question about shape of ground truth density map, and train.prototxt

miao0913 / SaCNN-CrowdCounting-Tencent_Youtu

Crowd Counting Via Scale-adaptive Convolutional Neural Network

107 stars 41 forks source link

question about shape of ground truth density map, and train.prototxt #16

Closed yypeng9468 closed 6 years ago

yypeng9468 commented 6 years ago

Sorry to bother, but I have one question about the shape of ground truth density map in this repo. You say in your essay that the output density map if 1/8 of the input image, so is it necessary for me to downsample my density map by factor 8. And if I want to prepare my data in lmdb format, I should turn the ground truth csv into density map picture, right?

miao0913 commented 6 years ago

yes. you need to downsample it by 8. And the prototxt we provide requires an input of lmdb formate for both density map and image.