carrierlxk / agnn Goto Github PK

Thank you for your great work. What is the difference between zero shot video target segmentation and semi-supervised video target segmentation?Zero shot video target segmentation without labels?

@carrierlxk Hi, Xiankai, I am confused about the inference procedure on DAVIS17 and YouTubeVOS, would you mind sharing the inference or test code for multi object segmentation?

Thanks.

I don't know how to write val_seqs.txt.I hope you can tell me. Thank you very mach.

How to write DAVIStest_seqs.txt?
I'm so sorry to ask this question.But I really don't how to write it

Thanks for your wonderful work, I'm trying to set up the environment and running the code, but an error occured. Detialed as follows:

Traceback (most recent call last):
File "train_iteration_conf_agnn.py", line 22, in
from utils.balanced_BCE import class_balanced_cross_entropy_loss
ModuleNotFoundError: No module named 'utils.balanced_BCE'

I can't find any file or folder named "utils" in this repository, could you tell me where I can find it.

when I run the code,it tells me that" ModuleNotFoundError: No module named 'dataloaders.helpers".then i looked for the dataloaders foder and i can't found file named 'helpers'.can you tell me why?

Would you mind sharing the training code of the paper? Thanks.

hi, you say at paper that graph is N frame with fully connected, but why graph with 3 node should work at implemetation level?

Hi , @carrierlxk ,

After watching your ICCV presentation, your work caught me a lot of interests. However, the details of your work couldn't be well understood if the code is unavailable. When will the AGNN be released?

THX!

Dear author:
Could you please give me some infomation about the number and version of your used GPU? I only have two 2080ti, and I do not know whether this hardware can reimplement your results. Have you ever test your code on such two small civil GPU?

您好：
感谢能开源代码
我遇到些小问题，test_seqs.txt应该是DAVIS/JPEGImages/480p下的子目录名称（也就是bear，blackswan，.....），可以使用os.walk自己抽取，但是'/home/ubuntu/xiankai/saliency_data.txt'具体是什么呢？在训练DAVIS数据集时候Dut saliency dataset 必须要有吗，它的作用主要是什么呢
期待回复，谢谢~

您好，非常感谢您开源代码。在代码的模型部分，我看到主模型中的forward对每一个batch做了循环，每一次循环独立处理，在我理解中，batch本身就是独立的，那么是否可以不做循环而直接批次处理呢？

The Error is

Traceback (most recent call last):
File "test_iteration_conf_gnn.py", line 185, in
main()
File "test_iteration_conf_gnn.py", line 136, in main
for index, batch in enumerate(testloader):
File "D:\lib\site-packages\torch\utils\data\dataloader.py", line 615, in next
batch = self.collate_fn([self.dataset[i] for i in indices])
File "D:\lib\site-packages\torch\utils\data\dataloader.py", line 615, in
batch = self.collate_fn([self.dataset[i] for i in indices])
File "D:\muqian\code\AGNN\dataloaders\PairwiseImg_test_new.py", line 115, in getitem
my_index = self.Index[seq_name1]
KeyError: '480p'

i don't know how to tackle it.Please help me.Thank you very mach.

thank you.

hi, the link for baidu or googledrive are both unavailable. Could you help update it?

Hello ！当我复现代码的时候，遇到一些问题，想咨询一下您~

1. 代码中 from utils.colorize_mask import cityscapes_colorize_mask, VOCColorize 在demo 中并未发现此库，是否需要额外下载，如何下载？
2. 在测试中，能否标注各个库的版本，分享一份requirement.txt
3. 测试中 test_seqs.txt 能否提供一下？下载的DAVIS中似乎并未包括。