.20 |
94.36 |
|
res2net101-w26-s4_3rdparty_8xb32_in1k |
45.21 |
8.12 |
79.19 |
94.44 |
|
resnext50-32x4d_8xb32_in1k |
25.03 |
4.27 |
77.90 |
93.66 |
|
resnext101-32x4d_8xb32_in1k |
44.18 |
8.03 |
78.61 |
94.17 |
|
resnext101-32x8d_8xb32_in1k |
88.79 |
16.50 |
79.27 |
94.58 |
|
resnext152-32x4d_8xb32_in1k |
59.95 |
11.80 |
78.88 |
94.33 |
|
seresnet50_8xb32_in1k |
28.09 |
4.13 |
77.74 |
93.84 |
|
seresnet101_8xb32_in1k |
49.33 |
7.86 |
78.26 |
94.07 |
|
shufflenet-v1-1x_16xb64_in1k |
1.87 |
0.15 |
68.13 |
87.81 |
|
shufflenet-v2-1x_16xb64_in1k |
2.28 |
0.15 |
69.55 |
88.92 |
|
swin-tiny_16xb64_in1k |
28.29 |
4.36 |
81.18 |
95.61 |
|
swin-small_16xb64_in1k |
49.61 |
8.52 |
83.02 |
96.29 |
|
swin-base_16xb64_in1k |
87.77 |
15.14 |
83.36 |
96.44 |
|
swin-tiny_3rdparty_in1k |
28.29 |
4.36 |
81.18 |
95.52 |
|
swin-small_3rdparty_in1k |
49.61 |
8.52 |
83.21 |
96.25 |
|
swin-base_3rdparty_in1k |
87.77 |
15.14 |
83.42 |
96.44 |
|
swin-base_3rdparty_in1k-384 |
87.90 |
44.49 |
84.49 |
96.95 |
|
swin-base_in21k-pre-3rdparty_in1k |
87.77 |
15.14 |
85.16 |
97.50 |
|
swin-base_in21k-pre-3rdparty_in1k-384 |
87.90 |
44.49 |
86.44 |
98.05 |
|
swin-large_in21k-pre-3rdparty_in1k |
196.53 |
34.04 |
86.24 |
97.88 |
|
swin-large_in21k-pre-3rdparty_in1k-384 |
196.74 |
100.04 |
87.25 |
98.25 |
|
vgg11_8xb32_in1k |
132.86 |
7.63 |
68.75 |
88.87 |
|
vgg13_8xb32_in1k |
133.05 |
11.34 |
70.02 |
89.46 |
|
vgg16_8xb32_in1k |
138.36 |
15.50 |
71.62 |
90.49 |
|
vgg19_8xb32_in1k |
143.67 |
19.67 |
72.41 |
90.80 |
|
vgg11bn_8xb32_in1k |
132.87 |
7.64 |
70.67 |
90.16 |
|
vgg13bn_8xb32_in1k |
133.05 |
11.36 |
72.12 |
90.66 |
|
vgg16bn_8xb32_in1k |
138.37 |
15.53 |
73.74 |
91.66 |
|
vgg19bn_8xb32_in1k |
143.68 |
19.70 |
74.68 |
92.27 |
|
repvgg-A0_8xb32_in1k |
8.31 |
1.36 |
72.37 |
90.56 |
|
repvgg-A1_8xb32_in1k |
12.79 |
2.36 |
74.23 |
91.80 |
|
repvgg-A2_8xb32_in1k |
25.50 |
5.12 |
76.49 |
93.09 |
|
repvgg-B0_8xb32_in1k |
3.42 |
15.82 |
75.27 |
92.21 |
|
repvgg-B1_8xb32_in1k |
51.83 |
11.81 |
78.19 |
94.04 |
|
repvgg-B1g2_8xb32_in1k |
41.36 |
8.81 |
77.87 |
93.99 |
|
repvgg-B1g4_8xb32_in1k |
36.13 |
7.30 |
77.81 |
93.77 |
|
repvgg-B2_8xb32_in1k |
80.32 |
18.37 |
78.58 |
94.23 |
|
repvgg-B2g4_8xb32_in1k |
55.78 |
11.33 |
79.44 |
94.72 |
|
repvgg-B3_8xb32_in1k |
110.96 |
26.21 |
80.58 |
95.33 |
|
repvgg-B3g4_8xb32_in1k |
75.63 |
16.06 |
80.26 |
95.15 |
|
repvgg-D2se_3rdparty_in1k |
120.39 |
32.84 |
81.81 |
95.94 |
|
tnt-small-p16_3rdparty_in1k |
23.76 |
3.36 |
81.52 |
95.73 |
|
