---
license: other
library_name: timm
tags:
- image-feature-extraction
- timm
---
# Model card for regnety_320.seer

A RegNetY-32GF feature / backbone model. Pretrained according to SEER: self-supervised learning with SwAV on "2B random internet images".

SEER is licensed under SEER license, Copyright (c) Meta Platforms, Inc. All Rights Reserved. The [license](https://github.com/facebookresearch/vissl/blob/04788de934b39278326331f7a4396e03e85f6e55/projects/SEER/MODEL_LICENSE.md) is a non-commercial license with useage and distribution restrictions.

The `timm` RegNet implementation includes a number of enhancements not present in other implementations, including:
 * stochastic depth
 * gradient checkpointing
 * layer-wise LR decay
 * configurable output stride (dilation)
 * configurable activation and norm layers
 * option for a pre-activation bottleneck block used in RegNetV variant
 * only known RegNetZ model definitions with pretrained weights


## Model Details
- **Model Type:** Image classification / feature backbone
- **Model Stats:**
  - Params (M): 141.3
  - GMACs: 32.3
  - Activations (M): 30.3
  - Image size: 224 x 224
- **Papers:**
  - Self-supervised Pretraining of Visual Features in the Wild: https://arxiv.org/abs/2103.01988v2
  - Designing Network Design Spaces: https://arxiv.org/abs/2003.13678
- **Original:** https://github.com/facebookresearch/vissl
- **Pretrain Dataset:** RandomInternetImages-2B

## Model Usage
### Image Classification
```python
from urllib.request import urlopen
from PIL import Image
import timm

img = Image.open(urlopen(
    'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))

model = timm.create_model('regnety_320.seer', pretrained=True)
model = model.eval()

# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)

output = model(transforms(img).unsqueeze(0))  # unsqueeze single image into batch of 1

top5_probabilities, top5_class_indices = torch.topk(output.softmax(dim=1) * 100, k=5)
```

### Feature Map Extraction
```python
from urllib.request import urlopen
from PIL import Image
import timm

img = Image.open(urlopen(
    'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))

model = timm.create_model(
    'regnety_320.seer',
    pretrained=True,
    features_only=True,
)
model = model.eval()

# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)

output = model(transforms(img).unsqueeze(0))  # unsqueeze single image into batch of 1

for o in output:
    # print shape of each feature map in output
    # e.g.:
    #  torch.Size([1, 32, 112, 112])
    #  torch.Size([1, 232, 56, 56])
    #  torch.Size([1, 696, 28, 28])
    #  torch.Size([1, 1392, 14, 14])
    #  torch.Size([1, 3712, 7, 7])

    print(o.shape)
```

### Image Embeddings
```python
from urllib.request import urlopen
from PIL import Image
import timm

img = Image.open(urlopen(
    'https://huggingface.co/datasets/huggingface/documentation-images/resolve/main/beignets-task-guide.png'
))

model = timm.create_model(
    'regnety_320.seer',
    pretrained=True,
    num_classes=0,  # remove classifier nn.Linear
)
model = model.eval()

# get model specific transforms (normalization, resize)
data_config = timm.data.resolve_model_data_config(model)
transforms = timm.data.create_transform(**data_config, is_training=False)

output = model(transforms(img).unsqueeze(0))  # output is (batch_size, num_features) shaped tensor

# or equivalently (without needing to set num_classes=0)

output = model.forward_features(transforms(img).unsqueeze(0))
# output is unpooled, a (1, 3712, 7, 7) shaped tensor

output = model.forward_head(output, pre_logits=True)
# output is a (1, num_features) shaped tensor
```

## Model Comparison
Explore the dataset and runtime metrics of this model in timm [model results](https://github.com/huggingface/pytorch-image-models/tree/main/results).

