OpenVLA provides an open-source vision-language-action model for robotic manipulation tasks.
Open source
24 alternativesTResNet: High Performance GPU-Dedicated Architecture
This repository provides the PyTorch implementation of the TResNet computer vision architecture.
About TResNet: High Performance GPU-Dedicated Architecture
This GitHub repository contains the official PyTorch implementation of TResNet, a computer vision architecture for image classification. The authors are researchers at DAMO Academy, Alibaba Group, and the work was published at WACV 2021. The architecture is designed to improve accuracy while keeping GPU training and inference speed close to ResNet50, which the authors describe as a more efficient alternative to models that are optimized mainly for FLOPs.
The repository includes the model code, an inference script, a model zoo document, and links to pretrained models. Reported results include 80.7% top-1 accuracy on ImageNet at GPU throughput similar to ResNet50, along with results on Stanford Cars, CIFAR-10, CIFAR-100, and Oxford-Flowers. The authors also report multi-label classification and object detection results. Speed figures were measured on an Nvidia V100 GPU with mixed precision, so they apply most directly to that setup.
Key features
- Official PyTorch implementation of the TResNet image classification architecture
- Pretrained TResNet model weights linked from the repository
- Pretrained weights from ImageNet-21K training for TResNet models
- Inference script (infer.py) for running trained models
- Benchmark tables comparing GPU speed and ImageNet accuracy with ResNet50
- Automatically generated test suite, noted in a 2023 repository update
Best for: Machine learning researchers and engineers who want to use or compare the TResNet image classification architecture in PyTorch on GPU hardware.
Good for
- Reports 80.7% top-1 ImageNet accuracy at GPU throughput similar to ResNet50.
- Provides pretrained weights, including weights from ImageNet-21K pretraining.
- Open source, with a license file included in the repository.
Watch out for
- Speed measurements are reported only for an Nvidia V100 GPU with mixed precision.
TResNet: High Performance GPU-Dedicated Architecture at a glance
- Category
- AI & Machine Learning › Models & ML Research
- Type
- Open-source project
- Pricing
- Not confirmed. Check the site
- Open source
- Yes · Source code
- Language
- English
- Last checked
- Oct 6, 2026 · Online when checked
- Listed
- Oct 5, 2026
TResNet: High Performance GPU-Dedicated Architecture alternatives
Tools and sites you could use instead, ranked by how closely they match.
DeepSeek-VL2 supports multimodal understanding through a mixture-of-experts vision-language model.
Open source
24 alternatives
timm provides PyTorch image encoders and backbones along with training, evaluation, inference, and export scripts.
Open source
24 alternatives
The learn2learn library supports meta learning experiments and research with PyTorch.
Open source
24 alternatives
MobiLlama is a small language model designed for edge devices, according to its repository description.
Open source
24 alternatives
This repository contains the DeepSeek-V3 language model project and related source files.
Open source
24 alternativesPopular in Models & ML Research
Well-known listings from the same topic.
Falcon LLMfalconllm.tii.aeERNIEernie.baidu.comTokenVersetoken-verse.github.iowTAObittensor.comAlpacacrfm.stanford.edu/2023/03/13/alpaca.htmlSmolVLAhuggingface.co/blog/smolvla
TResNet: High Performance GPU-Dedicated Architecture FAQ
Which tasks are covered by the reported results?
The results cover ImageNet classification, Stanford Cars, CIFAR-10, CIFAR-100, and Oxford-Flowers. The authors also report multi-label classification and object detection results, including on MS-COCO.
Where can I find the pretrained models?
The repository links to pretrained models and a model zoo document. Pretrained weights from ImageNet-21K training are also described in the repository's updates.
Is something wrong or out of date?
Tell us and an editor will check it.
Own this website?
Claim this listing
Claim the listing and suggest updates yourself. An editor checks every claim first.