Eliminate image squeezing by forcing square cropping in both preprocessing and browser bypass paths

Fix model loading by downloading snapshot and renaming .pth weight file

Shift classification model to ResNet-50 ConvNet architecture with Softmax activation and French-to-English translation

Restore confidence threshold check to 75% per user request

Use sigmoid activation on SigLIP2 logits to match sigmoid loss training

Add /api/debug_crop endpoint to verify AI input frames

Fix missing glass category mapping and lower confidence threshold to 40% for SigLIP2 accuracy

Completely clean up and remove all legacy models and YOLO references, leaving SigLIP2 as the sole classifier

Bypass server-side cropping for browser-uploaded frames to prevent double cropping

Optimize classification latency and fix canvas coordinate cropping scaling bug

Integrate YOLOv8 for deep-learning-based object detection and crop

Restore original dark blue/violet theme and re-integrate features

Deploy waste classifier to Hugging Face Spaces (clean binaries)