ResNet model pre-trained on ImageNet-1k at resolution 224x224. It was introduced in the paper Deep Residual Learning for Image Recognition by He et al. Disclaimer: The team releasing ResNet did not write a model card for this model so this model card has been written by the Hugging Face team. ResNet (Residual Network) is a convolutional neural network that democratized the concepts of residual learning and skip connections. This enables to train much deeper models. This is ResNet v1.5, which differs from the original model: in the bottleneck blocks which require downsampling, v1 has stride = 2 in the first 1x1 convolution, whereas v1.5 has stride = 2 in the 3x3 convolution. This difference…
Open-weight model · Image classification
resnet50.a1_in1k
by PyTorch Image Models timm/resnet50.a1_in1k
A ResNet-B image classification model. single layer 7x7 convolution with pooling 1x1 convolution shortcut downsample Trained on ImageNet-1k in timm using recipe template described below.
Parameters26M
Context—
Weights205.0 MB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads1.9M
Runs On
What it takes to serve resnet50.a1_in1k (26M parameters): the memory its weights need at each precision, and the cheapest way to rent enough data-center GPUs to hold them.
| Precision | Weights | Memory needed | Cheapest setup | Per hour | Also fits |
|---|---|---|---|---|---|
| 16-bit | 0.1 GB | 0.1 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 8-bit | 0.0 GB | 0.0 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
| 4-bit | 0.0 GB | 0.0 GB | 1x MI300X (192 GB) Vultr |
$1.85 | 1x H100 $1.99 · 1x MI325X $2.00 |
Memory is the weights at that precision plus 20% for the runtime and a short context; a long context needs more. Prices are the lowest on-demand hourly rates in the SAVRN Index, read Sep 18, 2026.
SAVRN's Notes on resnet50.a1_in1k
Classifying images is what this 26M parameter ResNet-50 from timm does, trained on ImageNet-1k with the A1 recipe from ResNet Strikes Back. Memory is not a decision here: 0.1 GB of weights, 0.1 GB to run at 16-bit, and the 8-bit and 4-bit figures round to zero. The download is 205 MB. One MI300X, the cheapest accelerator we price at $1.85 per hour, carries 192 GB and holds over a thousand copies, so the hardware question is the pipeline feeding it, not the model.
Apache 2.0 makes it easy to ship commercially: keep the notices, note significant changes, and the patent grant comes along. Check age and evidence: released 2023-04-05, last updated 2025-07-11, no reported evaluations in the record we hold, so test accuracy on your own images before production. The papers behind it, arXiv 2110.00476 for the recipe and arXiv 1512.03385 for the architecture, are the design record.
Model Card
By PyTorch Image Models, published under apache-2.0, revision 767268603ca0.
Model card for resnet50.a1_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 A1 recipe
* LAMB optimizer with BCE loss
* Cosine LR schedule with warmup
Model Details
- Model Type: Image classification / feature backbone
- Model Stats:
- Params (M): 25.6
- GMACs: 4.1
- Activations (M): 11.1
- Image size: train = 224 x 224, test = 288 x 288
- 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
Identity and Version
- Repository
- timm/resnet50.a1_in1k
- Publisher
- PyTorch Image Models
- Task
- Image classification
- Modality
- Image
- Library
- timm
- Parameters
- 26M parameters
- Languages
- Not stated by the source
- Revision
- 767268603ca0cb0bfe326fa87277f19c419566ef
- First published
- 2023-04-05
- Last updated
- 2025-07-11
Files and Weights
5 files, 205.1 MB in total. The weights are 2 files totalling 205.0 MB in bin, safetensors.
Weights2 files · 205.0 MB
Configuration1 file · 756 B
Documentation1 file · 38.4 KB
Repository1 file · 1.5 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 102.5 MB | 773525d5821d |
| pytorch_model.bin | Weights | 102.5 MB | c91efffdecf2 |
| config.json | Configuration | 756 B | — |
| README.md | Documentation | 38.4 KB | — |
| .gitattributes | Repository | 1.5 KB | — |
License and Download
- License
- apache-2.0
- Access
- Open weights, no gate
- Download size
- 205.0 MB
Download from PyTorch Image Models
Released by PyTorch Image Models through its official repository on Hugging Face. Read the license.
Built From
- Described by arXiv:1512.03385
- Described by arXiv:2110.00476
Memory Requirements
| Precision | Weights in memory |
|---|---|
| As published | 205.0 MB |
| 16-bit | 0.1 GB |
| 8-bit | 0.0 GB |
| 4-bit | 0.0 GB |
Weights only, from the published parameter count; the key-value cache and runtime add to this.
Questions About resnet50.a1_in1k
How much GPU memory does resnet50.a1_in1k need?
About 0.1 GB at 16-bit and 0 GB at 4-bit: the weights (26M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run resnet50.a1_in1k on?
At 16-bit, 1x MI300X from $1.85 an hour; at 4-bit, 1x MI300X from $1.85 an hour, at the lowest on-demand prices the SAVRN Index lists.
Can I use resnet50.a1_in1k commercially?
Yes. resnet50.a1_in1k is released under Apache License 2.0. The Apache License 2.0 is a permissive open-source license. It permits commercial use, modification and redistribution. It requires keeping the license and copyright notices and any NOTICE file, stating significant changes, and it includes an express patent grant from contributors.
Similar Models
A ResNet-B image classification model. single layer 7x7 convolution with pooling 1x1 convolution shortcut downsample Pretrained on Instagram-1B hashtags dataset using semi-weakly supervised learning and fine-tuned on ImageNet-1k by paper authors. - Billion-scale semi-supervised learning for image classification: https://arxiv.org/abs/1905.00546 - Deep Residual Learning for Image Recognition: https://arxiv.org/abs/1512.03385 Explore the dataset and runtime metrics of this model in timm model results.
A ResNet-D image classification model. 3-layer stem of 3x3 convolutions with pooling 2x2 average pool + 1x1 convolution shortcut downsample Trained on ImageNet-1k in timm using recipe template described below. RandAugment RA2 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 - Deep Residual Learning for Image Recognition: https://arxiv.org/abs/1512.03385 - Bag of Tricks for Image Classification with Convolutional Neural Networks: https://arxiv.org/abs/1812.01187 Explore the dataset and runtime metrics of…
A ResNet-B image classification model. single layer 7x7 convolution with pooling 1x1 convolution shortcut downsample Trained on ImageNet-1k in timm using recipe template described below. Based on ResNet Strikes Back A1 recipe Stronger dropout, stochastic depth, and RandAugment than paper A1 recipe - Deep Residual Learning for Image Recognition: https://arxiv.org/abs/1512.03385 Explore the dataset and runtime metrics of this model in timm model results.
This model is a fine-tuned version of microsoft/resnet-50 on the imagefolder dataset. It achieves the following results on the evaluation set: The following hyperparameters were used during training: - learningrate: 0.0001 - trainbatchsize: 8 - evalbatchsize: 16 - gradientaccumulationsteps: 2 - totaltrainbatchsize: 16 - lrschedulertype: cosine - numepochs: 20 - labelsmoothingfactor: 0.1 - Transformers 5.16.1 - Pytorch 2.11.0+cu128 - Datasets 4.8.5 - Tokenizers 0.23.1
A Swin Transformer image classification model. Pretrained on ImageNet-1k by paper authors. Explore the dataset and runtime metrics of this model in timm model results.