vit-base-p16_in21k-pre-3rdparty_ft-64xb64_in1k-384 |
86.86 |
33.03 |
85.43 |
97.77 |
|
vit-base-p32_in21k-pre-3rdparty_ft-64xb64_in1k-384 |
88.30 |
8.56 |
84.01 |
97.08 |
|
vit-large-p16_in21k-pre-3rdparty_ft-64xb64_in1k-384 |
304.72 |
116.68 |
85.63 |
97.63 |
|
vit-base-p16_pt-32xb128-mae_in1k |
86.86 |
33.03 |
82.37 |
96.15 |
|
t2t-vit-t-14_8xb64_in1k |
21.47 |
4.34 |
81.83 |
95.84 |
|
t2t-vit-t-19_8xb64_in1k |
39.08 |
7.80 |
82.63 |
96.18 |
|
t2t-vit-t-24_8xb64_in1k |
64.00 |
12.69 |
82.71 |
96.09 |
|
tinyvit-5m_3rdparty_in1k |
5.39 |
1.29 |
79.02 |
94.74 |
|
tinyvit-5m_in21k-distill-pre_3rdparty_in1k |
5.39 |
1.29 |
80.71 |
95.57 |
|
tinyvit-11m_3rdparty_in1k |
11.00 |
2.05 |
81.44 |
95.79 |
|
tinyvit-11m_in21k-distill-pre_3rdparty_in1k |
11.00 |
2.05 |
83.19 |
96.53 |
|
tinyvit-21m_3rdparty_in1k |
21.20 |
4.30 |
83.08 |
96.58 |
|
tinyvit-21m_in21k-distill-pre_3rdparty_in1k |
21.20 |
4.30 |
84.85 |
97.27 |
|
tinyvit-21m_in21k-distill-pre_3rdparty_in1k-384px |
21.23 |
13.85 |
86.21 |
97.77 |
|
tinyvit-21m_in21k-distill-pre_3rdparty_in1k-512px |
21.27 |
27.15 |
86.44 |
97.89 |
|
mlp-mixer-base-p16_3rdparty_64xb64_in1k |
59.88 |
12.61 |
76.68 |
92.25 |
|
mlp-mixer-large-p16_3rdparty_64xb64_in1k |
208.20 |
44.57 |
72.34 |
88.02 |
|
conformer-tiny-p16_3rdparty_8xb128_in1k |
23.52 |
4.90 |
81.31 |
95.60 |
|
conformer-small-p16_3rdparty_8xb128_in1k |
37.67 |
10.31 |
83.32 |
96.46 |
|
conformer-small-p32_8xb128_in1k |
38.85 |
7.09 |
81.96 |
96.02 |
|
conformer-base-p16_3rdparty_8xb128_in1k |
83.29 |
22.89 |
83.82 |
96.59 |
|
regnetx-400mf_8xb128_in1k |
5.16 |
0.41 |
72.56 |
90.78 |
|
regnetx-800mf_8xb128_in1k |
7.26 |
0.81 |
74.76 |
92.32 |
|
regnetx-1.6gf_8xb128_in1k |
9.19 |
1.63 |
76.84 |
93.31 |
|
regnetx-3.2gf_8xb64_in1k |
3.21 |
1.53 |
78.09 |
94.08 |
|
regnetx-4.0gf_8xb64_in1k |
22.12 |
4.00 |
78.60 |
94.17 |
|
regnetx-6.4gf_8xb64_in1k |
26.21 |
6.51 |
79.38 |
94.65 |
|
regnetx-8.0gf_8xb64_in1k |
39.57 |
8.03 |
79.12 |
94.51 |
|
regnetx-12gf_8xb64_in1k |
46.11 |
12.15 |
79.67 |
95.03 |
|
deit-tiny_pt-4xb256_in1k |
5.72 |
1.08 |
74.50 |
92.24 |
|
deit-tiny-distilled_3rdparty_pt-4xb256_in1k |
5.72 |
1.08 |
74.51 |
91.90 |
|
deit-small_pt-4xb256_in1k |
22.05 |
4.24 |
80.69 |
95.06 |
|
deit-small-distilled_3rdparty_pt-4xb256_in1k |
22.05 |
4.24 |
81.17 |
95.40 |
|
deit-base_pt-16xb64_in1k |
86.57 |
16.86 |
81.76 |
95.81 |
|
deit-base_3rdparty_pt-16xb64_in1k |
86.57 |
16.86 |
81.79 |
95.59 |
|
deit-base-distilled_3rdparty_pt-16xb64_in1k |
86.57 |
