carrierlxk / agnn Goto Github PK
View Code? Open in Web Editor NEWZero-shot Video Object Segmentation via Attentive Graph Neural Networks (ICCV2019 Oral)
Zero-shot Video Object Segmentation via Attentive Graph Neural Networks (ICCV2019 Oral)
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~
hi, you say at paper that graph is N frame with fully connected, but why graph with 3 node should work at implemetation level?
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,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?
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.
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 , @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!
I don't know how to write val_seqs.txt.I hope you can tell me. Thank you very mach.
Hello !当我复现代码的时候,遇到一些问题,想咨询一下您~
@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.
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?
How to write DAVIStest_seqs.txt?
I'm so sorry to ask this question.But I really don't how to write it
hi, the link for baidu or googledrive are both unavailable. Could you help update 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.
A declarative, efficient, and flexible JavaScript library for building user interfaces.
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
An Open Source Machine Learning Framework for Everyone
The Web framework for perfectionists with deadlines.
A PHP framework for web artisans
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
Some thing interesting about web. New door for the world.
A server is a program made to process requests and deliver data to clients.
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
Some thing interesting about visualization, use data art
Some thing interesting about game, make everyone happy.
We are working to build community through open source technology. NB: members must have two-factor auth.
Open source projects and samples from Microsoft.
Google ❤️ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.