Vishwanath Sindagi
Results
4
comments of
Vishwanath Sindagi
The authors in the paper suggested pre-training. However, I did not do pre-training.
I did not use any normalization on input data. Though batch normalization is implemented, I did not use it since the original paper does not use it. Also, the training...
You are correct. The ground-truth density maps are calculated differently as compared to the paper. Neverthless, I get comparable results as in the paper.
Note that the density map after resizing are normalized (see line 43). ![image](https://user-images.githubusercontent.com/29029426/34050316-6c50dd30-e188-11e7-971c-8ddb1c8069cb.png) So, resizing of input image and density map are not exactly similar.