16.86 |
83.33 |
96.49 |
|
deit-base_3rdparty_ft-16xb32_in1k-384px |
86.86 |
49.37 |
83.04 |
96.31 |
|
deit-base-distilled_3rdparty_ft-16xb32_in1k-384px |
86.86 |
49.37 |
85.55 |
97.35 |
|
twins-pcpvt-small_3rdparty_8xb128_in1k |
24.11 |
3.67 |
81.14 |
95.69 |
|
twins-pcpvt-base_3rdparty_8xb128_in1k |
43.83 |
6.45 |
82.66 |
96.26 |
|
twins-pcpvt-large_3rdparty_16xb64_in1k |
60.99 |
9.51 |
83.09 |
96.59 |
|
twins-svt-small_3rdparty_8xb128_in1k |
24.06 |
2.82 |
81.77 |
95.57 |
|
twins-svt-base_8xb128_3rdparty_in1k |
56.07 |
8.35 |
83.13 |
96.29 |
|
twins-svt-large_3rdparty_16xb64_in1k |
99.27 |
14.82 |
83.60 |
96.50 |
|
efficientnet-b0_3rdparty_8xb32_in1k |
5.29 |
0.42 |
76.74 |
93.17 |
|
efficientnet-b0_3rdparty_8xb32-aa_in1k |
5.29 |
0.42 |
77.26 |
93.41 |
|
efficientnet-b0_3rdparty_8xb32-aa-advprop_in1k |
5.29 |
0.42 |
77.53 |
93.61 |
|
efficientnet-b0_3rdparty-ra-noisystudent_in1k |
5.29 |
0.42 |
77.63 |
94.00 |
|
efficientnet-b1_3rdparty_8xb32_in1k |
7.79 |
0.74 |
78.68 |
94.28 |
|
efficientnet-b1_3rdparty_8xb32-aa_in1k |
7.79 |
0.74 |
79.20 |
94.42 |
|
efficientnet-b1_3rdparty_8xb32-aa-advprop_in1k |
7.79 |
0.74 |
79.52 |
94.43 |
|
efficientnet-b1_3rdparty-ra-noisystudent_in1k |
7.79 |
0.74 |
81.44 |
95.83 |
|
efficientnet-b2_3rdparty_8xb32_in1k |
9.11 |
1.07 |
79.64 |
94.80 |
|
efficientnet-b2_3rdparty_8xb32-aa_in1k |
9.11 |
1.07 |
80.21 |
94.96 |
|
efficientnet-b2_3rdparty_8xb32-aa-advprop_in1k |
9.11 |
1.07 |
80.45 |
95.07 |
|
efficientnet-b2_3rdparty-ra-noisystudent_in1k |
9.11 |
1.07 |
82.47 |
96.23 |
|
efficientnet-b3_3rdparty_8xb32_in1k |
12.23 |
1.95 |
81.01 |
95.34 |
|
efficientnet-b3_3rdparty_8xb32-aa_in1k |
12.23 |
1.95 |
81.58 |
95.67 |
|
efficientnet-b3_3rdparty_8xb32-aa-advprop_in1k |
12.23 |
1.95 |
81.81 |
95.69 |
|
efficientnet-b3_3rdparty-ra-noisystudent_in1k |
12.23 |
1.95 |
84.02 |
96.89 |
|
efficientnet-b4_3rdparty_8xb32_in1k |
19.34 |
4.66 |
82.57 |
96.09 |
|
efficientnet-b4_3rdparty_8xb32-aa_in1k |
19.34 |
4.66 |
82.95 |
96.26 |
|
efficientnet-b4_3rdparty_8xb32-aa-advprop_in1k |
19.34 |
4.66 |
83.25 |
96.44 |
|
efficientnet-b4_3rdparty-ra-noisystudent_in1k |
19.34 |
4.66 |
85.25 |
97.52 |
|
efficientnet-b5_3rdparty_8xb32_in1k |
30.39 |
10.80 |
83.18 |
96.47 |
|
efficientnet-b5_3rdparty_8xb32-aa_in1k |
30.39 |
10.80 |
83.82 |
96.76 |
|
efficientnet-b5_3rdparty_8xb32-aa-advprop_in1k |
30.39 |
10.80 |
84.21 |
96.98 |
|
efficientnet-b5_3rdparty-ra-noisystudent_in1k |
30.39 |
10.80 |
86.08 |
97.75 |
|
