ByteTrack_yolov5

ByteTrack_yolov5 copied to clipboard

When I set the weight to xx. engine, the terminal displays " AssertionError: (torch.Size([1,3,608,1088]), (1,3,640,640))". how to deal with it? thx

harryc7

The position of the drawn tracking frame has drifted

10

 please help me，thanks

zxq309


youzixpz

why can't use non_max_suppression replace of postprocess ?

5

outputs = self.model(img, False, False) # if self.decoder is not None: # outputs = self.decoder(outputs, dtype=outputs.type()) print('before nms:', outputs.size()) outputs = postprocess(outputs, self.num_classes, self.confthre, self.nmsthre) # outputs = non_max_suppression(outputs, 0.1,...

Pcyslist

Hello, were you able to run train.py and track.py using yolov5?

parthmalpathak

zhangda1018

tsize can't input high resolution

12

 I use yolov5 training input image size is (1600，1600), when inferencing, I want to set tsize to (1600，1600), but there is an error, what happened? tsize = （640,640）is running...

zxq309