Mercury-ML

Yolov7 export to CoreML crashing

4

Yolov7 trained with 1280 x 1280 images (pertained weights / model used: yolov7-d6) Trained with 5 custom labels. Inference runs fine, I added --img-size 1280 to the detect command: !python...

export to Onnx is missing inputs, can't run inference

6

This issue is blocking me from running inference on my trained model. When running inference from an ONNX exported file (I exported to ONNX by adding --export_onnx flag to testing)...

Hi - thank you for putting this on Git! I noticed when running your project from Xcode the first image I choose is parsed, but when I select another image...