CrowdCounting-SASNet

CrowdCounting-SASNet copied to clipboard

模型难以收敛

3

试过Adam, SGD优化器，学习率1e-4，模型没有收敛的迹象。请问一下，优化器，学习率以及数据增强等都用的哪些呢？

LaiPiXiong

train.py

9

您好，能参考一下您的train.py吗 如果可以的话请您发到873726675@qq .com 万分感谢

zuofengyouliang

There may be a difference about "Confence Head" between Code and paper

1

In paper, there are two **conv3** in Confidence Head, but according to your project code, I find there are two **conv1** in Confidence Head(line 111 to 134 of the CrowdCounting-SASNet/model.py...

CarpeDiemly

How did you train models?

10

thanks for good code! I want to know how did you train models(SHHA.pth,SHHB.pth)?

nomurakeiya

训练的时候给的batch为8能运行，测试的时候batch为1，显存都不够用呢？

8

32G显卡，batch为1都带不动。。。。。。。

LaiPiXiong

How to estimate own image.

4

Hey,there! I want to estimate the density map from the image I took and measure the number of people. Is it possible to create a density map using only images?...

nomurakeiya

Thanks for your code. Why do you use both sigmoid and softmax function instead of only softmax in the confidence heads? 感谢您分享的代码。在confidence heads中，为什么同时使用了sigmoid和softmax函数，而不是只用softmax函数？

BorisChen1998

I am a prospective graduate student, and I want to coding this paper during my vacation. At present, the training part of the code has been written roughly, but in...

msn199959

seekFire

在运行main.py程序的时候显示第22行出错， from datasets.loading_data import loading_data ModuleNotFoundError: No module named 'datasets.loading_data'

ankangzuo