For the comparison summary below, the ra_in1k, ra3_in1k, ch_in1k, sw_*, and lion_* tagged weights are trained in `timm`.
        
|model                    |img_size|top1  |top5  |param_count|gmacs|macts |
|-------------------------|--------|------|------|-----------|-----|------|
|[regnety_1280.swag_ft_in1k](https://huggingface.co/timm/regnety_1280.swag_ft_in1k)|384     |88.228|98.684|644.81     |374.99|210.2 |
|[regnety_320.swag_ft_in1k](https://huggingface.co/timm/regnety_320.swag_ft_in1k)|384     |86.84 |98.364|145.05     |95.0 |88.87 |
|[regnety_160.swag_ft_in1k](https://huggingface.co/timm/regnety_160.swag_ft_in1k)|384     |86.024|98.05 |83.59      |46.87|67.67 |
|[regnety_160.sw_in12k_ft_in1k](https://huggingface.co/timm/regnety_160.sw_in12k_ft_in1k)|288     |86.004|97.83 |83.59      |26.37|38.07 |
|[regnety_1280.swag_lc_in1k](https://huggingface.co/timm/regnety_1280.swag_lc_in1k)|224     |85.996|97.848|644.81     |127.66|71.58 |
|[regnety_160.lion_in12k_ft_in1k](https://huggingface.co/timm/regnety_160.lion_in12k_ft_in1k)|288     |85.982|97.844|83.59      |26.37|38.07 |
|[regnety_160.sw_in12k_ft_in1k](https://huggingface.co/timm/regnety_160.sw_in12k_ft_in1k)|224     |85.574|97.666|83.59      |15.96|23.04 |
|[regnety_160.lion_in12k_ft_in1k](https://huggingface.co/timm/regnety_160.lion_in12k_ft_in1k)|224     |85.564|97.674|83.59      |15.96|23.04 |
|[regnety_120.sw_in12k_ft_in1k](https://huggingface.co/timm/regnety_120.sw_in12k_ft_in1k)|288     |85.398|97.584|51.82      |20.06|35.34 |
|[regnety_2560.seer_ft_in1k](https://huggingface.co/timm/regnety_2560.seer_ft_in1k)|384     |85.15 |97.436|1282.6     |747.83|296.49|
|[regnetz_e8.ra3_in1k](https://huggingface.co/timm/regnetz_e8.ra3_in1k)|320     |85.036|97.268|57.7       |15.46|63.94 |
|[regnety_120.sw_in12k_ft_in1k](https://huggingface.co/timm/regnety_120.sw_in12k_ft_in1k)|224     |84.976|97.416|51.82      |12.14|21.38 |
|[regnety_320.swag_lc_in1k](https://huggingface.co/timm/regnety_320.swag_lc_in1k)|224     |84.56 |97.446|145.05     |32.34|30.26 |
|[regnetz_040_h.ra3_in1k](https://huggingface.co/timm/regnetz_040_h.ra3_in1k)|320     |84.496|97.004|28.94      |6.43 |37.94 |
|[regnetz_e8.ra3_in1k](https://huggingface.co/timm/regnetz_e8.ra3_in1k)|256     |84.436|97.02 |57.7       |9.91 |40.94 |
|[regnety_1280.seer_ft_in1k](https://huggingface.co/timm/regnety_1280.seer_ft_in1k)|384     |84.432|97.092|644.81     |374.99|210.2 |
|[regnetz_040.ra3_in1k](https://huggingface.co/timm/regnetz_040.ra3_in1k)|320     |84.246|96.93 |27.12      |6.35 |37.78 |
|[regnetz_d8.ra3_in1k](https://huggingface.co/timm/regnetz_d8.ra3_in1k)|320     |84.054|96.992|23.37      |6.19 |37.08 |
|[regnetz_d8_evos.ch_in1k](https://huggingface.co/timm/regnetz_d8_evos.ch_in1k)|320     |84.038|96.992|23.46      |7.03 |38.92 |
|[regnetz_d32.ra3_in1k](https://huggingface.co/timm/regnetz_d32.ra3_in1k)|320     |84.022|96.866|27.58      |9.33 |37.08 |
|[regnety_080.ra3_in1k](https://huggingface.co/timm/regnety_080.ra3_in1k)|288     |83.932|96.888|39.18      |13.22|29.69 |
