Charles Qi
Charles Qi
Issue converting the pytorch model to onnx with the attached script  [pt_to_onnx.py.gz](https://github.com/isl-org/MiDaS/files/12707028/pt_to_onnx.py.gz)
out of shear luck, the python inference code I wrote gave me significantly better detection results. So I did a big more debugging on the C++ netforward code under examples/yolo_9000_test....
The get_region_box function in yolo_v2_loss_layer.cpp doesn't appear to be using sigmoid to compute box.x and box.y. I wonder why? The logistic_activate() function is defined by never called. //why aren't we...