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).  So, resizing of input image and density map are not exactly similar.