efficientnet-b6_3rdparty_8xb32-aa_in1k |
43.04 |
19.97 |
84.05 |
96.82 |
|
efficientnet-b6_3rdparty_8xb32-aa-advprop_in1k |
43.04 |
19.97 |
84.74 |
97.14 |
|
efficientnet-b6_3rdparty-ra-noisystudent_in1k |
43.04 |
19.97 |
86.47 |
97.87 |
|
efficientnet-b7_3rdparty_8xb32-aa_in1k |
66.35 |
39.32 |
84.38 |
96.88 |
|
efficientnet-b7_3rdparty_8xb32-aa-advprop_in1k |
66.35 |
39.32 |
85.14 |
97.23 |
|
efficientnet-b7_3rdparty-ra-noisystudent_in1k |
66.35 |
39.32 |
86.83 |
98.08 |
|
efficientnet-b8_3rdparty_8xb32-aa-advprop_in1k |
87.41 |
65.00 |
85.38 |
97.28 |
|
efficientnet-l2_3rdparty-ra-noisystudent_in1k-800px |
480.31 |
174.20 |
88.33 |
98.65 |
|
efficientnet-l2_3rdparty-ra-noisystudent_in1k-475px |
480.31 |
484.98 |
88.18 |
98.55 |
|
convnext-tiny_32xb128_in1k |
28.59 |
4.46 |
82.14 |
96.06 |
|
convnext-tiny_32xb128-noema_in1k |
28.59 |
4.46 |
81.95 |
95.89 |
|
convnext-tiny_in21k-pre_3rdparty_in1k |
28.59 |
4.46 |
82.90 |
96.62 |
|
convnext-tiny_in21k-pre_3rdparty_in1k-384px |
28.59 |
13.14 |
84.11 |
97.14 |
|
convnext-small_32xb128_in1k |
50.22 |
8.69 |
83.16 |
96.56 |
|
convnext-small_32xb128-noema_in1k |
50.22 |
8.69 |
83.21 |
96.48 |
|
convnext-small_in21k-pre_3rdparty_in1k |
50.22 |
8.69 |
84.59 |
97.41 |
|
convnext-small_in21k-pre_3rdparty_in1k-384px |
50.22 |
25.58 |
85.75 |
97.88 |
|
convnext-base_32xb128_in1k |
88.59 |
15.36 |
83.66 |
96.74 |
|
convnext-base_32xb128-noema_in1k |
88.59 |
15.36 |
83.64 |
96.61 |
|
convnext-base_3rdparty_in1k |
88.59 |
15.36 |
83.85 |
96.74 |
|
convnext-base_3rdparty-noema_in1k |
88.59 |
15.36 |
83.71 |
96.60 |
|
convnext-base_3rdparty_in1k-384px |
88.59 |
45.21 |
85.10 |
97.34 |
|
convnext-base_in21k-pre_3rdparty_in1k |
88.59 |
15.36 |
85.81 |
97.86 |
|
convnext-base_in21k-pre-3rdparty_in1k-384px |
88.59 |
45.21 |
86.82 |
98.25 |
|
convnext-large_3rdparty_in1k |
197.77 |
34.37 |
84.30 |
96.89 |
|
convnext-large_3rdparty_in1k-384px |
197.77 |
101.10 |
85.50 |
97.59 |
|
convnext-large_in21k-pre_3rdparty_in1k |
197.77 |
34.37 |
86.61 |
98.04 |
|
convnext-large_in21k-pre-3rdparty_in1k-384px |
197.77 |
101.10 |
87.46 |
98.37 |
|
convnext-xlarge_in21k-pre_3rdparty_in1k |
350.20 |
60.93 |
86.97 |
98.20 |
|
convnext-xlarge_in21k-pre-3rdparty_in1k-384px |
350.20 |
179.20 |
87.76 |
98.55 |
|
hrnet-w18_3rdparty_8xb32_in1k |
21.30 |
4.33 |
76.75 |
93.44 |
|
hrnet-w30_3rdparty_8xb32_in1k |
37.71 |
8.17 |
78.19 |
94.22 |
|
hrnet-w32_3rdparty_8xb32_in1k |
41.23 |
8.99 |
78.44 |
94.19 |
|
hrnet-w40_3rdparty_8xb32_in1k |
57.55 |
12.77 |
