# ResNet

**Category:** CNN · **Code:**
[`timm/models/resnet.py`](https://github.com/huggingface/pytorch-image-models/blob/main/timm/models/resnet.py) ·
**Architectures:** 81 · **Pretrained weights:** 149 (144 with ImageNet-1k results)

Residual networks (ResNet) and the variants built on the same `ResNet` class: ResNeXt grouped convolutions,
Squeeze-and-Excitation (SE) and ECA channel attention, deep / tiered stems and average pool downsampling (the "c", "d",
"s" and "t" variants), anti-aliased downsampling, Wide ResNet and ResNet-RS configurations.

## Papers

* [Deep Residual Learning for Image Recognition](https://arxiv.org/abs/1512.03385)
* [Bag of Tricks for Image Classification with Convolutional Neural Networks](https://arxiv.org/abs/1812.01187)
* [Aggregated Residual Transformations for Deep Neural Networks](https://arxiv.org/abs/1611.05431)
* [Wide Residual Networks](https://arxiv.org/abs/1605.07146)
* [Squeeze-and-Excitation Networks](https://arxiv.org/abs/1709.01507)
* [ECA-Net: Efficient Channel Attention for Deep Convolutional Neural Networks](https://arxiv.org/abs/1910.03151)
* [Making Convolutional Networks Shift-Invariant Again](https://arxiv.org/abs/1904.11486)
* [Group Normalization](https://arxiv.org/abs/1803.08494)
* [Revisiting ResNets: Improved Training and Scaling Strategies](https://arxiv.org/abs/2103.07579)
* [ResNet strikes back: An improved training procedure in timm](https://arxiv.org/abs/2110.00476)
* [Billion-scale semi-supervised learning for image classification](https://arxiv.org/abs/1905.00546)
* [Exploring the Limits of Weakly Supervised Pretraining](https://arxiv.org/abs/1805.00932)
* [Knapsack Pruning with Inner Distillation](https://arxiv.org/abs/2002.08258)

## Usage

See the [Quickstart](../quickstart) for loading pretrained weights, image preprocessing and fine-tuning, and [Feature
Extraction](../feature_extraction) for using the models as backbones.

```py
>>> import timm
>>> model = timm.create_model('resnet50.a1_in1k', pretrained=True)
>>> data_config = timm.data.resolve_model_data_config(model)
```

## Model API support

| Feature | `ResNet` |
|---|---|
| [`features_only=True` feature maps](../model_api#intermediate-features) | ✓ (strides 2, 4, 8, 16, 32) |
| [`forward_intermediates()`](../model_api#intermediate-features) | ✓ |
| [`prune_intermediate_layers()`](../model_api#intermediate-features) | ✓ |
| [Any input size, no changes needed](../model_api#input-size) | ✓ |
| [`set_input_size()`](../model_api#input-size) | – |
| [`dynamic_img_size=True`](../model_api#input-size) | – |
| [`set_grad_checkpointing()`](../model_api#training-hooks) | ✓ |
| [Layer-wise LR decay (`group_matcher()`)](../model_api#training-hooks) | ✓ |
| [`reset_classifier()`](../model_api#classifier) | ✓ |

✓ supported, ✓ (square) works for square sizes only, ✗ not supported, – not needed (the model already accepts any input
size). Checked by running each feature on a randomly initialized model (`ResNet` with `resnet10t` at 176), other
architectures of the same class are expected to behave the same. See the [Model API](../model_api) page for details.

