timm documentation

Res2NeXt

Hugging Face's logo
Join the Hugging Face community

and get access to the augmented documentation experience

to get started

Res2NeXt

Res2NeXt is an image model that employs a variation on ResNeXt bottleneck residual blocks. The motivation is to be able to represent features at multiple scales. This is achieved through a novel building block for CNNs that constructs hierarchical residual-like connections within one single residual block. This represents multi-scale features at a granular level and increases the range of receptive fields for each network layer.

How do I use this model on an image?

To load a pretrained model:

>>> import timm
>>> model = timm.create_model('res2next50', 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. res2next50. 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('res2next50', 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

@article{Gao_2021,
   title={Res2Net: A New Multi-Scale Backbone Architecture},
   volume={43},
   ISSN={1939-3539},
   url={http://dx.doi.org/10.1109/TPAMI.2019.2938758},
   DOI={10.1109/tpami.2019.2938758},
   number={2},
   journal={IEEE Transactions on Pattern Analysis and Machine Intelligence},
   publisher={Institute of Electrical and Electronics Engineers (IEEE)},
   author={Gao, Shang-Hua and Cheng, Ming-Ming and Zhao, Kai and Zhang, Xin-Yu and Yang, Ming-Hsuan and Torr, Philip},
   year={2021},
   month={Feb},
   pages={652–662}
}
< > Update on GitHub