78.94 |
94.47 |
|
hrnet-w44_3rdparty_8xb32_in1k |
67.06 |
14.96 |
78.88 |
94.37 |
|
hrnet-w48_3rdparty_8xb32_in1k |
77.47 |
17.36 |
79.32 |
94.52 |
|
hrnet-w64_3rdparty_8xb32_in1k |
128.06 |
29.00 |
79.46 |
94.65 |
|
hrnet-w18_3rdparty_8xb32-ssld_in1k |
21.30 |
4.33 |
81.06 |
95.70 |
|
hrnet-w48_3rdparty_8xb32-ssld_in1k |
77.47 |
17.36 |
83.63 |
96.79 |
|
repmlp-base_3rdparty_8xb64_in1k |
68.24 |
6.71 |
80.41 |
95.14 |
|
repmlp-base_3rdparty_8xb64_in1k-256px.py |
96.45 |
9.69 |
81.11 |
95.50 |
|
wide-resnet50_3rdparty_8xb32_in1k |
68.88 |
11.44 |
78.48 |
94.08 |
|
wide-resnet101_3rdparty_8xb32_in1k |
126.89 |
22.81 |
78.84 |
94.28 |
|
wide-resnet50_3rdparty-timm_8xb32_in1k |
68.88 |
11.44 |
81.45 |
95.53 |
|
van-tiny_8xb128_in1k |
4.11 |
0.88 |
75.41 |
93.02 |
|
van-small_8xb128_in1k |
13.86 |
2.52 |
81.01 |
95.63 |
|
van-base_8xb128_in1k |
26.58 |
5.03 |
82.80 |
96.21 |
|
van-large_8xb128_in1k |
44.77 |
8.99 |
83.86 |
96.73 |
|
cspdarknet50_3rdparty_8xb32_in1k |
27.64 |
5.04 |
80.05 |
95.07 |
|
cspresnet50_3rdparty_8xb32_in1k |
21.62 |
3.48 |
79.55 |
94.68 |
|
cspresnext50_3rdparty_8xb32_in1k |
20.57 |
3.11 |
79.96 |
94.96 |
|
convmixer-768-32_10xb64_in1k |
21.11 |
19.62 |
80.16 |
95.08 |
|
convmixer-1024-20_10xb64_in1k |
24.38 |
5.55 |
76.94 |
93.36 |
|
convmixer-1536-20_10xb64_in1k |
51.63 |
48.71 |
81.37 |
95.61 |
|
densenet121_4xb256_in1k |
7.98 |
2.88 |
74.96 |
92.21 |
|
densenet169_4xb256_in1k |
14.15 |
3.42 |
76.08 |
93.11 |
|
densenet201_4xb256_in1k |
20.01 |
4.37 |
77.32 |
93.64 |
|
densenet161_4xb256_in1k |
28.68 |
7.82 |
77.61 |
93.83 |
|
poolformer-s12_3rdparty_32xb128_in1k |
11.92 |
1.87 |
77.24 |
93.51 |
|
poolformer-s24_3rdparty_32xb128_in1k |
21.39 |
3.51 |
80.33 |
95.05 |
|
poolformer-s36_3rdparty_32xb128_in1k |
30.86 |
5.15 |
81.43 |
95.45 |
|
poolformer-m36_3rdparty_32xb128_in1k |
56.17 |
8.96 |
82.14 |
95.71 |
|
poolformer-m48_3rdparty_32xb128_in1k |
73.47 |
11.80 |
82.51 |
95.95 |
|
inception-v3_3rdparty_8xb32_in1k |
23.83 |
5.75 |
77.57 |
93.58 |
|
mvitv2-tiny_3rdparty_in1k |
24.17 |
4.70 |
82.33 |
96.15 |
|
mvitv2-small_3rdparty_in1k |
34.87 |
7.00 |
83.63 |
96.51 |
|
mvitv2-base_3rdparty_in1k |
51.47 |
10.16 |
84.34 |
96.86 |
|
mvitv2-large_3rdparty_in1k |
217.99 |
43.87 |
85.25 |
97.14 |
|
edgenext-xxsmall_3rdparty_in1k |
1.33 |
0.26 |
71.20 |
89.91 |
|
edgenext-xsmall_3rdparty_in1k |
2.34 |
0.53 |
74.86 |
92.31 |
|
edgenext-small_3rdparty_in1k |
5.59 |
1.25 |
79.41 |
94.53 |
|
edgenext-small-usi_3rdparty_in1k |
