swin_s3_small_224.ms_in1k

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('swin_s3_small_224.ms_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)

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(
    'swin_s3_small_224.ms_in1k',
    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. for swin_base_patch4_window7_224 (NHWC output)
    #  torch.Size([1, 56, 56, 128])
    #  torch.Size([1, 28, 28, 256])
    #  torch.Size([1, 14, 14, 512])
    #  torch.Size([1, 7, 7, 1024])
    # e.g. for swinv2_cr_small_ns_224 (NCHW output)
    #  torch.Size([1, 96, 56, 56]) 
    #  torch.Size([1, 192, 28, 28])
    #  torch.Size([1, 384, 14, 14])
    #  torch.Size([1, 768, 7, 7])
    print(o.shape)

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(
    'swin_s3_small_224.ms_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 (ie.e a (batch_size, H, W,  num_features) tensor for swin / swinv2
# or (batch_size, num_features, H, W) for swinv2_cr

output = model.forward_head(output, pre_logits=True)
# output is (batch_size, num_features) tensor

@article{S3,
  title={Searching the Search Space of Vision Transformer},
  author={Minghao, Chen and Kan, Wu and Bolin, Ni and Houwen, Peng and Bei, Liu and Jianlong, Fu and Hongyang, Chao and Haibin, Ling},
  booktitle={Conference and Workshop on Neural Information Processing Systems (NeurIPS)},
  year={2021}
}    

@inproceedings{liu2021Swin,
  title={Swin Transformer: Hierarchical Vision Transformer using Shifted Windows},
  author={Liu, Ze and Lin, Yutong and Cao, Yue and Hu, Han and Wei, Yixuan and Zhang, Zheng and Lin, Stephen and Guo, Baining},
  booktitle={Proceedings of the IEEE/CVF International Conference on Computer Vision (ICCV)},
  year={2021}
}

@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}}
}