seresnextaa101d_32x8d.sw_in12k

Model card for seresnextaa101d_32x8d.sw_in12k

A SE-ResNeXt-D (Rectangle-2 Anti-Aliasing) image classification model with Squeeze-and-Excitation channel attention.

This model features:

• ReLU activations
• 3-layer stem of 3x3 convolutions with pooling
• 2x2 average pool + 1x1 convolution shortcut downsample
• grouped 3x3 bottleneck convolutions
• Squeeze-and-Excitation channel attention

Trained on ImageNet-12k by Ross Wightman 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): 115.8
  • GMACs: 17.3
  • Activations (M): 34.2
  • Image size: train = 224 x 224, test = 288 x 288
• Papers:
  • Aggregated Residual Transformations for Deep Neural Networks: https://arxiv.org/abs/1611.05431
  • Making Convolutional Networks Shift-Invariant Again: https://arxiv.org/abs/1904.11486
  • Deep Residual Learning for Image Recognition: https://arxiv.org/abs/1512.03385
  • Squeeze-and-Excitation Networks: https://arxiv.org/abs/1709.01507
  • Bag of Tricks for Image Classification with Convolutional Neural Networks: https://arxiv.org/abs/1812.01187
• 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('seresnextaa101d_32x8d.sw_in12k', 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)

Feature Map Extraction

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(
    'seresnextaa101d_32x8d.sw_in12k',
    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.:
    #  torch.Size([1, 64, 112, 112])
    #  torch.Size([1, 256, 56, 56])
    #  torch.Size([1, 512, 28, 28])
    #  torch.Size([1, 1024, 14, 14])
    #  torch.Size([1, 2048, 7, 7])

    print(o.shape)

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(
    'seresnextaa101d_32x8d.sw_in12k',
    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, 2048, 7, 7) 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}}
}

@article{Xie2016,
  title={Aggregated Residual Transformations for Deep Neural Networks},
  author={Saining Xie and Ross Girshick and Piotr Dollár and Zhuowen Tu and Kaiming He},
  journal={arXiv preprint arXiv:1611.05431},
  year={2016}
}

@inproceedings{zhang2019shiftinvar,
  title={Making Convolutional Networks Shift-Invariant Again},
  author={Zhang, Richard},
  booktitle={ICML},
  year={2019}
}

@article{He2015,
  author = {Kaiming He and Xiangyu Zhang and Shaoqing Ren and Jian Sun},
  title = {Deep Residual Learning for Image Recognition},
  journal = {arXiv preprint arXiv:1512.03385},
  year = {2015}
}

@inproceedings{hu2018senet,
  title={Squeeze-and-Excitation Networks},
  author={Jie Hu and Li Shen and Gang Sun},
  journal={IEEE Conference on Computer Vision and Pattern Recognition},
  year={2018}
}

@article{He2018BagOT,
  title={Bag of Tricks for Image Classification with Convolutional Neural Networks},
  author={Tong He and Zhi Zhang and Hang Zhang and Zhongyue Zhang and Junyuan Xie and Mu Li},
  journal={2019 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2018},
  pages={558-567}
}