ContrastiveSeg

ContrastiveSeg copied to clipboard

Hello. Thanks for your great work. I run the script cityscapes/hrnet/run_h_48_d_4_contrast_mem.sh, but the it turns out that the result is worse than baseline. There may be some bugs in the...

hhxzzy

Thank you for your excellent work, Dr. Zhou. I am a novice postgraduate, and my coding ability is not high. I want to use your method on my own two-class...

Pantherk1

Memory and semi-hard example mining code

6

Hi, well done on the nice work. I have the following questions regarding the codebase: 1) I believe there is an issue in the pixel memory code. (or perhaps that's...

TheoPis

About the hard anchor samping

3

Hi, thank you for the great work. I am currently using your pipeline on my dataset. I have a question about the hard anchor sampling function. As the label (128...

leeh43

Cannot run the loss of loss_contrast_mem.py

1

Hello, I tried to run contrastive seg with memory bank, but the code seems that it cannot connect to **loss_contrast_mem.py** and I cannot find a suitable seg_net to conduct in...

winycg

About args n_view,max_samples

4

Hello! Your work is outstanding! I did a detailed research on both the paper and the code. There are a lot of questions that I don’t understand: 1. I want...

xianxuan-z

Question about hard sample mining

3

Hi Dr.Zhou, thank you for your excellent work. Did you provide the loss implementation for Hardest Example Sampling and Semi-Hard Example Sampling? I only found the implementation of Segmentation-Aware Hard...

curiosity654

I don't find your 10% hardest sampling strategy implement. Your memory bank only randomly stores K positive and negative pairs.

Thebodyoflake

Momentum Update

2

First of all, I would like to say that this is a very milestone work. But I need to solve several problems so that I can better understand it. 1....

Macc520

maybe bug in ./segmentor/trainer_contrastive.py

5

In./segmentor/trainer_contrastive.py I think #138 pixel_queue_ptr[lb] = (pixel_queue_ptr[lb] + 1) % self.memory_size should be #138 pixel_queue_ptr[lb] = (pixel_queue_ptr[lb] + K) % self.memory_size

eraserNut