pytorch-image-models/docs/models/selecsls.md

# Summary

**SelecSLS** uses novel selective long and short range skip connections to improve the information flow allowing for a drastically faster network without compromising accuracy.

## How do I use this model on an image?
To load a pretrained model:

```python
import timm
model = timm.create_model('selecsls42b', pretrained=True)
model.eval()
```

To load and preprocess the image:
```python 
import urllib
from PIL import Image
from timm.data import resolve_data_config
from timm.data.transforms_factory import create_transform

config = resolve_data_config({}, model=model)
transform = create_transform(**config)

url, filename = ("https://github.com/pytorch/hub/raw/master/images/dog.jpg", "dog.jpg")
urllib.request.urlretrieve(url, filename)
img = Image.open(filename).convert('RGB')
tensor = transform(img).unsqueeze(0) # transform and add batch dimension
```

To get the model predictions:
```python
import torch
with torch.no_grad():
    out = model(tensor)
probabilities = torch.nn.functional.softmax(out[0], dim=0)
print(probabilities.shape)
# prints: torch.Size([1000])
```

To get the top-5 predictions class names:
```python
# Get imagenet class mappings
url, filename = ("https://raw.githubusercontent.com/pytorch/hub/master/imagenet_classes.txt", "imagenet_classes.txt")
urllib.request.urlretrieve(url, filename) 
with open("imagenet_classes.txt", "r") as f:
    categories = [s.strip() for s in f.readlines()]

# Print top categories per image
top5_prob, top5_catid = torch.topk(probabilities, 5)
for i in range(top5_prob.size(0)):
    print(categories[top5_catid[i]], top5_prob[i].item())
# prints class names and probabilities like:
# [('Samoyed', 0.6425196528434753), ('Pomeranian', 0.04062102362513542), ('keeshond', 0.03186424449086189), ('white wolf', 0.01739676296710968), ('Eskimo dog', 0.011717947199940681)]
```

Replace the model name with the variant you want to use, e.g. `selecsls42b`. You can find the IDs in the model summaries at the top of this page.

To extract image features with this model, follow the [timm feature extraction examples](https://rwightman.github.io/pytorch-image-models/feature_extraction/), just change the name of the model you want to use.

## How do I finetune this model?
You can finetune any of the pre-trained models just by changing the classifier (the last layer).
```python
model = timm.create_model('selecsls42b', pretrained=True).reset_classifier(NUM_FINETUNE_CLASSES)
```
To finetune on your own dataset, you have to write a training loop or adapt [timm's training
script](https://github.com/rwightman/pytorch-image-models/blob/master/train.py) to use your dataset.

## How do I train this model?

You can follow the [timm recipe scripts](https://rwightman.github.io/pytorch-image-models/scripts/) for training a new model afresh.

## Citation

```BibTeX
@article{Mehta_2020,
   title={XNect},
   volume={39},
   ISSN={1557-7368},
   url={http://dx.doi.org/10.1145/3386569.3392410},
   DOI={10.1145/3386569.3392410},
   number={4},
   journal={ACM Transactions on Graphics},
   publisher={Association for Computing Machinery (ACM)},
   author={Mehta, Dushyant and Sotnychenko, Oleksandr and Mueller, Franziska and Xu, Weipeng and Elgharib, Mohamed and Fua, Pascal and Seidel, Hans-Peter and Rhodin, Helge and Pons-Moll, Gerard and Theobalt, Christian},
   year={2020},
   month={Jul}
}
```

<!--
Models:
- Name: selecsls42b
  Metadata:
    FLOPs: 3824022528
    Training Data:
    - ImageNet
    Training Techniques:
    - Cosine Annealing
    - Random Erasing
    Architecture:
    - Batch Normalization
    - Convolution
    - Dense Connections
    - Dropout
    - Global Average Pooling
    - ReLU
    - SelecSLS Block
    File Size: 129948954
    Tasks:
    - Image Classification
    ID: selecsls42b
    Crop Pct: '0.875'
    Image Size: '224'
    Interpolation: bicubic
  Code: https://github.com/rwightman/pytorch-image-models/blob/b9843f954b0457af2db4f9dea41a8538f51f5d78/timm/models/selecsls.py#L335
  In Collection: SelecSLS
- Name: selecsls60
  Metadata:
    FLOPs: 4610472600
    Training Data:
    - ImageNet
    Training Techniques:
    - Cosine Annealing
    - Random Erasing
    Architecture:
    - Batch Normalization
    - Convolution
    - Dense Connections
    - Dropout
    - Global Average Pooling
    - ReLU
    - SelecSLS Block
    File Size: 122839714
    Tasks:
    - Image Classification
    ID: selecsls60
    Crop Pct: '0.875'
    Image Size: '224'
    Interpolation: bicubic
  Code: https://github.com/rwightman/pytorch-image-models/blob/b9843f954b0457af2db4f9dea41a8538f51f5d78/timm/models/selecsls.py#L342
  In Collection: SelecSLS
- Name: selecsls60b
  Metadata:
    FLOPs: 4657653144
    Training Data:
    - ImageNet
    Training Techniques:
    - Cosine Annealing
    - Random Erasing
    Architecture:
    - Batch Normalization
    - Convolution
    - Dense Connections
    - Dropout
    - Global Average Pooling
    - ReLU
    - SelecSLS Block
    File Size: 131252898
    Tasks:
    - Image Classification
    ID: selecsls60b
    Crop Pct: '0.875'
    Image Size: '224'
    Interpolation: bicubic
  Code: https://github.com/rwightman/pytorch-image-models/blob/b9843f954b0457af2db4f9dea41a8538f51f5d78/timm/models/selecsls.py#L349
  In Collection: SelecSLS
Collections:
- Name: SelecSLS
  Paper:
    title: 'XNect: Real-time Multi-Person 3D Motion Capture with a Single RGB Camera'
    url: https://paperswithcode.com//paper/xnect-real-time-multi-person-3d-human-pose
  type: model-index
Type: model-index
-->