ACSCP_cGAN icon indicating copy to clipboard operation
ACSCP_cGAN copied to clipboard

Code implementation for paper that "ACSCS: Crowd Counting via Adversarial Cross-Scale Consistency Pursuit"; This is method of Crowd counting by conditional generation adversarial networks

Results 14 ACSCP_cGAN issues
Sort by recently updated
recently updated
newest added

## Beep boop. Your images are optimized! Your image file size has been reduced by **9%** 🎉 Details | File | Before | After | Percent reduction | |:--|:--|:--|:--| |...

为什么 我进行标注 完成之后生成GT_mat文件 没有后缀 并且标注一次覆盖一次 有谁能解决一下么?

Hi! Thanks for your project and can you give me your UCF_CC_50 with .npy dataset? Thanks!

您好!很高兴您能够分享您的项目,不过我用您的代码直接运行`python main.py --phase train`会报错,提示: ValueError: Variable vgg_16/conv1/conv1_1/weights already exists, disallowed. Did you mean to set reuse=True in VarScope? Originally defined at: File "/home/user/anaconda2/lib/python2.7/site-packages/tensorflow/contrib/framework/python/ops/variables.py", line 216, in variable use_resource=use_resource) File "/home/user/anaconda2/lib/python2.7/site-packages/tensorflow/contrib/framework/python/ops/arg_scope.py",...

您好,之前在尝试给自己的训练集打标签。您所给出的制作标签第二步matlab代码,应当输出mat文件。但是我的check程序跑不动,请问check是什么功能,是否可以忽略第三步中的gt文件是第二步手动标注所获得的的吧。希望得到您的帮助。

您好,我尝试着跑了一些论文出现的例子,比如ShangehaiTech/part_B/test_data/images/IMG_141.jpg,(论文中Figure 4.的第5行),得到的estimated=236, 与论文中的33.9相差甚远。 我是参考的product.py的代码去跑的, 图片resize成720x720。请问我使用的方法对吗? 提前感谢。

For anyone having trouble creating density maps using the given map_mcnn.m, try using this one which I made a few changes to. [MCNN_Density_Matlab.zip](https://github.com/Ling-Bao/ACSCP_cGAN/files/2935427/MCNN_Density_Matlab.zip)

为什么ground truth里面标记的头的坐标不是整数?

您好,看了您的一系列回答,代码中使用padding将图像尺寸固定,请问 1)怎样使用padding固定尺寸, 2)固定尺寸的同时,需要对密度图进行处理吗?

您好,不知道您在UCSD和worldexpo'10这两个数据集做过测试没有,这两个数据集都有一个ROI区域的限制。那最后对密度图求和的时候,是采用整张图求和还是对密度图的ROI部分进行求和?