Context-Aware_Crowd_Counting-pytorch

Context-Aware_Crowd_Counting-pytorch copied to clipboard

 cannnet.py第75行，谢谢你帮我解决除0错误

hosegragon

Q- Can i load pretrained weights for training of part A?

SyedHamza0196

你好，为什么我用的你的代码，跑了352个epoch(shanghaiTech Part_A)，mae81左右，没有达到论文说的62.3

haojie0616

The paper sain'We therefore exploit them as input to auxiliary networks with weights θjsa that compute the weights ωj assigned to each one of the S different scales we use.',But...

RanRan-Margaret

when I train ，apperance “OSError: cannot find loader for this HDF5 file，how to solve this problem ”

huangqi111

when there is less than 4 point gaussian_filter_density get an error

3

s-JoL

When using data_preparation / k_nearest_gaussian_kernel.py, I can't find 'IMG_1.npy'. Has anyone encountered this problem? Thanks for answering.

ft-z

resize the img and target to the desired size? It's not a common approach and not a ideal handle intuitively. The image size of SHT-A is quite Variegated, will that...

Harr7y

如何将测试生成的密度图和GT输出出来？

eain3314

validation的选择

13

请问您这个是不是只有train test，没有val？

visionxyz