Kim Young

I have the same question. One of my model detect less object in test set than another, but after intersect.py, its mAP is even higher.

 Just change the order of sys.path, make sure python2 is in the last position. This solution solved my problem.

> Thank you! I find my mistakes, 在2020-02-25 18:21:04，[email protected]写道： @cauivy Is the error message is thrown out when you run the script? After checking my PyTorch, my Pytorch version is...

把append缩进 ` # Load labels label_path = self.label_files[index] if os.path.isfile(label_path): x = self.labels[index] if x is None: # labels not preloaded with open(label_path, 'r') as f: x = np.array([x.split() for...

似乎在AIDetection_pytorch.py里面，没有对pred为None的情况处理

`pip install opencv-python-headless` It works for me in a conda env