## Architectures

| Architecture | Params (M) | GMACs | Input size | Pretrained weights |
|---|---:|---:|---:|---:|
| `ecaresnet26t` | 16.01 | 3.35 | 256 | 1 |
| `ecaresnet50d` | 25.58 | 4.35 | 224 | 1 |
| `ecaresnet50d_pruned` | 19.94 | 2.53 | 224 | 1 |
| `ecaresnet50t` | 25.57 | 5.64 | 256 | 4 |
| `ecaresnet101d` | 44.57 | 8.08 | 224 | 1 |
| `ecaresnet101d_pruned` | 24.88 | 3.48 | 224 | 1 |
| `ecaresnet200d` | 64.69 | 20.00 | 256 | 0 |
| `ecaresnet269d` | 102.09 | 41.53 | 320 | 1 |
| `ecaresnetlight` | 30.16 | 4.11 | 224 | 1 |
| `ecaresnext26t_32x4d` | 15.41 | 2.70 | 224 | 0 |
| `ecaresnext50t_32x4d` | 25.05 | - | 224 | 0 |
| `resnet10t` | 5.44 | 0.70 | 176 | 1 |
| `resnet14t` | 10.08 | 1.07 | 176 | 1 |
| `resnet18` | 11.69 | 1.82 | 224 | 7 |
| `resnet18d` | 11.71 | 2.06 | 224 | 2 |
| `resnet26` | 16.00 | 2.36 | 224 | 1 |
| `resnet26d` | 16.01 | 2.60 | 224 | 1 |
| `resnet26t` | 16.01 | 3.35 | 256 | 1 |
| `resnet34` | 21.80 | 3.67 | 224 | 7 |
| `resnet34d` | 21.82 | 3.91 | 224 | 1 |
| `resnet50` | 25.56 | 4.11 | 224 | 18 |
| `resnet50_gn` | 25.56 | 4.14 | 224 | 1 |
| `resnet50c` | 25.58 | 4.35 | 224 | 1 |
| `resnet50d` | 25.58 | 4.35 | 224 | 6 |
| `resnet50s` | 25.68 | 5.47 | 224 | 1 |
| `resnet50t` | 25.57 | 4.32 | 224 | 0 |
| `resnet101` | 44.55 | 7.83 | 224 | 7 |
| `resnet101c` | 44.57 | 8.08 | 224 | 1 |
| `resnet101d` | 44.57 | 10.55 | 256 | 2 |
| `resnet101s` | 44.67 | 9.19 | 224 | 1 |
| `resnet152` | 60.19 | 11.56 | 224 | 7 |
| `resnet152c` | 60.21 | 11.80 | 224 | 1 |
| `resnet152d` | 60.21 | 15.41 | 256 | 2 |
| `resnet152s` | 60.32 | 12.92 | 224 | 1 |
| `resnet200` | 64.67 | 15.07 | 224 | 0 |
| `resnet200d` | 64.69 | 20.00 | 256 | 1 |
| `resnetaa34d` | 21.82 | 4.43 | 224 | 0 |
| `resnetaa50` | 25.56 | 5.15 | 224 | 1 |
| `resnetaa50d` | 25.58 | 5.39 | 224 | 3 |
| `resnetaa101d` | 44.57 | 9.12 | 224 | 2 |
| `resnetblur18` | 11.69 | 2.34 | 224 | 0 |
