Closed i3oi3o closed 5 years ago
Yeah, you are right. Could you please fix this and submit PR?
Sure, I will try PR next weekend. By the way, My PC's GPU is very old, You will need to manual test it. Don't want to use my workplace PC.
The letterbox function is fine, but the detections are drawn out of place, where should i change back the position @i3oi3o
The pull request #49 have already been accepted. So, I will close this issue. It can be improve further by moving the letter box logic to Tensorflow side, GPU is very good with this kind of thing. But let create another issue for that.
If I'm wrong, please correct me. This line don't care about aspect ratio. https://github.com/mystic123/tensorflow-yolo-v3/blob/fb9f5439d90ecff255b008e9c9d9e3b8ac4813da/demo.py#L49
This is a letter box function. If run "./darknet detect" seem to call to detector.c's test_detector() function which also use letter box function. The padding use 128 (uint) or 0.5 (float) value.
This is resize function which use bi-linear interpolation. This is used in detector.c's validate_detector_recall() function.
Now the question, Should the resized image keeping aspect ratio? This should improve its accuracy, shouldn't it?