|[regnety_640.seer_ft_in1k](https://huggingface.co/timm/regnety_640.seer_ft_in1k)|384     |83.912|96.924|281.38     |188.47|124.83|
|[regnety_160.swag_lc_in1k](https://huggingface.co/timm/regnety_160.swag_lc_in1k)|224     |83.778|97.286|83.59      |15.96|23.04 |
|[regnetz_040_h.ra3_in1k](https://huggingface.co/timm/regnetz_040_h.ra3_in1k)|256     |83.776|96.704|28.94      |4.12 |24.29 |
|[regnetv_064.ra3_in1k](https://huggingface.co/timm/regnetv_064.ra3_in1k)|288     |83.72 |96.75 |30.58      |10.55|27.11 |
|[regnety_064.ra3_in1k](https://huggingface.co/timm/regnety_064.ra3_in1k)|288     |83.718|96.724|30.58      |10.56|27.11 |
|[regnety_160.deit_in1k](https://huggingface.co/timm/regnety_160.deit_in1k)|288     |83.69 |96.778|83.59      |26.37|38.07 |
|[regnetz_040.ra3_in1k](https://huggingface.co/timm/regnetz_040.ra3_in1k)|256     |83.62 |96.704|27.12      |4.06 |24.19 |
|[regnetz_d8.ra3_in1k](https://huggingface.co/timm/regnetz_d8.ra3_in1k)|256     |83.438|96.776|23.37      |3.97 |23.74 |
|[regnetz_d32.ra3_in1k](https://huggingface.co/timm/regnetz_d32.ra3_in1k)|256     |83.424|96.632|27.58      |5.98 |23.74 |
|[regnetz_d8_evos.ch_in1k](https://huggingface.co/timm/regnetz_d8_evos.ch_in1k)|256     |83.36 |96.636|23.46      |4.5  |24.92 |
|[regnety_320.seer_ft_in1k](https://huggingface.co/timm/regnety_320.seer_ft_in1k)|384     |83.35 |96.71 |145.05     |95.0 |88.87 |
|[regnetv_040.ra3_in1k](https://huggingface.co/timm/regnetv_040.ra3_in1k)|288     |83.204|96.66 |20.64      |6.6  |20.3  |
|[regnety_320.tv2_in1k](https://huggingface.co/timm/regnety_320.tv2_in1k)|224     |83.162|96.42 |145.05     |32.34|30.26 |
|[regnety_080.ra3_in1k](https://huggingface.co/timm/regnety_080.ra3_in1k)|224     |83.16 |96.486|39.18      |8.0  |17.97 |
|[regnetv_064.ra3_in1k](https://huggingface.co/timm/regnetv_064.ra3_in1k)|224     |83.108|96.458|30.58      |6.39 |16.41 |
|[regnety_040.ra3_in1k](https://huggingface.co/timm/regnety_040.ra3_in1k)|288     |83.044|96.5  |20.65      |6.61 |20.3  |
|[regnety_064.ra3_in1k](https://huggingface.co/timm/regnety_064.ra3_in1k)|224     |83.02 |96.292|30.58      |6.39 |16.41 |
|[regnety_160.deit_in1k](https://huggingface.co/timm/regnety_160.deit_in1k)|224     |82.974|96.502|83.59      |15.96|23.04 |
|[regnetx_320.tv2_in1k](https://huggingface.co/timm/regnetx_320.tv2_in1k)|224     |82.816|96.208|107.81     |31.81|36.3  |
|[regnety_032.ra_in1k](https://huggingface.co/timm/regnety_032.ra_in1k)|288     |82.742|96.418|19.44      |5.29 |18.61 |
|[regnety_160.tv2_in1k](https://huggingface.co/timm/regnety_160.tv2_in1k)|224     |82.634|96.22 |83.59      |15.96|23.04 |
|[regnetz_c16_evos.ch_in1k](https://huggingface.co/timm/regnetz_c16_evos.ch_in1k)|320     |82.634|96.472|13.49      |3.86 |25.88 |
|[regnety_080_tv.tv2_in1k](https://huggingface.co/timm/regnety_080_tv.tv2_in1k)|224     |82.592|96.246|39.38      |8.51 |19.73 |
|[regnetx_160.tv2_in1k](https://huggingface.co/timm/regnetx_160.tv2_in1k)|224     |82.564|96.052|54.28      |15.99|25.52 |
