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
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_b1.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_b1.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 1for o in output:
# print shape of each feature map in output# e.g.:# torch.Size([1, 16, 120, 120])# torch.Size([1, 24, 60, 60])# torch.Size([1, 40, 30, 30])# torch.Size([1, 112, 15, 15])# torch.Size([1, 320, 8, 8])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_b1.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, 1280, 8, 8) 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}}
}
Runs of timm tf_efficientnet_b1.ns_jft_in1k on huggingface.co
69.9K
Total runs
0
24-hour runs
9.7K
3-day runs
46.9K
7-day runs
57.0K
30-day runs
More Information About tf_efficientnet_b1.ns_jft_in1k huggingface.co Model
More tf_efficientnet_b1.ns_jft_in1k license Visit here:
tf_efficientnet_b1.ns_jft_in1k huggingface.co is an AI model on huggingface.co that provides tf_efficientnet_b1.ns_jft_in1k's model effect (), which can be used instantly with this timm tf_efficientnet_b1.ns_jft_in1k model. huggingface.co supports a free trial of the tf_efficientnet_b1.ns_jft_in1k model, and also provides paid use of the tf_efficientnet_b1.ns_jft_in1k. Support call tf_efficientnet_b1.ns_jft_in1k model through api, including Node.js, Python, http.
tf_efficientnet_b1.ns_jft_in1k huggingface.co is an online trial and call api platform, which integrates tf_efficientnet_b1.ns_jft_in1k's modeling effects, including api services, and provides a free online trial of tf_efficientnet_b1.ns_jft_in1k, you can try tf_efficientnet_b1.ns_jft_in1k online for free by clicking the link below.
timm tf_efficientnet_b1.ns_jft_in1k online free url in huggingface.co:
tf_efficientnet_b1.ns_jft_in1k is an open source model from GitHub that offers a free installation service, and any user can find tf_efficientnet_b1.ns_jft_in1k on GitHub to install. At the same time, huggingface.co provides the effect of tf_efficientnet_b1.ns_jft_in1k install, users can directly use tf_efficientnet_b1.ns_jft_in1k installed effect in huggingface.co for debugging and trial. It also supports api for free installation.
tf_efficientnet_b1.ns_jft_in1k install url in huggingface.co: