README.md

metadata

license: apache-2.0
library_name: timm
tags:
  - image-classification
  - timm
datasets:
  - imagenet-1k

Model card for gernet_m.idstcv_in1k

A GENet (GPU-Efficient-Networks) image classification model. Trained on ImageNet-1k by paper authors.

This model architecture is implemented using timm's flexible BYOBNet (Bring-Your-Own-Blocks Network).

BYOBNet allows configuration of:

• block / stage layout
• stem layout
• output stride (dilation)
• activation and norm layers
• channel and spatial / self-attention layers

...and also includes timm features common to many other architectures, including:

• stochastic depth
• gradient checkpointing
• layer-wise LR decay
• per-stage feature extraction

Model Details

• Model Type: Image classification / feature backbone
• Model Stats:
  • Params (M): 21.1
  • GMACs: 3.0
  • Activations (M): 5.2
  • Image size: 224 x 224
• Papers:
  • Neural Architecture Design for GPU-Efficient Networks: https://arxiv.org/abs/2006.14090
• Dataset: ImageNet-1k
• Original: https://github.com/idstcv/GPU-Efficient-Networks

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('gernet_m.idstcv_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(
    'gernet_m.idstcv_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, 32, 112, 112])
    #  torch.Size([1, 128, 56, 56])
    #  torch.Size([1, 192, 28, 28])
    #  torch.Size([1, 640, 14, 14])
    #  torch.Size([1, 2560, 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(
    'gernet_m.idstcv_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, 2560, 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}}
}

@misc{lin2020neural,
  title={Neural Architecture Design for GPU-Efficient Networks},
  author={Ming Lin and Hesen Chen and Xiuyu Sun and Qi Qian and Hao Li and Rong Jin},
  year={2020},
  eprint={2006.14090},
  archivePrefix={arXiv},
  primaryClass={cs.CV}
}