Name: resnet18.a3 in1k
Author: timm

Overview

The resnet18.a3_in1k is a lightweight convolutional neural network based on the ResNet-18 architecture, pre-trained on the ImageNet-1K dataset. For developers, this model serves as an efficient baseline for image classification tasks where low latency and minimal memory overhead are critical. Unlike larger ensembles, it offers a fast inference cycle and is highly compatible with standard PyTorch workflows via the timm library. It is particularly effective for transfer learning; developers can freeze the backbone and fine-tune the final fully connected layer for domain-specific datasets with relatively small sample sizes. While it lacks the top-tier accuracy of Vision Transformers or larger ResNet variants, its balance of speed and performance makes it ideal for edge deployment and rapid prototyping.

Highlights

Efficient ResNet-18 architecture for low-latency image classification
Pre-trained on ImageNet-1K for robust feature extraction
Seamless integration via the timm library for PyTorch
Ideal for transfer learning on small, custom datasets
Lightweight footprint suitable for edge device 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/resnet18.a3_in1k")
tokenizer = AutoTokenizer.from_pretrained("timm/resnet18.a3_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

huggingface-cli download timm/resnet18.a3_in1k

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

huggingface-cli download timm/resnet18.a3_in1k config.json --local-dir ./dir

See the official docs for more CLI options

SDK Download

# 模型下载
from huggingface_hub import snapshot_download
model_dir = snapshot_download('timm/resnet18.a3_in1k')

Git Download

Make sure git-lfs is installed first

Git Download

git lfs install
git clone https://huggingface.co/timm/resnet18.a3_in1k

To skip LFS large-file downloads, use:

Skip LFS

GIT_LFS_SKIP_SMUDGE=1 git clone https://huggingface.co/timm/resnet18.a3_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

pip install -U transformers torch

Load the model and run inference

from transformers import AutoModelForCausalLM, AutoTokenizer

model = AutoModelForCausalLM.from_pretrained('timm/resnet18.a3_in1k')
tokenizer = AutoTokenizer.from_pretrained('timm/resnet18.a3_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

modelscope download --model timm/resnet18.a3_in1k

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

modelscope download --model timm/resnet18.a3_in1k README.md --local_dir ./dir

See the docs for more CLI options

SDK Download

# 模型下载
from modelscope import snapshot_download
model_dir = snapshot_download('timm/resnet18.a3_in1k')

Git Download

Make sure git-lfs is installed first

Git Download

git lfs install
git clone https://www.modelscope.cn/timm/resnet18.a3_in1k.git

To skip LFS large-file downloads, use:

Skip LFS

GIT_LFS_SKIP_SMUDGE=1 git clone https://www.modelscope.cn/timm/resnet18.a3_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

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

from modelscope.pipelines import pipeline
from modelscope.utils.constant import Tasks

p = pipeline('text-generation', 'timm/resnet18.a3_in1k')

Full Documentation

来源: HuggingFace

---
license: apache-2.0
library_name: timm
tags:

image-classification

timm

transformers

---

Model card for resnet18.a3_in1k

A ResNet-B image classification model.

This model features:
* ReLU activations
* single layer 7x7 convolution with pooling
* 1x1 convolution shortcut downsample

Trained on ImageNet-1k in timm using recipe template described below.

Recipe details:
* ResNet Strikes Back A3 recipe
* LAMB optimizer with BCE loss
* Cosine LR schedule with warmup

Model Details

Model Type: Image classification / feature backbone

Model Stats:

- Params (M): 11.7 - GMACs: 0.9 - Activations (M): 1.3 - Image size: train = 160 x 160, test = 224 x 224

Papers:

- ResNet strikes back: An improved training procedure in timm: https://arxiv.org/abs/2110.00476 - Deep Residual Learning for Image Recognition: https://arxiv.org/abs/1512.03385

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('resnet18.a3_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(
    'resnet18.a3_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, 64, 80, 80])
    #  torch.Size([1, 64, 40, 40])
    #  torch.Size([1, 128, 20, 20])
    #  torch.Size([1, 256, 10, 10])
    #  torch.Size([1, 512, 5, 5])
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(
    'resnet18.a3_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, 512, 5, 5) 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.