| `resnetblur50` | 25.56 | 5.16 | 224 | 1 |
| `resnetblur50d` | 25.58 | 5.40 | 224 | 0 |
| `resnetblur101d` | 44.57 | 9.12 | 224 | 0 |
| `resnetrs50` | 35.69 | 2.29 | 160 | 1 |
| `resnetrs101` | 63.62 | 6.04 | 192 | 1 |
| `resnetrs152` | 86.62 | 15.59 | 256 | 1 |
| `resnetrs200` | 93.21 | 20.18 | 256 | 1 |
| `resnetrs270` | 129.86 | 27.06 | 256 | 1 |
| `resnetrs350` | 163.96 | 43.67 | 288 | 1 |
| `resnetrs420` | 191.89 | 64.20 | 320 | 1 |
| `resnext50_32x4d` | 25.03 | 4.26 | 224 | 10 |
| `resnext50d_32x4d` | 25.05 | 4.50 | 224 | 1 |
| `resnext101_32x4d` | 44.18 | 8.01 | 224 | 3 |
| `resnext101_32x8d` | 88.79 | 16.48 | 224 | 5 |
| `resnext101_32x16d` | 194.03 | 36.27 | 224 | 3 |
| `resnext101_32x32d` | 468.53 | 87.29 | 224 | 1 |
| `resnext101_64x4d` | 83.46 | 15.52 | 224 | 3 |
| `senet154` | 115.09 | 20.77 | 224 | 1 |
| `seresnet18` | 11.78 | 1.82 | 224 | 0 |
| `seresnet34` | 21.96 | 3.67 | 224 | 0 |
| `seresnet50` | 28.09 | 4.11 | 224 | 4 |
| `seresnet50t` | 28.10 | 4.32 | 224 | 0 |
| `seresnet101` | 49.33 | 7.84 | 224 | 0 |
| `seresnet152` | 66.82 | 11.57 | 224 | 0 |
| `seresnet152d` | 66.84 | 15.42 | 256 | 1 |
| `seresnet200d` | 71.86 | 20.01 | 256 | 0 |
| `seresnet269d` | 113.67 | 26.59 | 256 | 0 |
| `seresnetaa50d` | 28.11 | 5.40 | 224 | 0 |
| `seresnext26d_32x4d` | 16.81 | 2.73 | 224 | 1 |
| `seresnext26t_32x4d` | 16.81 | 2.70 | 224 | 1 |
| `seresnext50_32x4d` | 27.56 | 4.26 | 224 | 2 |
| `seresnext101_32x4d` | 48.96 | 8.02 | 224 | 1 |
| `seresnext101_32x8d` | 93.57 | 16.48 | 224 | 1 |
| `seresnext101_64x4d` | 88.23 | 15.53 | 224 | 1 |
| `seresnext101d_32x8d` | 93.59 | 16.72 | 224 | 1 |
| `seresnextaa101d_32x8d` | 93.59 | 28.51 | 288 | 4 |
| `seresnextaa201d_32x8d` | 149.39 | 101.11 | 384 | 2 |
| `test_resnet` | 0.47 | 0.10 | 160 | 1 |
| `wide_resnet50_2` | 68.88 | 11.43 | 224 | 3 |
| `wide_resnet101_2` | 126.89 | 22.80 | 224 | 2 |

