Model card for tf_efficientnet_l2.ns_jft_in1k

A EfficientNet image classification model. Trained on ImageNet-1k and unlabeled JFT-300m using Noisy Student semi-supervised learning in Tensorflow by paper authors, ported to PyTorch by Ross Wightman.

Model Details

• Model Type: Image classification / feature backbone
• Model Stats:
  • Params (M): 480.3
  • GMACs: 479.1
  • Activations (M): 1707.4
  • Image size: 800 x 800
• Papers:
  • EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks: https://arxiv.org/abs/1905.11946
  • Self-training with Noisy Student improves ImageNet classification: https://arxiv.org/abs/1911.04252
• Dataset: ImageNet-1k
• Original: https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet

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('tf_efficientnet_l2.ns_jft_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(
    'tf_efficientnet_l2.ns_jft_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, 72, 400, 400])
    #  torch.Size([1, 104, 200, 200])
    #  torch.Size([1, 176, 100, 100])
    #  torch.Size([1, 480, 50, 50])
    #  torch.Size([1, 1376, 25, 25])

    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(
    'tf_efficientnet_l2.ns_jft_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, 5504, 25, 25) 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

@inproceedings{tan2019efficientnet,
  title={Efficientnet: Rethinking model scaling for convolutional neural networks},
  author={Tan, Mingxing and Le, Quoc},
  booktitle={International conference on machine learning},
  pages={6105--6114},
  year={2019},
  organization={PMLR}
}

@article{Xie2019SelfTrainingWN,
  title={Self-Training With Noisy Student Improves ImageNet Classification},
  author={Qizhe Xie and Eduard H. Hovy and Minh-Thang Luong and Quoc V. Le},
  journal={2020 IEEE/CVF Conference on Computer Vision and Pattern Recognition (CVPR)},
  year={2019},
  pages={10684-10695}
}

@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}}
}