|model |img_size|top1 |top5 |param_count|gmacs|macts|img/sec|
|------------------------------------------|--------|-----|-----|-----------|-----|-----|-------|
|seresnextaa101d_32x8d.sw_in12k_ft_in1k_288|320 |86.72|98.17|93.6 |35.2 |69.7 |451 |
|seresnextaa101d_32x8d.sw_in12k_ft_in1k_288|288 |86.51|98.08|93.6 |28.5 |56.4 |560 |
|seresnextaa101d_32x8d.sw_in12k_ft_in1k|288 |86.49|98.03|93.6 |28.5 |56.4 |557 |
|seresnextaa101d_32x8d.sw_in12k_ft_in1k|224 |85.96|97.82|93.6 |17.2 |34.2 |923 |
|resnext101_32x32d.fb_wsl_ig1b_ft_in1k|224 |85.11|97.44|468.5 |87.3 |91.1 |254 |
|resnetrs420.tf_in1k|416 |85.0 |97.12|191.9 |108.4|213.8|134 |
|ecaresnet269d.ra2_in1k|352 |84.96|97.22|102.1 |50.2 |101.2|291 |
|ecaresnet269d.ra2_in1k|320 |84.73|97.18|102.1 |41.5 |83.7 |353 |
|resnetrs350.tf_in1k|384 |84.71|96.99|164.0 |77.6 |154.7|183 |
|seresnextaa101d_32x8d.ah_in1k|288 |84.57|97.08|93.6 |28.5 |56.4 |557 |
|resnetrs200.tf_in1k|320 |84.45|97.08|93.2 |31.5 |67.8 |446 |
|resnetrs270.tf_in1k|352 |84.43|96.97|129.9 |51.1 |105.5|280 |
|seresnext101d_32x8d.ah_in1k|288 |84.36|96.92|93.6 |27.6 |53.0 |595 |
|seresnet152d.ra2_in1k|320 |84.35|97.04|66.8 |24.1 |47.7 |610 |
|resnetrs350.tf_in1k|288 |84.3 |96.94|164.0 |43.7 |87.1 |333 |
|resnext101_32x8d.fb_swsl_ig1b_ft_in1k|224 |84.28|97.17|88.8 |16.5 |31.2 |1100 |
|resnetrs420.tf_in1k|320 |84.24|96.86|191.9 |64.2 |126.6|228 |
|seresnext101_32x8d.ah_in1k|288 |84.19|96.87|93.6 |27.2 |51.6 |613 |
|resnext101_32x16d.fb_wsl_ig1b_ft_in1k|224 |84.18|97.19|194.0 |36.3 |51.2 |581 |
|resnetaa101d.sw_in12k_ft_in1k|288 |84.11|97.11|44.6 |15.1 |29.0 |1144 |
|resnet200d.ra2_in1k|320 |83.97|96.82|64.7 |31.2 |67.3 |518 |
|resnetrs200.tf_in1k|256 |83.87|96.75|93.2 |20.2 |43.4 |692 |
|seresnextaa101d_32x8d.ah_in1k|224 |83.86|96.65|93.6 |17.2 |34.2 |923 |
|resnetrs152.tf_in1k|320 |83.72|96.61|86.6 |24.3 |48.1 |617 |
|seresnet152d.ra2_in1k|256 |83.69|96.78|66.8 |15.4 |30.6 |943 |
|seresnext101d_32x8d.ah_in1k|224 |83.68|96.61|93.6 |16.7 |32.0 |986 |
|resnet152d.ra2_in1k|320 |83.67|96.74|60.2 |24.1 |47.7 |706 |
|resnetrs270.tf_in1k|256 |83.59|96.61|129.9 |27.1 |55.8 |526 |
|seresnext101_32x8d.ah_in1k|224 |83.58|96.4 |93.6 |16.5 |31.2 |1013 |
|[resnetaa101d.sw_in1