search

leeyeehoo / CSRNet-pytorch

CSRNet: Dilated Convolutional Neural Networks for Understanding the Highly Congested Scenes
642 stars 259 forks source link

关于target的resize #87

Open ruiqiren opened 3 years ago

ruiqiren commented 3 years ago

target = cv2.resize(target,(target.shape[1]/8,target.shape[0]/8),interpolation = cv2.INTER_CUBIC)*64 这个语句什么作用

WYG-2021 commented 3 years ago

The size of the output density map after passing through the model is 1 / 8 of that of the original image，and'*64' is to ensure the consistency of the count。