ResNeSt

A ResNeSt is a variant on a ResNet, which instead stacks Split-Attention blocks. The cardinal group representations are then concatenated along the channel dimension: $V = \text{Concat}$ {$ V^{1},V^{2},\cdots{V}^{K} $}. As in standard residual blocks, the final output $Y$ of otheur Split-Attention block is produced using a shortcut connection: $Y=V+X$ , if the input and output feature-map share the same shape. For blocks with a stride, an appropriate transformation $\mathcal{T}$ is applied to the shortcut connection to align the output shapes: $Y=V+\mathcal{T}(X)$ . For example, $\mathcal{T}$ can be strided convolution or combined convolution-with-pooling.

How do I use this model on an image?

To load a pretrained model:

>>> import timm
>>> model = timm.create_model('resnest101e', pretrained=True)
>>> model.eval()

To load and preprocess the image:

>>> 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:

>>> 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:

>>> # 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. resnest101e. 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, 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).

>>> model = timm.create_model('resnest101e', pretrained=True, num_classes=NUM_FINETUNE_CLASSES)

To finetune on your own dataset, you have to write a training loop or adapt timm’s training script to use your dataset.

How do I train this model?

You can follow the timm recipe scripts for training a new model afresh.

Citation

@misc{zhang2020resnest,
      title={ResNeSt: Split-Attention Networks},
      author={Hang Zhang and Chongruo Wu and Zhongyue Zhang and Yi Zhu and Haibin Lin and Zhi Zhang and Yue Sun and Tong He and Jonas Mueller and R. Manmatha and Mu Li and Alexander Smola},
      year={2020},
      eprint={2004.08955},
      archivePrefix={arXiv},
      primaryClass={cs.CV}
}

< > Update on GitHub