tf efficientnetv2 s.in21k ft in1k

Providertimm
Categoryimage-classification
Licenseapache-2.0
Downloads1.9K
Stars3

Overview

The EfficientNetV2-S (in21k-ft-in1k) is a high-performance convolutional neural network optimized for image classification. This specific variant leverages a powerful two-stage training strategy: it was pre-trained on the massive ImageNet-21k dataset and subsequently fine-tuned on ImageNet-1k. For developers, this means the model possesses superior feature extraction capabilities and faster convergence compared to models trained from scratch. It balances parameter efficiency with high accuracy, making it an ideal candidate for deployment in resource-constrained environments or as a robust backbone for downstream computer vision tasks like object detection or segmentation. Integration is straightforward via the timm library, offering a drop-in replacement for standard CNN architectures while reducing training latency and memory overhead.

Highlights

  • Pre-trained on ImageNet-21k for superior feature representation
  • Optimized balance between inference speed and top-1 accuracy
  • Seamless integration via the timm PyTorch library
  • Efficient backbone for transfer learning and downstream CV tasks
  • Apache-2.0 license ensures flexible commercial deployment

Usage

Install
# Install Hugging Face transformers
pip install transformers torch
SDK Usage
# Load model with transformers
from transformers import AutoModel, AutoTokenizer

model = AutoModel.from_pretrained("timm/tf_efficientnetv2_s.in21k_ft_in1k")
tokenizer = AutoTokenizer.from_pretrained("timm/tf_efficientnetv2_s.in21k_ft_in1k")

Hugging Face Download

We recommend downloading the model via the Hugging Face CLI or Hub SDK.

Guidance：Before downloading, install huggingface_hub with:

Guidance 
pip install -U huggingface_hub

CLI Download

Download the full repository

Download the full repository 
huggingface-cli download timm/tf_efficientnetv2_s.in21k_ft_in1k

Download a single file to a local folder (e.g. config.json into ./dir)

Download a single file to a local folder (e.g. config.json into ./dir) 
huggingface-cli download timm/tf_efficientnetv2_s.in21k_ft_in1k config.json --local-dir ./dir

See the official docs for more CLI options

SDK Download

SDK Download 
# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('timm/tf_efficientnetv2_s.in21k_ft_in1k')

Git Download

Make sure git-lfs is installed first

Git Download 
git lfs install
git clone https://huggingface.co/timm/tf_efficientnetv2_s.in21k_ft_in1k

To skip LFS large-file downloads, use:

Skip LFS 
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/timm/tf_efficientnetv2_s.in21k_ft_in1k

Model files are hosted on the Hugging Face Hub — download directly via HF CLI / SDK / Git, not through this site.

PyTorch / Transformers Usage

Install Transformers

Install Transformers 
pip install -U transformers torch

Load the model and run inference

Load the model and run inference 
from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained('timm/tf_efficientnetv2_s.in21k_ft_in1k')
tokenizer = AutoTokenizer.from_pretrained('timm/tf_efficientnetv2_s.in21k_ft_in1k')

Model Download

We recommend downloading the model via the ModelScope CLI or SDK.

Guidance：Before downloading, install ModelScope with:

Guidance 
pip install modelscope

CLI Download

Download the full repository

Download the full repository 
modelscope download --model timm/tf_efficientnetv2_s.in21k_ft_in1k

Download a single file to a local folder (e.g. README.md into ./dir)

Download a single file to a local folder (e.g. README.md into ./dir) 
modelscope download --model timm/tf_efficientnetv2_s.in21k_ft_in1k README.md --local_dir ./dir

See the docs for more CLI options

SDK Download

SDK Download 
# 模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('timm/tf_efficientnetv2_s.in21k_ft_in1k')

Git Download

Make sure git-lfs is installed first

Git Download 
git lfs install
git clone https://www.modelscope.cn/timm/tf_efficientnetv2_s.in21k_ft_in1k.git

To skip LFS large-file downloads, use:

Skip LFS 
GIT_LFS_SKIP_SMUDGE=1 git clone https://www.modelscope.cn/timm/tf_efficientnetv2_s.in21k_ft_in1k.git

ModelScope 模型页直接下载模型文件；无需将模型文件放在本站服务器。

Notebook Quickstart

Install the ModelScope library

Install the ModelScope library 
pip install "modelscope[audio,cv,nlp,multi-modal,science]" -f https://modelscope.oss-cn-beijing.aliyuncs.com/releases/repo.html

Load the model and run inference

Load the model and run inference 
from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

p = pipeline('text-generation', 'timm/tf_efficientnetv2_s.in21k_ft_in1k')

Full Documentation

来源: HuggingFace

---
tags:

  • image-classification

  • timm

  • transformers

library_name: timm
license: apache-2.0
datasets:
  • imagenet-1k

  • imagenet-21k

---

Model card for tf_efficientnetv2_s.in21k_ft_in1k

A EfficientNet-v2 image classification model. Trained on ImageNet-21k and fine-tuned on ImageNet-1k in Tensorflow by paper authors, ported to PyTorch by Ross Wightman.

Model Details

  • Model Type: Image classification / feature backbone
  • Model Stats:
- Params (M): 21.5 - GMACs: 5.4 - Activations (M): 22.7 - Image size: train = 300 x 300, test = 384 x 384
  • Papers:
- EfficientNetV2: Smaller Models and Faster Training: https://arxiv.org/abs/2104.00298
  • Dataset: ImageNet-1k
  • Pretrain Dataset: ImageNet-21k
  • Original: https://github.com/tensorflow/tpu/tree/master/models/official/efficientnet

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('tf_efficientnetv2_s.in21k_ft_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(
    'tf_efficientnetv2_s.in21k_ft_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, 24, 150, 150])
    #  torch.Size([1, 48, 75, 75])
    #  torch.Size([1, 64, 38, 38])
    #  torch.Size([1, 160, 19, 19])
    #  torch.Size([1, 256, 10, 10])


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(
    'tf_efficientnetv2_s.in21k_ft_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, 10, 10) 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
@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}
}
bibtex
@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}}
}
View official source
Join our Telegram