Model card for convnextv2_large.fcmae

A ConvNeXt-V2 self-supervised feature representation model. Pretrained with a fully convolutional masked autoencoder framework (FCMAE). This model has no pretrained head and is only useful for fine-tune or feature extraction.

Model Details

• Model Type: Image classification / feature backbone
• Model Stats:
• Params (M): 196.4
• GMACs: 34.4
• Activations (M): 43.1
• Image size: 224 x 224
• Papers:
• ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders: https://arxiv.org/abs/2301.00808
• Original: https://github.com/facebookresearch/ConvNeXt-V2
• Pretrain Dataset: ImageNet-1k

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('convnextv2_large.fcmae', 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(
    'convnextv2_large.fcmae',
    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, 192, 56, 56])
    #  torch.Size([1, 384, 28, 28])
    #  torch.Size([1, 768, 14, 14])
    #  torch.Size([1, 1536, 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(
    'convnextv2_large.fcmae',
    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, 1536, 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.

All timing numbers from eager model PyTorch 1.13 on RTX 3090 w/ AMP.

Citation

@article{Woo2023ConvNeXtV2,
  title={ConvNeXt V2: Co-designing and Scaling ConvNets with Masked Autoencoders},
  author={Sanghyun Woo, Shoubhik Debnath, Ronghang Hu, Xinlei Chen, Zhuang Liu, In So Kweon and Saining Xie},
  year={2023},
  journal={arXiv preprint arXiv:2301.00808},
}

@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}}
}