Model card for vit_relpos_base_patch32_plus_rpn_256.sw_in1k
A Vision Transformer (ViT) image classification model. This is a timm specific variation of the ViT architecture with relative position embeddings and residual post normalization blocks, no class token, and final representation via global average pool of tokens. Trained on ImageNet-1k in timm using recipe template described below.
Recipe details:
- Based on Swin Transformer train / pretrain recipe with modifications (related to both DeiT and ConvNeXt recipes)
- AdamW optimizer, gradient clipping, EMA weight averaging
- Cosine LR schedule with warmup
Model Details
- Model Type: Image classification / feature backbone
- Model Stats:
- Params (M): 119.4
- GMACs: 7.6
- Activations (M): 6.6
- Image size: 256 x 256
- Papers:
- Swin Transformer V2: Scaling Up Capacity and Resolution: https://arxiv.org/abs/2111.09883
- An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale: https://arxiv.org/abs/2010.11929v2
- Dataset: ImageNet-1k
- Original: https://github.com/huggingface/pytorch-image-models
Model Usage
Image Classification
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('vit_relpos_base_patch32_plus_rpn_256.sw_in1k', 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)
Image Embeddings
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(
'vit_relpos_base_patch32_plus_rpn_256.sw_in1k',
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, 64, 896) 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.
Citation
@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}}
}
@inproceedings{liu2021swinv2,
title={Swin Transformer V2: Scaling Up Capacity and Resolution},
author={Ze Liu and Han Hu and Yutong Lin and Zhuliang Yao and Zhenda Xie and Yixuan Wei and Jia Ning and Yue Cao and Zheng Zhang and Li Dong and Furu Wei and Baining Guo},
booktitle={International Conference on Computer Vision and Pattern Recognition (CVPR)},
year={2022}
}
@article{dosovitskiy2020vit,
title={An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale},
author={Dosovitskiy, Alexey and Beyer, Lucas and Kolesnikov, Alexander and Weissenborn, Dirk and Zhai, Xiaohua and Unterthiner, Thomas and Dehghani, Mostafa and Minderer, Matthias and Heigold, Georg and Gelly, Sylvain and Uszkoreit, Jakob and Houlsby, Neil},
journal={ICLR},
year={2021}
}