timm / tf_efficientnetv2_m.in21k

huggingface.co
Total runs: 78.2K
24-hour runs: 0
7-day runs: 14.6K
30-day runs: 74.4K
Model's Last Updated: 2025年1月21日
image-classification

Introduction of tf_efficientnetv2_m.in21k

Model Details of tf_efficientnetv2_m.in21k

Model card for tf_efficientnetv2_m.in21k

A EfficientNet-v2 image classification model. Trained on ImageNet-21k in Tensorflow by paper authors, ported to PyTorch by Ross Wightman.

Model Details
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_efficientnetv2_m.in21k', 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_efficientnetv2_m.in21k',
    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, 24, 192, 192])
    #  torch.Size([1, 48, 96, 96])
    #  torch.Size([1, 80, 48, 48])
    #  torch.Size([1, 176, 24, 24])
    #  torch.Size([1, 512, 12, 12])

    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_efficientnetv2_m.in21k',
    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, 12, 12) 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{tan2021efficientnetv2,
  title={Efficientnetv2: Smaller models and faster training},
  author={Tan, Mingxing and Le, Quoc},
  booktitle={International conference on machine learning},
  pages={10096--10106},
  year={2021},
  organization={PMLR}
}
@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_efficientnetv2_m.in21k on huggingface.co

78.2K
Total runs
0
24-hour runs
4.7K
3-day runs
14.6K
7-day runs
74.4K
30-day runs

More Information About tf_efficientnetv2_m.in21k huggingface.co Model

More tf_efficientnetv2_m.in21k license Visit here:

https://choosealicense.com/licenses/apache-2.0

tf_efficientnetv2_m.in21k huggingface.co

tf_efficientnetv2_m.in21k huggingface.co is an AI model on huggingface.co that provides tf_efficientnetv2_m.in21k's model effect (), which can be used instantly with this timm tf_efficientnetv2_m.in21k model. huggingface.co supports a free trial of the tf_efficientnetv2_m.in21k model, and also provides paid use of the tf_efficientnetv2_m.in21k. Support call tf_efficientnetv2_m.in21k model through api, including Node.js, Python, http.

tf_efficientnetv2_m.in21k huggingface.co Url

https://huggingface.co/timm/tf_efficientnetv2_m.in21k

timm tf_efficientnetv2_m.in21k online free

tf_efficientnetv2_m.in21k huggingface.co is an online trial and call api platform, which integrates tf_efficientnetv2_m.in21k's modeling effects, including api services, and provides a free online trial of tf_efficientnetv2_m.in21k, you can try tf_efficientnetv2_m.in21k online for free by clicking the link below.

timm tf_efficientnetv2_m.in21k online free url in huggingface.co:

https://huggingface.co/timm/tf_efficientnetv2_m.in21k

tf_efficientnetv2_m.in21k install

tf_efficientnetv2_m.in21k is an open source model from GitHub that offers a free installation service, and any user can find tf_efficientnetv2_m.in21k on GitHub to install. At the same time, huggingface.co provides the effect of tf_efficientnetv2_m.in21k install, users can directly use tf_efficientnetv2_m.in21k installed effect in huggingface.co for debugging and trial. It also supports api for free installation.

tf_efficientnetv2_m.in21k install url in huggingface.co:

https://huggingface.co/timm/tf_efficientnetv2_m.in21k

Url of tf_efficientnetv2_m.in21k

tf_efficientnetv2_m.in21k huggingface.co Url

Provider of tf_efficientnetv2_m.in21k huggingface.co

timm
ORGANIZATIONS

Other API from timm

huggingface.co

Total runs: 19.0M
Run Growth: -1.8M
Growth Rate: -9.67%
Updated: 2025年1月21日
huggingface.co

Total runs: 4.9M
Run Growth: 3.3M
Growth Rate: 68.60%
Updated: 2025年1月21日
huggingface.co

Total runs: 125.5K
Run Growth: 103.6K
Growth Rate: 82.60%
Updated: 2023年10月25日
huggingface.co

Total runs: 121.9K
Run Growth: -120.0K
Growth Rate: -98.99%
Updated: 2025年1月21日
huggingface.co

Total runs: 113.9K
Run Growth: -112.3K
Growth Rate: -100.13%
Updated: 2025年1月21日
huggingface.co

Total runs: 112.5K
Run Growth: 101.7K
Growth Rate: 89.79%
Updated: 2025年1月21日
huggingface.co

Total runs: 90.3K
Run Growth: 64.4K
Growth Rate: 80.38%
Updated: 2025年1月21日
huggingface.co

Total runs: 31.4K
Run Growth: 8.7K
Growth Rate: 27.99%
Updated: 2025年1月21日
huggingface.co

Total runs: 24.0K
Run Growth: 7.5K
Growth Rate: 31.41%
Updated: 2025年1月21日
huggingface.co

Total runs: 22.4K
Run Growth: 15.1K
Growth Rate: 70.96%
Updated: 2025年1月21日
huggingface.co

Total runs: 20.8K
Run Growth: 7.7K
Growth Rate: 37.02%
Updated: 2025年1月21日
huggingface.co

Total runs: 20.8K
Run Growth: 6.5K
Growth Rate: 32.11%
Updated: 2025年1月21日
huggingface.co

Total runs: 20.5K
Run Growth: 6.0K
Growth Rate: 30.02%
Updated: 2025年1月21日
huggingface.co

Total runs: 20.5K
Run Growth: 5.8K
Growth Rate: 28.79%
Updated: 2025年1月21日
huggingface.co

Total runs: 20.2K
Run Growth: 15.2K
Growth Rate: 76.29%
Updated: 2025年1月21日