GMACs and parameter counts are for the default input size and classifier of each architecture, from the [benchmark
results](https://github.com/huggingface/pytorch-image-models/tree/main/results).

## Pretrained weights

Top-1 is ImageNet-1k validation accuracy from
[`results-imagenet.csv`](https://github.com/huggingface/pytorch-image-models/blob/main/results/results-imagenet.csv) at
the listed eval size, - if the weight has no ImageNet-1k result (e.g. pretraining or image-text weights). Classes is the
size of the pretrained classifier, none for weights without one.

Weights are grouped by source: the paper or origin given in the pretrained config, else a Hub organization other than
`timm`, else the first part of the pretrained tag (`architecture.tag`). Sources with a single weight are listed under
other.

### ResNet strikes back

Pretrained configs reference [ResNet strikes back: An improved training procedure in
timm](https://arxiv.org/abs/2110.00476).

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `ecaresnet50t.a1_in1k` | 224 (test 288) | 82.110 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/ecaresnet50t.a1_in1k) |
| `ecaresnet50t.a2_in1k` | 224 (test 288) | 81.682 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/ecaresnet50t.a2_in1k) |
| `ecaresnet50t.a3_in1k` | 160 (test 224) | 79.548 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/ecaresnet50t.a3_in1k) |
| `resnet18.a1_in1k` | 224 (test 288) | 73.164 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet18.a1_in1k) |
| `resnet18.a2_in1k` | 224 (test 288) | 72.364 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet18.a2_in1k) |
| `resnet18.a3_in1k` | 160 (test 224) | 68.250 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet18.a3_in1k) |
| `resnet18d.ra4_e3600_r224_in1k` | 224 (test 288) | 76.012 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet18d.ra4_e3600_r224_in1k) |
| `resnet34.a1_in1k` | 224 (test 288) | 77.930 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet34.a1_in1k) |
| `resnet34.a2_in1k` | 224 (test 288) | 77.150 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet34.a2_in1k) |
| `resnet34.a3_in1k` | 160 (test 224) | 72.996 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet34.a3_in1k) |
| `resnet34.ra4_e3600_r224_in1k` | 224 (test 288) | 78.972 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet34.ra4_e3600_r224_in1k) |
| `resnet50.a1_in1k` | 224 (test 288) | 81.240 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet50.a1_in1k) |
| `resnet50.a1h_in1k` | 176 (test 224) | 80.654 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet50.a1h_in1k) |
| `resnet50.a2_in1k` | 224 (test 288) | 80.774 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet50.a2_in1k) |
| `resnet50.a3_in1k` | 160 (test 224) | 78.052 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet50.a3_in1k) |
| `resnet50.b1k_in1k` | 224 (test 288) | 80.708 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet50.b1k_in1k) |
| `resnet50.b2k_in1k` | 224 (test 288) | 80.466 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet50.b2k_in1k) |
| `resnet50.c1_in1k` | 224 (test 288) | 80.928 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet50.c1_in1k) |
| `resnet50.c2_in1k` | 224 (test 288) | 80.862 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet50.c2_in1k) |
| `resnet50.d_in1k` | 224 (test 288) | 81.012 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet50.d_in1k) |
| `resnet50d.a1_in1k` | 224 (test 288) | 81.466 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet50d.a1_in1k) |
| `resnet50d.a2_in1k` | 224 (test 288) | 81.164 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet50d.a2_in1k) |
| `resnet50d.a3_in1k` | 160 (test 224) | 78.742 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet50d.a3_in1k) |
| `resnet50d.ra4_e3600_r224_in1k` | 224 (test 288) | 81.840 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet50d.ra4_e3600_r224_in1k) |
| `resnet101.a1_in1k` | 224 (test 288) | 82.326 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet101.a1_in1k) |
| `resnet101.a1h_in1k` | 224 (test 288) | 82.796 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet101.a1h_in1k) |
| `resnet101.a2_in1k` | 224 (test 288) | 82.218 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet101.a2_in1k) |
| `resnet101.a3_in1k` | 160 (test 224) | 79.836 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet101.a3_in1k) |
| `resnet152.a1_in1k` | 224 (test 288) | 82.742 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet152.a1_in1k) |
| `resnet152.a1h_in1k` | 224 (test 288) | 83.494 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet152.a1h_in1k) |
| `resnet152.a2_in1k` | 224 (test 288) | 82.614 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet152.a2_in1k) |
| `resnet152.a3_in1k` | 160 (test 224) | 80.548 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet152.a3_in1k) |
| `resnetaa50.a1h_in1k` | 224 (test 288) | 81.618 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnetaa50.a1h_in1k) |
| `resnext50_32x4d.a1_in1k` | 224 (test 288) | 81.480 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnext50_32x4d.a1_in1k) |
| `resnext50_32x4d.a1h_in1k` | 224 (test 288) | 82.016 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnext50_32x4d.a1h_in1k) |
| `resnext50_32x4d.a2_in1k` | 224 (test 288) | 81.304 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnext50_32x4d.a2_in1k) |
| `resnext50_32x4d.a3_in1k` | 160 (test 224) | 79.258 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnext50_32x4d.a3_in1k) |
| `resnext101_64x4d.c1_in1k` | 224 (test 288) | 83.158 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnext101_64x4d.c1_in1k) |
| `seresnet50.a1_in1k` | 224 (test 288) | 81.114 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/seresnet50.a1_in1k) |
| `seresnet50.a2_in1k` | 224 (test 288) | 81.094 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/seresnet50.a2_in1k) |
| `seresnet50.a3_in1k` | 160 (test 224) | 77.036 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/seresnet50.a3_in1k) |
| `seresnext101_32x8d.ah_in1k` | 224 (test 288) | 84.192 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/seresnext101_32x8d.ah_in1k) |
| `seresnext101d_32x8d.ah_in1k` | 224 (test 288) | 84.380 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/seresnext101d_32x8d.ah_in1k) |
| `seresnextaa101d_32x8d.ah_in1k` | 224 (test 288) | 84.580 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/seresnextaa101d_32x8d.ah_in1k) |

### huggingface/pytorch-image-models

Origin: [github.com/huggingface/pytorch-image-models](https://github.com/huggingface/pytorch-image-models)

