lee-dro/PatchCore
基于 PatchCore 的工业异常检测项目，研究 layer2/layer3 分数融合、敏感性引导收缩与风险受控门控，并提供 Streamlit 工程化 Demo。
- Stars
- 186
- Forks
- 29
- Open issues
- 0
- Last push
- 9d ago
PatchCore star history
+65 this week
Get PatchCore running
Setup: Hard · build from source, typically 1–3 hours
Full install steps in the README →Can I sell what I build with it?
Yes
A guide, not legal advice.
About PatchCore
PatchCore is a free, open-source computer vision tool by lee-dro, written mainly in Python. 基于 PatchCore 的工业异常检测项目，研究 layer2/layer3 分数融合、敏感性引导收缩与风险受控门控，并提供 Streamlit 工程化 Demo。. It has 186 GitHub stars and 29 forks, and was last updated 9d ago. It's released under the Apache-2.0 license, a standard open-source license.
- License
- Apache-2.0
- Commercial use
- Commercial OK
- Language
- Python
- Stars
- 186
- Last update
- 9d ago
- Runs on Mac
- Not stated
- GPU
- Not stated
- Paid API key
- Not stated
- Self-hostable
- Yes
Similar free tools
ultralytics63k stars · Perform object detection, instance segmentation, and image classification using YOLO models.
supervision51k stars · Build computer vision tools with reusable components and models.
segmentation_models.pytorch12k stars · Provides PyTorch models for image semantic segmentation.
pytorch-grad-cam13k stars · Provides advanced methods for explaining AI model predictions in computer vision.
vit-pytorch26k stars · PyTorch implementation of Vision Transformer for image classification.
PatchCore FAQ
Can I use PatchCore commercially?
Yes. Apache-2.0 is a permissive license: commercial use is allowed as long as you keep the license notice. This is a plain-English summary, not legal advice.
Is PatchCore free?
Yes. PatchCore is open source and free to use. It's released under the Apache-2.0 license, a standard open-source license.
Does PatchCore run on a Mac?
The project doesn't say. Check its installation guide before you start.
Does PatchCore need a GPU?
The project doesn't state hardware needs. AI models generally run much faster with a GPU.
Is PatchCore still maintained?
Yes. It was last updated 9d ago and has 0 open issues on GitHub.
How hard is PatchCore to set up?
Hard: typically 1–3 hours, using build from source.
What are alternatives to PatchCore?
Similar free, open-source tools include ultralytics, yolov5, supervision, segmentation_models.pytorch.
Maintain PatchCore?
Add this badge to your README to show it's featured on FreeAIRepo.
[](https://www.freeairepo.com/repo/lee-dro/PatchCore)