A proper train/val/test experiment with 10 real Tiny ImageNet classes. Train and validation use 2,000 images each; test uses 1,000 images.
Edit .env file and add your Claude API key: . ├── ai/ # AI modules (supplier inference, impact calc, etc.) ├── api/ # Data APIs (simulated vendor data) ├── data/ # Company data (BeverageCo, PharmaCorp ...
Some results have been hidden because they may be inaccessible to you
Show inaccessible results