CSRNet-pytorch

CSRNet-pytorch copied to clipboard

What does the following code mean?img[0,:,:]=img[0,:,:]-92.8207477031

4

img[0,:,:]=img[0,:,:]-92.8207477031 img[1,:,:]=img[1,:,:]-95.2757037428 img[2,:,:]=img[2,:,:]-104.877445883 @leeyeehoo Thank you for your sharing. When you validate CSRNet with 'val.ipynb',you use the code above.So,my question is why you minus the specific values above(92.8207477031,95.2757037428,104.877445883).What is the...

CheungYooo

line 18 , 19 change because the difference of python 2 and 3

farnaz-frd

line 18 , 19 changed because the conflict syntax of python 2 vs, 3

farnaz-frd

in line 10 --> ground_truth to ground-truth

farnaz-frd

KungFuPandaPro

Can you provide the test file to test new images on and get a count for them? thanks

Muhibullah1

How to get the count from the density map

6

Hi, you said that the method to generate ground truth is from https://arxiv.org/abs/1608.06197 from that paper, they said > We generate our ground truth by simply blurring each head annotation...

twmht

Can anyone please suggest a good tagging tool for crowd counting tasks. Be it online or offline.

SyedHamza0196

为什么要把img和target用Variable封装起来?

1

如题. 在`train.py:train()`的`train_loader`循环里, img和target都套上了一层`torch.autograd.Variable`. 在`train.py:validate()`的`test_loader`循环里, img套上了一层`torch.autograd.Variable`. 为什么要让数据成为可导的??

winston-wen

训练part_A数据集，batch size=1，loss震荡很厉害，有什么解决办法吗

3

berylyellow