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `ecaresnet26t.ra2_in1k` | 256 (test 320) | 79.900 | 320 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/ecaresnet26t.ra2_in1k) |
| `ecaresnet269d.ra2_in1k` | 320 (test 352) | 84.968 | 352 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/ecaresnet269d.ra2_in1k) |
| `resnet10t.c3_in1k` | 176 (test 224) | 68.354 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet10t.c3_in1k) |
| `resnet14t.c3_in1k` | 176 (test 224) | 72.242 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet14t.c3_in1k) |
| `resnet18d.ra2_in1k` | 224 (test 288) | 73.790 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet18d.ra2_in1k) |
| `resnet26.bt_in1k` | 224 (test 288) | 76.384 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet26.bt_in1k) |
| `resnet26d.bt_in1k` | 224 (test 288) | 77.422 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet26d.bt_in1k) |
| `resnet26t.ra2_in1k` | 256 (test 320) | 78.330 | 320 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet26t.ra2_in1k) |
| `resnet34.bt_in1k` | 224 (test 288) | 76.506 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet34.bt_in1k) |
| `resnet34d.ra2_in1k` | 224 (test 288) | 78.440 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet34d.ra2_in1k) |
| `resnet50.bt_in1k` | 224 (test 288) | 79.652 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet50.bt_in1k) |
| `resnet50.ra_in1k` | 224 (test 288) | 79.864 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet50.ra_in1k) |
| `resnet50.ram_in1k` | 224 (test 288) | 79.982 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet50.ram_in1k) |
| `resnet50_gn.a1h_in1k` | 224 (test 288) | 81.216 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet50_gn.a1h_in1k) |
| `resnet50d.ra2_in1k` | 224 (test 288) | 81.354 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet50d.ra2_in1k) |
| `resnet101d.ra2_in1k` | 256 (test 320) | 83.020 | 320 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet101d.ra2_in1k) |
| `resnet152d.ra2_in1k` | 256 (test 320) | 83.684 | 320 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet152d.ra2_in1k) |
| `resnet200d.ra2_in1k` | 256 (test 320) | 83.976 | 320 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet200d.ra2_in1k) |
| `resnetaa50d.d_in12k` | 224 (test 288) | - | - | 11821 | apache-2.0 | [timm](https://huggingface.co/timm/resnetaa50d.d_in12k) |
| `resnetaa50d.sw_in12k` | 224 (test 288) | - | - | 11821 | apache-2.0 | [timm](https://huggingface.co/timm/resnetaa50d.sw_in12k) |
| `resnetaa50d.sw_in12k_ft_in1k` | 224 (test 288) | 82.656 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnetaa50d.sw_in12k_ft_in1k) |
| `resnetaa101d.sw_in12k` | 224 (test 288) | - | - | 11821 | apache-2.0 | [timm](https://huggingface.co/timm/resnetaa101d.sw_in12k) |
| `resnetaa101d.sw_in12k_ft_in1k` | 224 (test 288) | 84.114 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnetaa101d.sw_in12k_ft_in1k) |
| `resnetblur50.bt_in1k` | 224 (test 288) | 80.248 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnetblur50.bt_in1k) |
| `resnext50_32x4d.ra_in1k` | 224 (test 288) | 80.720 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnext50_32x4d.ra_in1k) |
| `resnext50d_32x4d.bt_in1k` | 224 (test 288) | 80.676 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnext50d_32x4d.bt_in1k) |
| `seresnet50.ra2_in1k` | 224 (test 288) | 81.288 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/seresnet50.ra2_in1k) |
| `seresnet152d.ra2_in1k` | 256 (test 320) | 84.344 | 320 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/seresnet152d.ra2_in1k) |
| `seresnext26d_32x4d.bt_in1k` | 224 (test 288) | 78.816 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/seresnext26d_32x4d.bt_in1k) |
| `seresnext26t_32x4d.bt_in1k` | 224 (test 288) | 78.736 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/seresnext26t_32x4d.bt_in1k) |
| `seresnext50_32x4d.racm_in1k` | 224 (test 288) | 82.186 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/seresnext50_32x4d.racm_in1k) |
| `seresnextaa101d_32x8d.sw_in12k` | 224 (test 288) | - | - | 11821 | apache-2.0 | [timm](https://huggingface.co/timm/seresnextaa101d_32x8d.sw_in12k) |
| `seresnextaa101d_32x8d.sw_in12k_ft_in1k` | 224 (test 288) | 86.524 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/seresnextaa101d_32x8d.sw_in12k_ft_in1k) |
| `seresnextaa101d_32x8d.sw_in12k_ft_in1k_288` | 288 (test 320) | 86.722 | 320 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/seresnextaa101d_32x8d.sw_in12k_ft_in1k_288) |
| `wide_resnet50_2.racm_in1k` | 224 (test 288) | 82.260 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/wide_resnet50_2.racm_in1k) |

