#142142nd of 168 in ML frameworks and libraries
paddleclas
Image classification and recognition toolkit on PaddlePaddle, with PP-ShiTuV2 and PULC
- Stars
- 5.9k
- License
- Apache-2.0
- Last commit
- Oct 2026
- Last release
- Nov 2024
- Language
- Python
5,769 on 21 Apr 20265,861 on 10 Nov 2026
From GitHub's daily star counts.
Checked on GitHub.
Overview
PaddleClas is a PaddlePaddle toolkit for training and deploying image classification and image retrieval models. It ships the PP-LCNet, PP-LCNetV2 and PP-HGNet backbones, the PULC lightweight classifiers (13 tasks listed, such as person, vehicle and text orientation), and PP-ShiTuV2, a detection, feature extraction and vector search pipeline. Since 2024-11 the low-code PaddleX tool wraps 98 of its models as six pipelines.
Who it is for: Engineers training or deploying image classification models on PaddlePaddle
Strengths
- Covers training, SSLD distillation, pruning and quantization in one toolkit
- Deployment paths: Python and C++ inference, Paddle Serving, Paddle Lite, Paddle2ONNX
- PULC claims 3 ms CPU inference; PP-LCNet targets Intel CPUs with MKLDNN
- PP-ShiTuV2 includes a gallery management tool and an Android demo
Weaknesses
- Requires the PaddlePaddle framework, not PyTorch; weights are .pdparams
- README and most docs are primarily in Chinese
- Last release was 2024-11-05; newer work is directed to PaddleX
- Image classification and retrieval only; no LLM or generative support
What it needs
- GPU optional
- Needs PaddlePaddle
- Models: PP-LCNet, PP-LCNetV2, PP-HGNet, PULC, PP-ShiTuV2
Quick answers
Is paddleclas open source?
Yes. Its code is on GitHub under the Apache-2.0 license.
Does paddleclas need a GPU?
No. It runs on a CPU and can use a GPU when you have one.
Also in ML frameworks and libraries
See all 168| Rank | Project | Score |
|---|---|---|
| 1 | transformersPython library defining open models for text, vision, audio and multimodal tasks | 94 out of 100 |
| 2 | pytorchPython tensor library with GPU support and tape-based autograd | 93 out of 100 |
| 3 | ultralyticsPython library and CLI for training and running YOLO vision models | 93 out of 100 |
| #4 | pytorch-image-modelsPyTorch library of image models, pretrained weights and training scripts | 93 out of 100 |
| #5 | supervisionPython toolkit for loading, annotating and counting computer vision detections | 92 out of 100 |