Daniel Koguciuk

Hello, FYI, I've ported the repository to tensorflow 1.2 and keras 2.1. I don't know if anyone would need it, but I thought, I'll just leave this here... :smile: Best,...

#### Changes Implementation of biHomE perceptual loss. Based on: [ Perceptual Loss for Robust Unsupervised Homography Estimation ](https://openaccess.thecvf.com/content/CVPR2021W/IMW/html/Koguciuk_Perceptual_Loss_for_Robust_Unsupervised_Homography_Estimation_CVPRW_2021_paper.html) paper and its implementation: [CODE](https://github.com/NeurAI-Lab/biHomE). #### Type of change - [ ]...

Unloading fix

3

Now unloading a sequence does not delete the information about the sequence from the dataset - it just release the loaded data.

Masksembles - a couple of questions

3

Hi @nikitadurasov , I have a couple of questions about Masksembles: 1. What is the difference between Masksembles and Batchensemble? Is there any particular reason you do not discuss it...

Code ETA

1

Hi @suyz526 , do you have any estimate on when your code could be published? Best, D

MACE of provided model

17

Hi @ruizengalways , What MACE should the provided model have? I've downloaded `pfnet_0200.h5 `, run the eval script and ended up with: `MACE Metric: 7.451346` It sounds like a way...

How to understand the results

8

Hi @Seth-Park , I'm struggling to understand the evaluation metrics. In the paper you've got Table 2:  But after downloading and evaluating your pretrained model I...