### cv.gluon.ai

Origin: [cv.gluon.ai/model_zoo/classification.html](https://cv.gluon.ai/model_zoo/classification.html)

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `resnet18.gluon_in1k` | 224 | 70.844 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet18.gluon_in1k) |
| `resnet34.gluon_in1k` | 224 | 74.574 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet34.gluon_in1k) |
| `resnet50.gluon_in1k` | 224 | 77.580 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet50.gluon_in1k) |
| `resnet50c.gluon_in1k` | 224 | 78.016 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet50c.gluon_in1k) |
| `resnet50d.gluon_in1k` | 224 | 79.080 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet50d.gluon_in1k) |
| `resnet50s.gluon_in1k` | 224 | 78.710 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet50s.gluon_in1k) |
| `resnet101.gluon_in1k` | 224 | 79.306 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet101.gluon_in1k) |
| `resnet101c.gluon_in1k` | 224 | 79.542 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet101c.gluon_in1k) |
| `resnet101d.gluon_in1k` | 224 | 80.466 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet101d.gluon_in1k) |
| `resnet101s.gluon_in1k` | 224 | 80.278 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet101s.gluon_in1k) |
| `resnet152.gluon_in1k` | 224 | 79.712 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet152.gluon_in1k) |
| `resnet152c.gluon_in1k` | 224 | 79.904 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet152c.gluon_in1k) |
| `resnet152d.gluon_in1k` | 224 | 80.476 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet152d.gluon_in1k) |
| `resnet152s.gluon_in1k` | 224 | 81.048 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet152s.gluon_in1k) |
| `resnext50_32x4d.gluon_in1k` | 224 | 79.354 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnext50_32x4d.gluon_in1k) |
| `resnext101_32x4d.gluon_in1k` | 224 | 80.336 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnext101_32x4d.gluon_in1k) |
| `resnext101_64x4d.gluon_in1k` | 224 | 80.640 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnext101_64x4d.gluon_in1k) |
| `senet154.gluon_in1k` | 224 | 81.258 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/senet154.gluon_in1k) |
| `seresnext50_32x4d.gluon_in1k` | 224 | 79.916 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/seresnext50_32x4d.gluon_in1k) |
| `seresnext101_32x4d.gluon_in1k` | 224 | 80.886 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/seresnext101_32x4d.gluon_in1k) |
| `seresnext101_64x4d.gluon_in1k` | 224 | 80.884 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/seresnext101_64x4d.gluon_in1k) |

### pytorch/vision

Origin: [github.com/pytorch/vision](https://github.com/pytorch/vision)

