Open JialeTao opened 2 years ago
Can you post some of your visual results here?
Thanks for quick reply. I make a screen shot of the reconstructed gif as follow:
Can you send an entire gif?
Hi, I uploaded a few results.
I see, so there are some problematic gray artifacts on the border. I need to check it out.
Yeah, I just noticed that. Thanks for checking.
I see, so there are some problematic gray artifacts on the border. I need to check it out.
Hi, is the cause of this phenomenon checked out?
Hi, I use the provided checkpoint of MGIF dataset to run evaluation code for the "mode" reconstruction, and get the L1 metric of 0.027 while the paper report the 0.0206. There is a big difference between them. So I doubt that if I make sth. wrong. I use the pytorch version 1.4.0.![image](https://user-images.githubusercontent.com/38600167/130404943-fb970608-4f29-4eb9-a9cb-6a70e34dee11.png)