5.59 |
1.25 |
81.06 |
95.34 |
|
edgenext-base_3rdparty_in1k |
18.51 |
3.81 |
82.48 |
96.20 |
|
edgenext-base_3rdparty-usi_in1k |
18.51 |
3.81 |
83.67 |
96.70 |
|
mobileone-s0_8xb32_in1k |
2.08 |
0.27 |
71.34 |
89.87 |
|
mobileone-s1_8xb32_in1k |
4.76 |
0.82 |
75.72 |
92.54 |
|
mobileone-s2_8xb32_in1k |
7.81 |
1.30 |
77.37 |
93.34 |
|
mobileone-s3_8xb32_in1k |
10.08 |
1.89 |
78.06 |
93.83 |
|
mobileone-s4_8xb32_in1k |
14.84 |
2.98 |
79.69 |
94.46 |
|
efficientformer-l1_3rdparty_8xb128_in1k |
12.28 |
1.30 |
80.46 |
94.99 |
|
efficientformer-l3_3rdparty_8xb128_in1k |
31.41 |
3.74 |
82.45 |
96.18 |
|
efficientformer-l7_3rdparty_8xb128_in1k |
82.23 |
10.16 |
83.40 |
96.60 |
|
swinv2-tiny-w8_3rdparty_in1k-256px |
28.35 |
4.35 |
81.76 |
95.87 |
|
swinv2-tiny-w16_3rdparty_in1k-256px |
28.35 |
4.40 |
82.81 |
96.23 |
|
swinv2-small-w8_3rdparty_in1k-256px |
49.73 |
8.45 |
83.74 |
96.60 |
|
swinv2-small-w16_3rdparty_in1k-256px |
49.73 |
8.57 |
84.13 |
96.83 |
|
swinv2-base-w8_3rdparty_in1k-256px |
87.92 |
14.99 |
84.20 |
96.86 |
|
swinv2-base-w16_3rdparty_in1k-256px |
87.92 |
15.14 |
84.60 |
97.05 |
|
swinv2-base-w16_in21k-pre_3rdparty_in1k-256px |
87.92 |
15.14 |
86.17 |
97.88 |
|
swinv2-base-w24_in21k-pre_3rdparty_in1k-384px |
87.92 |
34.07 |
87.14 |
98.23 |
|
swinv2-large-w16_in21k-pre_3rdparty_in1k-256px |
196.75 |
33.86 |
86.93 |
98.06 |
|
swinv2-large-w24_in21k-pre_3rdparty_in1k-384px |
196.75 |
76.20 |
87.59 |
98.27 |
|
deit3-small-p16_3rdparty_in1k |
22.06 |
4.61 |
81.35 |
95.31 |
|
deit3-small-p16_3rdparty_in1k-384px |
22.21 |
15.52 |
83.43 |
96.68 |
|
deit3-small-p16_in21k-pre_3rdparty_in1k |
22.06 |
4.61 |
83.06 |
96.77 |
|
deit3-small-p16_in21k-pre_3rdparty_in1k-384px |
22.21 |
15.52 |
84.84 |
97.48 |
|
deit3-medium-p16_3rdparty_in1k |
38.85 |
8.00 |
82.99 |
96.22 |
|
deit3-medium-p16_in21k-pre_3rdparty_in1k |
38.85 |
8.00 |
84.56 |
97.19 |
|
deit3-base-p16_3rdparty_in1k |
86.59 |
17.58 |
83.80 |
96.55 |
|
deit3-base-p16_3rdparty_in1k-384px |
86.88 |
55.54 |
85.08 |
97.25 |
|
deit3-base-p16_in21k-pre_3rdparty_in1k |
86.59 |
17.58 |
85.70 |
97.75 |
|
deit3-base-p16_in21k-pre_3rdparty_in1k-384px |
86.88 |
55.54 |
86.73 |
98.11 |
|
deit3-large-p16_3rdparty_in1k |
304.37 |
61.60 |
84.87 |
97.01 |
|
deit3-large-p16_3rdparty_in1k-384px |
304.76 |
191.21 |
85.82 |
97.60 |
|
deit3-large-p16_in21k-pre_3rdparty_in1k |
304.37 |
61.60 |
86.97 |
98.24 |
|
deit3-large-p16_in21k-pre_3rdparty_in1k-384px |
304.76 |
191.21 |
87.73 |
98.51 |
|
deit3-huge-p14_3rdparty_in1k |