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `resnet18.tv_in1k` | 224 | 69.752 | 224 | 1000 | bsd-3-clause | [timm](https://huggingface.co/timm/resnet18.tv_in1k) |
| `resnet34.tv_in1k` | 224 | 73.298 | 224 | 1000 | bsd-3-clause | [timm](https://huggingface.co/timm/resnet34.tv_in1k) |
| `resnet50.tv2_in1k` | 176 (test 224) | 80.846 | 224 | 1000 | bsd-3-clause | [timm](https://huggingface.co/timm/resnet50.tv2_in1k) |
| `resnet50.tv_in1k` | 224 | 76.156 | 224 | 1000 | bsd-3-clause | [timm](https://huggingface.co/timm/resnet50.tv_in1k) |
| `resnet101.tv2_in1k` | 176 (test 224) | 81.906 | 224 | 1000 | bsd-3-clause | [timm](https://huggingface.co/timm/resnet101.tv2_in1k) |
| `resnet101.tv_in1k` | 224 | 77.404 | 224 | 1000 | bsd-3-clause | [timm](https://huggingface.co/timm/resnet101.tv_in1k) |
| `resnet152.tv2_in1k` | 176 (test 224) | 82.294 | 224 | 1000 | bsd-3-clause | [timm](https://huggingface.co/timm/resnet152.tv2_in1k) |
| `resnet152.tv_in1k` | 224 | 78.330 | 224 | 1000 | bsd-3-clause | [timm](https://huggingface.co/timm/resnet152.tv_in1k) |
| `resnext50_32x4d.tv2_in1k` | 176 (test 224) | 81.190 | 224 | 1000 | bsd-3-clause | [timm](https://huggingface.co/timm/resnext50_32x4d.tv2_in1k) |
| `resnext50_32x4d.tv_in1k` | 224 | 77.632 | 224 | 1000 | bsd-3-clause | [timm](https://huggingface.co/timm/resnext50_32x4d.tv_in1k) |
| `resnext101_32x8d.tv2_in1k` | 176 (test 224) | 82.832 | 224 | 1000 | bsd-3-clause | [timm](https://huggingface.co/timm/resnext101_32x8d.tv2_in1k) |
| `resnext101_32x8d.tv_in1k` | 224 | 79.308 | 224 | 1000 | bsd-3-clause | [timm](https://huggingface.co/timm/resnext101_32x8d.tv_in1k) |
| `resnext101_64x4d.tv_in1k` | 224 | 82.978 | 224 | 1000 | bsd-3-clause | [timm](https://huggingface.co/timm/resnext101_64x4d.tv_in1k) |
| `wide_resnet50_2.tv2_in1k` | 176 (test 224) | 81.612 | 224 | 1000 | bsd-3-clause | [timm](https://huggingface.co/timm/wide_resnet50_2.tv2_in1k) |
| `wide_resnet50_2.tv_in1k` | 224 | 78.486 | 224 | 1000 | bsd-3-clause | [timm](https://huggingface.co/timm/wide_resnet50_2.tv_in1k) |
| `wide_resnet101_2.tv2_in1k` | 176 (test 224) | 82.514 | 224 | 1000 | bsd-3-clause | [timm](https://huggingface.co/timm/wide_resnet101_2.tv2_in1k) |
| `wide_resnet101_2.tv_in1k` | 224 | 78.862 | 224 | 1000 | bsd-3-clause | [timm](https://huggingface.co/timm/wide_resnet101_2.tv_in1k) |

### facebookresearch/semi-supervised-ImageNet1K-models

Origin:
[github.com/facebookresearch/semi-supervised-ImageNet1K-models](https://github.com/facebookresearch/semi-supervised-ImageNet1K-models)

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `resnet18.fb_ssl_yfcc100m_ft_in1k` | 224 | 72.636 | 224 | 1000 | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/resnet18.fb_ssl_yfcc100m_ft_in1k) |
| `resnet18.fb_swsl_ig1b_ft_in1k` | 224 | 73.286 | 224 | 1000 | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/resnet18.fb_swsl_ig1b_ft_in1k) |
| `resnet50.fb_ssl_yfcc100m_ft_in1k` | 224 | 79.252 | 224 | 1000 | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/resnet50.fb_ssl_yfcc100m_ft_in1k) |
| `resnet50.fb_swsl_ig1b_ft_in1k` | 224 | 81.146 | 224 | 1000 | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/resnet50.fb_swsl_ig1b_ft_in1k) |
| `resnext50_32x4d.fb_ssl_yfcc100m_ft_in1k` | 224 | 80.316 | 224 | 1000 | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/resnext50_32x4d.fb_ssl_yfcc100m_ft_in1k) |
| `resnext50_32x4d.fb_swsl_ig1b_ft_in1k` | 224 | 82.162 | 224 | 1000 | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/resnext50_32x4d.fb_swsl_ig1b_ft_in1k) |
| `resnext101_32x4d.fb_ssl_yfcc100m_ft_in1k` | 224 | 80.936 | 224 | 1000 | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/resnext101_32x4d.fb_ssl_yfcc100m_ft_in1k) |
| `resnext101_32x4d.fb_swsl_ig1b_ft_in1k` | 224 | 83.268 | 224 | 1000 | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/resnext101_32x4d.fb_swsl_ig1b_ft_in1k) |
| `resnext101_32x8d.fb_ssl_yfcc100m_ft_in1k` | 224 | 81.620 | 224 | 1000 | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/resnext101_32x8d.fb_ssl_yfcc100m_ft_in1k) |
| `resnext101_32x8d.fb_swsl_ig1b_ft_in1k` | 224 | 84.276 | 224 | 1000 | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/resnext101_32x8d.fb_swsl_ig1b_ft_in1k) |
| `resnext101_32x16d.fb_ssl_yfcc100m_ft_in1k` | 224 | 81.856 | 224 | 1000 | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/resnext101_32x16d.fb_ssl_yfcc100m_ft_in1k) |
| `resnext101_32x16d.fb_swsl_ig1b_ft_in1k` | 224 | 83.340 | 224 | 1000 | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/resnext101_32x16d.fb_swsl_ig1b_ft_in1k) |

