lxztju/pytorch_classification
A complete PyTorch image classification toolkit supporting CNN architectures (ResNet, DenseNet, EfficientNet, Swin Transformer), knowledge distillation, model ensemble, and deployment via Flask API or C++ libtorch.
Not currently ranked — collecting fresh signals.
star history
The repository provides end-to-end image classification capabilities using PyTorch and torchvision models. It includes training with warmup cosine learning rate scheduling, label smoothing, and multi-model ensemble prediction. The project supports CNN feature extraction followed by classification using SVM, Random Forest, MLP, or KNN classifiers. For deployment, it offers Flask + Redis cloud API, C++ libtorch inference, and TensorRT C++ inference options.
Frequently asked
- What is lxztju/pytorch_classification?
- A complete PyTorch image classification toolkit supporting CNN architectures (ResNet, DenseNet, EfficientNet, Swin Transformer), knowledge distillation, model ensemble, and deployment via Flask API or C++ libtorch.
- Is pytorch_classification open source?
- Yes — lxztju/pytorch_classification is open source, released under the MIT license.
- What language is pytorch_classification written in?
- lxztju/pytorch_classification is primarily written in Jupyter Notebook.
- How popular is pytorch_classification?
- lxztju/pytorch_classification has 1.5k stars on GitHub.
- Where can I find pytorch_classification?
- lxztju/pytorch_classification is on GitHub at https://github.com/lxztju/pytorch_classification.