FGVC

FGVC copied to clipboard

How to train the network？

1

How to train the network？

lengfengio

Brothers, add a QQ to discuss this code。 +1261450199

lengfengio

Evaluation Metrics

2

Hey, I ran the inference on the 29 Huang annotated sequences from DAVIS 2017. ``` srun python video_completion.py \ --mode object_removal \ --seamless \ --path ../data/Davis/Huang_annotations/rgb_png \ --path_mask ../data/Davis/Huang_annotations/mask_png \...

ewwnage

test question

2

1. I observed that when the scene changes greatly, the repair results are better, but when the scene changes little, there maybe have artifacts in the repair results. How to...

gao123qiang

grid_sample() error caused by shape miss-match between feature maps and grid object

2

Hi, I ran into this error, I tried to work it out myself and I found the cause but no real solution yet, I'm willing to find a reliable one...

eduardathome

Where can I read about all those parameters such as edge guide, mixed precisions and so on?

1

Also, if I don't type them in the prompt they're not used or some default options are used? Noob questions I know. I don't know anything about coding As far...

MyaaMyaa

Object removal task evaluation code

3

Thankyou for the great code. "Results in the object removal setting, however, are difficult to compare and evaluate due to the lack of ground truth content behind the masked object....

harsh-sengar

对于较少背景移动时，去除文字水印，会出现填充拖影问题

1

测试图片在这个压缩包里 testing pictures are here. [test.zip](https://github.com/vt-vl-lab/FGVC/files/7248243/test.zip) l)

1fisher

How can I elaborate 500 images?

5

Hi! I've problems to elaborate 500 images because I go in out of memory of ram. Moreover I tried with 2 images and It went in OOM of VRAM. Maybe...

Cioscos

No frame_seamless_comp_xxx folder in Colab

1

Like the title says; it doesn't create these folders after processing. I would love to hear what I missed! :)

GuusDeKroon