### `tf` tags

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `resnetrs50.tf_in1k` | 160 (test 224) | 79.934 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnetrs50.tf_in1k) |
| `resnetrs101.tf_in1k` | 192 (test 288) | 82.288 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnetrs101.tf_in1k) |
| `resnetrs152.tf_in1k` | 256 (test 320) | 83.710 | 320 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnetrs152.tf_in1k) |
| `resnetrs200.tf_in1k` | 256 (test 320) | 84.448 | 320 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnetrs200.tf_in1k) |
| `resnetrs270.tf_in1k` | 256 (test 352) | 84.438 | 352 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnetrs270.tf_in1k) |
| `resnetrs350.tf_in1k` | 288 (test 384) | 84.710 | 384 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnetrs350.tf_in1k) |
| `resnetrs420.tf_in1k` | 320 (test 416) | 85.010 | 416 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnetrs420.tf_in1k) |

### `miil` tags

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `ecaresnet50d.miil_in1k` | 224 (test 288) | 81.648 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/ecaresnet50d.miil_in1k) |
| `ecaresnet50d_pruned.miil_in1k` | 224 (test 288) | 80.808 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/ecaresnet50d_pruned.miil_in1k) |
| `ecaresnet101d.miil_in1k` | 224 (test 288) | 83.006 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/ecaresnet101d.miil_in1k) |
| `ecaresnet101d_pruned.miil_in1k` | 224 (test 288) | 82.016 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/ecaresnet101d_pruned.miil_in1k) |
| `ecaresnetlight.miil_in1k` | 224 (test 288) | 81.430 | 288 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/ecaresnetlight.miil_in1k) |

### facebookresearch/WSL-Images

Origin: [github.com/facebookresearch/WSL-Images](https://github.com/facebookresearch/WSL-Images)

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `resnext101_32x8d.fb_wsl_ig1b_ft_in1k` | 224 | 82.720 | 224 | 1000 | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/resnext101_32x8d.fb_wsl_ig1b_ft_in1k) |
| `resnext101_32x16d.fb_wsl_ig1b_ft_in1k` | 224 | 84.166 | 224 | 1000 | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/resnext101_32x16d.fb_wsl_ig1b_ft_in1k) |
| `resnext101_32x32d.fb_wsl_ig1b_ft_in1k` | 224 | 85.090 | 224 | 1000 | cc-by-nc-4.0 | [timm](https://huggingface.co/timm/resnext101_32x32d.fb_wsl_ig1b_ft_in1k) |

### `sw` tags

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `seresnextaa201d_32x8d.sw_in12k` | 320 (test 384) | - | - | 11821 | apache-2.0 | [timm](https://huggingface.co/timm/seresnextaa201d_32x8d.sw_in12k) |
| `seresnextaa201d_32x8d.sw_in12k_ft_in1k_384` | 384 | 87.304 | 384 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/seresnextaa201d_32x8d.sw_in12k_ft_in1k_384) |

### Other

| Weight | Input size | Top-1 (%) | Eval size | Classes | License | Hub |
|---|---:|---:|---:|---:|---|---|
| `ecaresnet50t.ra2_in1k` | 256 (test 320) | 82.370 | 320 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/ecaresnet50t.ra2_in1k) |
| `resnet50.am_in1k` | 224 | 79.004 | 224 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/resnet50.am_in1k) |
| `test_resnet.r160_in1k` | 160 | 41.602 | 160 | 1000 | apache-2.0 | [timm](https://huggingface.co/timm/test_resnet.r160_in1k) |