Sai Srinadhu K

Pre-trained Bayesian Loss Crowd Counting Model

1

Hello @gjy3035, Can you also please provide the above pre-trained model? One more thing the CANNet model is not getting loaded properly, it's saying model might be corrupted. Thanks.

@emited Please check and let me know. 1. Added clipping before the optimizer step. 2. Updated with .item() rather than .data[0] 3. Input is normalized but the reconstruction is done...

Parameters for ShanghaiTech Part A

6

Hello @ZhihengCV , I changed the --crop-size to 256 as mentioned in the paper. While data-preparation the min_size is fixed as 256 and max_size as 5096. All the other parameters...

How is the idea any different?

1

Hello @gjy3035, I skimmed through the paper. Please do correct me if I am wrong, How is the attention presented in here any different from [Dual Attention Network for Scene...