CoolFace
Modelpublic

timm/vgg16_bn.tv_in1k

sourceHugging Facebsd-3-clauseupdated 2y agoView on Hugging Face
1likes5.6kdownloads
Model Card

Model card for vgg16bn.tvin1k

A VGG image classification model. Trained on ImageNet-1k, original torchvision weights.

Model Details

  • —Model Type: Image classification / feature backbone
  • —Model Stats:
  • —Params (M): 138.4
  • —GMACs: 15.5
  • —Activations (M): 13.6
  • —Image size: 224 x 224
  • —Papers:
  • —Very Deep Convolutional Networks for Large-Scale Image Recognition: https://arxiv.org/abs/1409.1556
  • —Dataset: ImageNet-1k
  • —Original: https://github.com/pytorch/vision

Model Usage

Image Classification

python
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('vgg16_bn.tv_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

python
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(
    'vgg16_bn.tv_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, 224, 224])
    #  torch.Size([1, 128, 112, 112])
    #  torch.Size([1, 256, 56, 56])
    #  torch.Size([1, 512, 28, 28])
    #  torch.Size([1, 512, 14, 14])
    #  torch.Size([1, 512, 7, 7])

    print(o.shape)

Image Embeddings

python
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(
    'vgg16_bn.tv_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, 512, 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

bibtex
@article{Simonyan2014VeryDC,
  title={Very Deep Convolutional Networks for Large-Scale Image Recognition},
  author={Karen Simonyan and Andrew Zisserman},
  journal={CoRR},
  year={2014},
  volume={abs/1409.1556}
}