|[regnetz_c16.ra3_in1k](https://huggingface.co/timm/regnetz_c16.ra3_in1k)|320     |82.51 |96.358|13.46      |3.92 |25.88 |
|[regnetv_040.ra3_in1k](https://huggingface.co/timm/regnetv_040.ra3_in1k)|224     |82.44 |96.198|20.64      |4.0  |12.29 |
|[regnety_040.ra3_in1k](https://huggingface.co/timm/regnety_040.ra3_in1k)|224     |82.304|96.078|20.65      |4.0  |12.29 |
|[regnetz_c16.ra3_in1k](https://huggingface.co/timm/regnetz_c16.ra3_in1k)|256     |82.16 |96.048|13.46      |2.51 |16.57 |
|[regnetz_c16_evos.ch_in1k](https://huggingface.co/timm/regnetz_c16_evos.ch_in1k)|256     |81.936|96.15 |13.49      |2.48 |16.57 |
|[regnety_032.ra_in1k](https://huggingface.co/timm/regnety_032.ra_in1k)|224     |81.924|95.988|19.44      |3.2  |11.26 |
|[regnety_032.tv2_in1k](https://huggingface.co/timm/regnety_032.tv2_in1k)|224     |81.77 |95.842|19.44      |3.2  |11.26 |
|[regnetx_080.tv2_in1k](https://huggingface.co/timm/regnetx_080.tv2_in1k)|224     |81.552|95.544|39.57      |8.02 |14.06 |
|[regnetx_032.tv2_in1k](https://huggingface.co/timm/regnetx_032.tv2_in1k)|224     |80.924|95.27 |15.3       |3.2  |11.37 |
|[regnety_320.pycls_in1k](https://huggingface.co/timm/regnety_320.pycls_in1k)|224     |80.804|95.246|145.05     |32.34|30.26 |
|[regnetz_b16.ra3_in1k](https://huggingface.co/timm/regnetz_b16.ra3_in1k)|288     |80.712|95.47 |9.72       |2.39 |16.43 |
|[regnety_016.tv2_in1k](https://huggingface.co/timm/regnety_016.tv2_in1k)|224     |80.66 |95.334|11.2       |1.63 |8.04  |
|[regnety_120.pycls_in1k](https://huggingface.co/timm/regnety_120.pycls_in1k)|224     |80.37 |95.12 |51.82      |12.14|21.38 |
|[regnety_160.pycls_in1k](https://huggingface.co/timm/regnety_160.pycls_in1k)|224     |80.288|94.964|83.59      |15.96|23.04 |
|[regnetx_320.pycls_in1k](https://huggingface.co/timm/regnetx_320.pycls_in1k)|224     |80.246|95.01 |107.81     |31.81|36.3  |
|[regnety_080.pycls_in1k](https://huggingface.co/timm/regnety_080.pycls_in1k)|224     |79.882|94.834|39.18      |8.0  |17.97 |
|[regnetz_b16.ra3_in1k](https://huggingface.co/timm/regnetz_b16.ra3_in1k)|224     |79.872|94.974|9.72       |1.45 |9.95  |
|[regnetx_160.pycls_in1k](https://huggingface.co/timm/regnetx_160.pycls_in1k)|224     |79.862|94.828|54.28      |15.99|25.52 |
|[regnety_064.pycls_in1k](https://huggingface.co/timm/regnety_064.pycls_in1k)|224     |79.716|94.772|30.58      |6.39 |16.41 |
|[regnetx_120.pycls_in1k](https://huggingface.co/timm/regnetx_120.pycls_in1k)|224     |79.592|94.738|46.11      |12.13|21.37 |
|[regnetx_016.tv2_in1k](https://huggingface.co/timm/regnetx_016.tv2_in1k)|224     |79.44 |94.772|9.19       |1.62 |7.93  |
|[regnety_040.pycls_in1k](https://huggingface.co/timm/regnety_040.pycls_in1k)|224     |79.23 |94.654|20.65      |4.0  |12.29 |
|[regnetx_080.pycls_in1k](https://huggingface.co/timm/regnetx_080.pycls_in1k)|224     |79.198|94.55 |39.57      |8.02 |14.06 |
|[regnetx_064.pycls_in1k](https://huggingface.co/timm/regnetx_064.pycls_in1k)|224     |79.064|94.454|26.21      |6.49 |16.37 |