632.13 |
167.40 |
85.21 |
97.36 |
|
deit3-huge-p14_in21k-pre_3rdparty_in1k |
632.13 |
167.40 |
87.19 |
98.26 |
|
hornet-tiny_3rdparty_in1k |
22.41 |
3.98 |
82.84 |
96.24 |
|
hornet-tiny-gf_3rdparty_in1k |
22.99 |
3.90 |
82.98 |
96.38 |
|
hornet-small_3rdparty_in1k |
49.53 |
8.83 |
83.79 |
96.75 |
|
hornet-small-gf_3rdparty_in1k |
50.40 |
8.71 |
83.98 |
96.77 |
|
hornet-base_3rdparty_in1k |
87.26 |
15.58 |
84.24 |
96.94 |
|
hornet-base-gf_3rdparty_in1k |
88.42 |
15.42 |
84.32 |
96.95 |
|
mobilevit-small_3rdparty_in1k |
5.58 |
2.03 |
78.25 |
94.09 |
|
mobilevit-xsmall_3rdparty_in1k |
2.32 |
1.05 |
74.75 |
92.32 |
|
mobilevit-xxsmall_3rdparty_in1k |
1.27 |
0.42 |
69.02 |
88.91 |
|
davit-tiny_3rdparty_in1k |
28.36 |
4.54 |
82.24 |
96.13 |
|
davit-small_3rdparty_in1k |
49.75 |
8.80 |
83.61 |
96.75 |
|
davit-base_3rdparty_in1k |
87.95 |
15.51 |
84.09 |
96.82 |
|
replknet-31B_3rdparty_in1k |
79.86 |
15.64 |
83.48 |
96.57 |
|
replknet-31B_3rdparty_in1k-384px |
79.86 |
45.95 |
84.84 |
97.34 |
|
replknet-31B_in21k-pre_3rdparty_in1k |
79.86 |
15.64 |
85.20 |
97.56 |
|
replknet-31B_in21k-pre_3rdparty_in1k-384px |
79.86 |
45.95 |
85.99 |
97.75 |
|
replknet-31L_in21k-pre_3rdparty_in1k-384px |
172.67 |
97.24 |
86.63 |
98.00 |
|
replknet-XL_meg73m-pre_3rdparty_in1k-320px |
335.44 |
129.57 |
87.57 |
98.39 |
|
beit-base_3rdparty_in1k |
86.53 |
17.58 |
85.28 |
97.59 |
|
beitv2-base_3rdparty_in1k |
86.53 |
17.58 |
86.47 |
97.99 |
|
eva-g-p14_30m-in21k-pre_3rdparty_in1k-336px |
1013.01 |
620.64 |
89.61 |
98.93 |
|
eva-g-p14_30m-in21k-pre_3rdparty_in1k-560px |
1014.45 |
1906.76 |
89.71 |
98.96 |
|
eva-l-p14_mim-pre_3rdparty_in1k-336px |
304.53 |
191.10 |
88.66 |
98.75 |
|
eva-l-p14_mim-in21k-pre_3rdparty_in1k-336px |
304.53 |
191.10 |
89.17 |
98.86 |
|
eva-l-p14_mim-pre_3rdparty_in1k-196px |
304.14 |
61.57 |
87.94 |
98.50 |
|
eva-l-p14_mim-in21k-pre_3rdparty_in1k-196px |
304.14 |
61.57 |
88.58 |
98.65 |
|
revvit-small_3rdparty_in1k |
22.44 |
4.58 |
79.87 |
94.90 |
|
revvit-base_3rdparty_in1k |
87.34 |
17.49 |
81.81 |
95.56 |
|
clip-vit-base-p32_laion2b-in12k-pre_3rdparty_in1k |
88.22 |
4.36 |
83.06 |
96.49 |
|
clip-vit-base-p32_laion2b-pre_3rdparty_in1k |
88.22 |
4.36 |
82.46 |
96.12 |
|
clip-vit-base-p32_openai-pre_3rdparty_in1k |
88.22 |
4.36 |
81.77 |
95.89 |
|
clip-vit-base-p32_laion2b-in12k-pre_3rdparty_in1k-384px |
88.22 |
12.66 |
85.39 |
97.67 |
|
clip-vit-base-p32_openai-in12k-pre_3rdparty_in1k-384px |
88.22 |
12.66 |
85.13 |
97.42 |
|
