| frameworks | license | tags | tasks | ||
|---|---|---|---|---|---|
|
Apache License 2.0 |
|
You are viewing the default Readme template, the detailed model-card was provided by the model’s contributors. You can access the model files in the "Files and versions" tab.
Download with ModelScope’s Python SDK
#Install ModelScope
pip install modelscope#Download with ModelScope’s Python SDK
from modelscope import snapshot_download
model_dir = snapshot_download('bniladridas/patch')Download with Git clone
git clone https://www.modelscope.cn/bniladridas/patch.git
If you are a contributor to this model, we invite you to promptly update the model card content according to the model contribution documentation.
I am addressing inference output:
Model loaded successfully!
Anomaly score for datasets/test/good/000.png: 13.8731
The model loads and runs inference. The score of ~13.87 for a normal image is expected (normal images have lower scores, anomalies have higher scores).
inference.py now:
- Reads model_params if available in checkpoint
- Falls back to defaults if not
The script now handles both old checkpoints (with hardcoded defaults) and new checkpoints (with saved params).