resnetrs420.tf_in1k

Model card for resnetrs420.tf_in1k

A ResNetRS-B image classification model.

This model features:

• ReLU activations
• single layer 7x7 convolution with pooling
• 1x1 convolution shortcut downsample

Trained on ImageNet-1k by paper authors in Tensorflow.

Model Details

• Model Type: Image classification / feature backbone
• Model Stats:
  • Params (M): 191.9
  • GMACs: 64.2
  • Activations (M): 126.6
  • Image size: train = 320 x 320, test = 416 x 416
• Papers:
  • Revisiting ResNets: Improved Training and Scaling Strategies: https://arxiv.org/abs/2103.07579
  • Deep Residual Learning for Image Recognition: https://arxiv.org/abs/1512.03385
• Original: https://github.com/tensorflow/tpu/tree/master/models/official/resnet

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('resnetrs420.tf_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)

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(
    'resnetrs420.tf_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.:
    #  torch.Size([1, 64, 160, 160])
    #  torch.Size([1, 256, 80, 80])
    #  torch.Size([1, 512, 40, 40])
    #  torch.Size([1, 1024, 20, 20])
    #  torch.Size([1, 2048, 10, 10])

    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(
    'resnetrs420.tf_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, 2048, 10, 10) 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

@article{bello2021revisiting,
  title={Revisiting ResNets: Improved Training and Scaling Strategies},
  author={Irwan Bello and William Fedus and Xianzhi Du and Ekin D. Cubuk and Aravind Srinivas and Tsung-Yi Lin and Jonathon Shlens and Barret Zoph},
  journal={arXiv preprint arXiv:2103.07579},
  year={2021}
}

@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}
}

@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}}
}