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. Explore the dataset and runtime metrics of this model in timm model results.
Open-weight model · Image classification
resnet34.a1_in1k
by PyTorch Image Models timm/resnet34.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.
Parameters22M
Context—
Weights174.6 MB
Licenseapache-2.0
AccessOpen weights
Monthly Downloads489.2k
Runs On
What it takes to serve resnet34.a1_in1k (22M 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 | 0.0 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 resnet34.a1_in1k
We put this one in the category of models you run on whatever is already on the rack. A 22-million-parameter ResNet-B for ImageNet-1k classification, trained in timm with the A1 recipe from ResNet Strikes Back, it rounds to 0.0 GB of weights at 16-bit and needs 0.1 GB to run. Our cheapest listing, a single MI300X with 192 GB at $1.85 per hour on-demand, is the wrong unit of measure; the real question is images per hour.
Apache 2.0 means a classifier or feature backbone built from it can go into a commercial product, provided the notices travel with it and significant changes are stated. What to check: the ImageNet-1k label set is the output, so anything outside it means fine-tuning, and the two papers listed, arXiv:1512.03385 for the architecture and arXiv:2110.00476 for the recipe, hold the specifics. There is no context length; the input is an image.
Model Card
By PyTorch Image Models, published under apache-2.0, revision 0e8757122c4c.
Model card for resnet34.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): 21.8
- GMACs: 3.7
- Activations (M): 3.7
- 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/resnet34.a1_in1k
- Publisher
- PyTorch Image Models
- Task
- Image classification
- Modality
- Image
- Library
- timm
- Parameters
- 22M parameters
- Languages
- Not stated by the source
- Revision
- 0e8757122c4c09b15fb9300c0fd09b3fe89e28bf
- First published
- 2023-04-05
- Last updated
- 2025-01-21
Files and Weights
5 files, 174.6 MB in total. The weights are 2 files totalling 174.6 MB in bin, safetensors.
Weights2 files · 174.6 MB
Configuration1 file · 755 B
Documentation1 file · 38.4 KB
Repository1 file · 1.5 KB
Every file
| File | Type | Size | SHA-256 |
|---|---|---|---|
| model.safetensors | Weights | 87.3 MB | 829a220f9529 |
| pytorch_model.bin | Weights | 87.3 MB | f6c1d7785b5d |
| config.json | Configuration | 755 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
- 174.6 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 | 174.6 MB |
| 16-bit | 0.0 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 resnet34.a1_in1k
How much GPU memory does resnet34.a1_in1k need?
About 0.1 GB at 16-bit and 0 GB at 4-bit: the weights (22M parameters) plus a working margin. A long context needs more.
What is the cheapest GPU to run resnet34.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 resnet34.a1_in1k commercially?
Yes. resnet34.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 Vision Transformer (ViT) image classification model. Trained on ImageNet-21k and fine-tuned on ImageNet-1k (with additional augmentation and regularization) in JAX by paper authors, ported to PyTorch by Ross Wightman. - How to train your ViT? Data, Augmentation, and Regularization in Vision Transformers: https://arxiv.org/abs/2106.10270 - An Image is Worth 16x16 Words: Transformers for Image Recognition at Scale: https://arxiv.org/abs/2010.11929v2 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 RegNetY-3.2GF image classification model. Trained on ImageNet-1k by Ross Wightman in timm. The timm RegNet implementation includes a number of enhancements not present in other implementations, including: stochastic depth gradient checkpointing layer-wise LR decay configurable output stride (dilation) configurable activation and norm layers option for a pre-activation bottleneck block used in RegNetV variant only known RegNetZ model definitions with pretrained weights Explore the dataset and runtime metrics of this model in timm model results. For the comparison summary below, the rain1k, ra3in1k, chin1k, sw, and lion tagged weights are trained in timm.
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.
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. ResNet Strikes Back 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.