Junyu Gao

@wait1988 1. we do not conduct the experiment on the combined dataset. I am looking forward to your results! 2. we find the some patterns outsides of ROI are similar...

@wait1988 1. You can download the pre-trained CSRNet model on GCC from this [link](https://mailnwpueducn-my.sharepoint.com/:u:/g/personal/gjy3035_mail_nwpu_edu_cn/EUvnSBJPri9Hhu0b6X2oM_4B0U6xiTB0rMfi2kdHzC-0YA?e=a4K49S). In fact, I implement the relative expreimrnts on UCF-QNRF, Shanghai Tech A and B. The concrete...

1. The setting of CSR on QNRF is same as the setting on Shanghai Tech A. 2. Please check your CSR's module list. You should rename the key values to...

I just run the code to train CSR based on pretrained GCC model, which works well. I think you may use single GPU to train the model. However, our provided...

Semantic segmentation and crowd counting are pixel-wise task. SS is classification and CC is regression. Their network architecture is similar. However, the SOTA SS network maybe perform poorly when directly...

I think you should check the weights is successfully loaded before training. The setting of the two experiments are same. 

@homurajiang See also in https://github.com/gjy3035/C-3-Framework/issues/22#issuecomment-494287652

建议提供具体报错的位置，便于排查问题所在。

@MarkusPfundstein Use the matlab code: https://github.com/gjy3035/C-3-Framework/blob/python3.x/datasets/QNRF/preapre_QNRF.m

1. 不合适。CorwdHuman中会对高密度人群直接用一个大框标注。倒是可以用这种box训练粗糙的人群分割模型，来帮助counting的提升。 2. 是的，counting中一个比较棘手的问题是，人头尺度变化过大。以往的策略是采用自适应核。当然ICME也有检测核密度图回归结合的方案。