|[regnety_032.pycls_in1k](https://huggingface.co/timm/regnety_032.pycls_in1k)|224     |78.884|94.412|19.44      |3.2  |11.26 |
|[regnety_008_tv.tv2_in1k](https://huggingface.co/timm/regnety_008_tv.tv2_in1k)|224     |78.654|94.388|6.43       |0.84 |5.42  |
|[regnetx_040.pycls_in1k](https://huggingface.co/timm/regnetx_040.pycls_in1k)|224     |78.482|94.24 |22.12      |3.99 |12.2  |
|[regnetx_032.pycls_in1k](https://huggingface.co/timm/regnetx_032.pycls_in1k)|224     |78.178|94.08 |15.3       |3.2  |11.37 |
|[regnety_016.pycls_in1k](https://huggingface.co/timm/regnety_016.pycls_in1k)|224     |77.862|93.73 |11.2       |1.63 |8.04  |
|[regnetx_008.tv2_in1k](https://huggingface.co/timm/regnetx_008.tv2_in1k)|224     |77.302|93.672|7.26       |0.81 |5.15  |
|[regnetx_016.pycls_in1k](https://huggingface.co/timm/regnetx_016.pycls_in1k)|224     |76.908|93.418|9.19       |1.62 |7.93  |
|[regnety_008.pycls_in1k](https://huggingface.co/timm/regnety_008.pycls_in1k)|224     |76.296|93.05 |6.26       |0.81 |5.25  |
|[regnety_004.tv2_in1k](https://huggingface.co/timm/regnety_004.tv2_in1k)|224     |75.592|92.712|4.34       |0.41 |3.89  |
|[regnety_006.pycls_in1k](https://huggingface.co/timm/regnety_006.pycls_in1k)|224     |75.244|92.518|6.06       |0.61 |4.33  |
|[regnetx_008.pycls_in1k](https://huggingface.co/timm/regnetx_008.pycls_in1k)|224     |75.042|92.342|7.26       |0.81 |5.15  |
|[regnetx_004_tv.tv2_in1k](https://huggingface.co/timm/regnetx_004_tv.tv2_in1k)|224     |74.57 |92.184|5.5        |0.42 |3.17  |
|[regnety_004.pycls_in1k](https://huggingface.co/timm/regnety_004.pycls_in1k)|224     |74.018|91.764|4.34       |0.41 |3.89  |
|[regnetx_006.pycls_in1k](https://huggingface.co/timm/regnetx_006.pycls_in1k)|224     |73.862|91.67 |6.2        |0.61 |3.98  |
|[regnetx_004.pycls_in1k](https://huggingface.co/timm/regnetx_004.pycls_in1k)|224     |72.38 |90.832|5.16       |0.4  |3.14  |
|[regnety_002.pycls_in1k](https://huggingface.co/timm/regnety_002.pycls_in1k)|224     |70.282|89.534|3.16       |0.2  |2.17  |
|[regnetx_002.pycls_in1k](https://huggingface.co/timm/regnetx_002.pycls_in1k)|224     |68.752|88.556|2.68       |0.2  |2.16  |

## Citation
```bibtex
@article{goyal2022vision,
  title={Vision Models Are More Robust And Fair When Pretrained On Uncurated Images Without Supervision}, 
  author={Priya Goyal and Quentin Duval and Isaac Seessel and Mathilde Caron and Ishan Misra and Levent Sagun and Armand Joulin and Piotr Bojanowski},
  year={2022},
  eprint={2202.08360},
  archivePrefix={arXiv},
  primaryClass={cs.CV}
}
```
```bibtex
@InProceedings{Radosavovic2020,
  title = {Designing Network Design Spaces},
  author = {Ilija Radosavovic and Raj Prateek Kosaraju and Ross Girshick and Kaiming He and Piotr Doll{'a}r},
  booktitle = {CVPR},
  year = {2020}
}
```
```bibtex
@misc{rw2019timm,
  author = {Ross Wightman},
  title = {PyTorch Image Models},
  year = {2019},
  publisher = {GitHub},
  journal = {GitHub repository},
  doi = {10.5281/zenodo.4414861},
  howpublished = {\url{https://github.com/huggingface/pytorch-image-models}}
}
```