Qi Dai

icon indicating an email [email protected]

icon location Hong Kong icon location PhD Student @ EE CUHK

Results 4 issues of Qi Dai

Loss for train_from_scratch and continue_train

Hey, I wonder what's the loss level when you train from scratch? For me I followed the instruction in README to format KITTI data. When training from scratch the loss...

Large EPE for optical flow evaluation

Hey Anurag, thanks for your wonderful work! I got the following results when running test_flow.py: | | epe_total | epe_sp | epe_mv | Fl | epe_total_gt_mask | epe_sp_gt_mask | epe_mv_gt_mask...

Questions of running run_CIL on Town02

2 comment

Hey! When I run the 'run_CIL.py' of Carla_0.8.2 in Town01, it works good. However when change to Town02, something strange happen: 1. The first episode runs smoothly, but the car...

Feature Request

Correlation or Convolution during Local Frequency Analysis

Hi Cattle, thanks for your wonderful code! I notice that you use _imfilter_ in gabor_gradient_field.m. The default operation adopted by _imfilter_ is **correlation**, instead of convolution. However, the operation in...