efficientnet b0.ra in1k

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

Overview

EfficientNet-B0 (ra in1k) is a lightweight convolutional neural network optimized for image classification tasks where computational efficiency is critical. Built on the principle of compound scaling, it balances network depth, width, and resolution to achieve high accuracy with significantly fewer parameters than traditional ResNet architectures. For developers, this model is ideal for edge deployment, mobile applications, or as a fast baseline for transfer learning on custom datasets. Integrated via the timm library, it offers a streamlined pipeline for feature extraction and classification, providing a competitive trade-off between inference latency and Top-1 accuracy on ImageNet-1k benchmarks.

Highlights

  • Optimized compound scaling for high efficiency
  • Low memory footprint ideal for edge deployment
  • Easy integration via the timm library
  • Strong baseline for transfer learning tasks
  • Apache-2.0 license for flexible commercial use

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/efficientnet_b0.ra_in1k")
tokenizer = AutoTokenizer.from_pretrained("timm/efficientnet_b0.ra_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/efficientnet_b0.ra_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/efficientnet_b0.ra_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/efficientnet_b0.ra_in1k')

Git Download

Make sure git-lfs is installed first

Git Download 
git lfs install
git clone https://huggingface.co/timm/efficientnet_b0.ra_in1k

To skip LFS large-file downloads, use:

Skip LFS 
GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/timm/efficientnet_b0.ra_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/efficientnet_b0.ra_in1k')
tokenizer = AutoTokenizer.from_pretrained('timm/efficientnet_b0.ra_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/efficientnet_b0.ra_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/efficientnet_b0.ra_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/efficientnet_b0.ra_in1k')

Git Download

Make sure git-lfs is installed first

Git Download 
git lfs install
git clone https://www.modelscope.cn/timm/efficientnet_b0.ra_in1k.git

To skip LFS large-file downloads, use:

Skip LFS 
GIT_LFS_SKIP_SMUDGE=1 git clone https://www.modelscope.cn/timm/efficientnet_b0.ra_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/efficientnet_b0.ra_in1k')

Full Documentation

来源: HuggingFace

---
tags:

  • image-classification

  • timm

  • transformers

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

---

Model card for efficientnet_b0.ra_in1k

A EfficientNet image classification model. Trained on ImageNet-1k in timm using recipe template described below.

Recipe details:
* RandAugment RA recipe. Inspired by and evolved from EfficientNet RandAugment recipes. Published as B recipe in ResNet Strikes Back.
* RMSProp (TF 1.0 behaviour) optimizer, EMA weight averaging
* Step (exponential decay w/ staircase) LR schedule with warmup

Model Details

  • Model Type: Image classification / feature backbone
  • Model Stats:
- Params (M): 5.3 - GMACs: 0.4 - Activations (M): 6.7 - Image size: 224 x 224
  • Papers:
- EfficientNet: Rethinking Model Scaling for Convolutional Neural Networks: https://arxiv.org/abs/1905.11946 - ResNet strikes back: An improved training procedure in timm: https://arxiv.org/abs/2110.00476
  • Dataset: ImageNet-1k
  • Original: https://github.com/huggingface/pytorch-image-models

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('efficientnet_b0.ra_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(
    'efficientnet_b0.ra_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, 16, 112, 112])
    #  torch.Size([1, 24, 56, 56])
    #  torch.Size([1, 40, 28, 28])
    #  torch.Size([1, 112, 14, 14])
    #  torch.Size([1, 320, 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(
    'efficientnet_b0.ra_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, 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
@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}
}
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}}
}
bibtex
@inproceedings{wightman2021resnet,
  title={ResNet strikes back: An improved training procedure in timm},
  author={Wightman, Ross and Touvron, Hugo and Jegou, Herve},
  booktitle={NeurIPS 2021 Workshop on ImageNet: Past, Present, and Future}
}
View official source
Join our Telegram