Variations-of-SFANet-for-Crowd-Counting

Variations-of-SFANet-for-Crowd-Counting copied to clipboard

How is the Shanghai tech A and B dataset labelled ?

8

Hello ! May I know how did people label the density maps on shanghai tech A and B data set ? Is it possible for us to add on extra...

fatbringer

About "max_unpool2d" function

4

When i use another backbone , i meet this problem：  I cheak the conv5_3.shape and id4.shape , they meet the requirements of the "max_unpool2d" function  Could you help...

ChenFan666

unable download the pretrain model

1

can you share the download link of Paper's_weights_UCF_QNRF.zip again? The current download speed is too slow! thx very much!

Jharry502

Create GT for a different dataset

1

I'm trying to understand how can I get the third column of the .npy training file. What's the meaning of that value? Is there any script to generate it?

javiercalle97

Unable to reproduce the result of the testing image

6

Unable to reproduce the result of the testing image, with using the pretrained model, anyone know how to reproduce the result? thanks.

icoicqico

About the training and testing datasets

1

Hello, I would like to ask where can I find the datasets for testing and training? Thanks.

icoicqico

Problems when training

3

Hi, I trained M-SFANet with part of shanghaiTech samples. BUT the loss converge too slow, and the mse and mae remain large after training a few hundred epoches. Do you...

KrystalCWT

Question about the different checkpoint

1

Hello, First of all, thank you for sharing your work with the code. I have few questions regarding the checkpoints available. I have tried to visualize the density map with...

Shiro-LK

Need requirements of the code

1

jap-patel

Inconsistent shapes of conv4, conv5,feature in Backend()'s forwarding in MSegNet

2

  Anybody come across this problem while using random input picture to generate density map through M-SegNet? why the shape[2] of these 3 tensor differ?

Mozijie255