clip-vit-base-p16_laion2b-in12k-pre_3rdparty_in1k |
86.57 |
16.86 |
86.02 |
97.76 |
|
clip-vit-base-p16_laion2b-pre_3rdparty_in1k |
86.57 |
16.86 |
85.49 |
97.59 |
|
clip-vit-base-p16_openai-in12k-pre_3rdparty_in1k |
86.57 |
16.86 |
85.99 |
97.72 |
|
clip-vit-base-p16_openai-pre_3rdparty_in1k |
86.57 |
16.86 |
85.30 |
97.50 |
|
clip-vit-base-p32_laion2b-in12k-pre_3rdparty_in1k-448px |
88.22 |
17.20 |
85.76 |
97.63 |
|
clip-vit-base-p16_laion2b-in12k-pre_3rdparty_in1k-384px |
86.57 |
49.37 |
87.17 |
98.02 |
|
clip-vit-base-p16_laion2b-pre_3rdparty_in1k-384px |
86.57 |
49.37 |
86.52 |
97.97 |
|
clip-vit-base-p16_openai-in12k-pre_3rdparty_in1k-384px |
86.57 |
49.37 |
86.87 |
98.05 |
|
clip-vit-base-p16_openai-pre_3rdparty_in1k-384px |
86.57 |
49.37 |
86.25 |
97.90 |
|
mixmim-base_3rdparty_in1k |
88.34 |
16.35 |
84.60 |
97.00 |
|
efficientnetv2-b0_3rdparty_in1k |
7.14 |
0.92 |
78.52 |
94.44 |
|
efficientnetv2-b1_3rdparty_in1k |
8.14 |
1.44 |
79.80 |
94.89 |
|
efficientnetv2-b2_3rdparty_in1k |
10.10 |
1.99 |
80.63 |
95.30 |
|
efficientnetv2-b3_3rdparty_in1k |
14.36 |
3.50 |
82.03 |
95.88 |
|
efficientnetv2-s_3rdparty_in1k |
21.46 |
9.72 |
83.82 |
96.67 |
|
efficientnetv2-m_3rdparty_in1k |
54.14 |
26.88 |
85.01 |
97.26 |
|
efficientnetv2-l_3rdparty_in1k |
118.52 |
60.14 |
85.43 |
97.31 |
|
efficientnetv2-s_in21k-pre_3rdparty_in1k |
21.46 |
9.72 |
84.29 |
97.26 |
|
efficientnetv2-m_in21k-pre_3rdparty_in1k |
54.14 |
26.88 |
85.47 |
97.76 |
|
efficientnetv2-l_in21k-pre_3rdparty_in1k |
118.52 |
60.14 |
86.31 |
97.99 |
|
efficientnetv2-xl_in21k-pre_3rdparty_in1k |
208.12 |
98.34 |
86.39 |
97.83 |
CIFAR-10¶
Model |
Params (M) |
Flops (G) |
Top-1 (%) |
Top-5 (%) |
Readme |
|---|---|---|---|---|---|
resnet18_8xb16_cifar10 |
11.17 |
0.56 |
94.82 |
||
resnet34_8xb16_cifar10 |
21.28 |
1.16 |
95.34 |
||
resnet50_8xb16_cifar10 |
23.52 |
1.31 |
95.55 |
||
resnet101_8xb16_cifar10 |
42.51 |
2.52 |
95.58 |
||
resnet152_8xb16_cifar10 |
58.16 |
3.74 |
95.76 |
CIFAR-100¶
Model |
Params (M) |
Flops (G) |
Top-1 (%) |
Top-5 (%) |
Readme |
|---|---|---|---|---|---|
resnet50_8xb16_cifar100 |
23.71 |
1.31 |
79.90 |
95.19 |
CUB-200-2011¶
Model |
Params (M) |
Flops (G) |
Top-1 (%) |
Top-5 (%) |
Readme |
|---|---|---|---|---|---|
resnet50_8xb8_cub |
23.92 |
16.48 |
88.45 |
||
swin-large_8xb8_cub_384px |
195.51 |
100.04 |
91.87 |
PASCAL VOC 2007¶
Model |
Params (M) |
Flops (G) |
Top-1 (%) |
Top-5 (%) |
Readme |
|---|---|---|---|---|---|
resnet101-csra_1xb16_voc07-448px |
23.55 |
4.12 |