xlliu7 / tadtr Goto Github PK
View Code? Open in Web Editor NEW[TIP 2022] End-to-end Temporal Action Detection with Transformer
License: Apache License 2.0
[TIP 2022] End-to-end Temporal Action Detection with Transformer
License: Apache License 2.0
Hello,Thank u for your work!
I want to know how feature_length can be read directly from the video feature files,because I use my own dataset to try this code.
Hi, xiaolong. I'm very interested in your work. As you mentioned in another issue, you use the I3D features form P-GCN for the Thumos14 experiment. I find that some features for the same video have different sizes so that I can't concat them directly. And the diff is always 1. Have you ever met this situation. If ever, how you deal with it? Thx~
Hi, first thanks for your great work.
I am trying to reproduce your results in ActivityNet. I follow the operations in your paper. Using TSP features and add some codes in Dataset module. I can run through whole process in ActivityNet but i just cannot get results as good as you present in the paper. For me, the results drop all about 3-4%.
I am wondering whether you have planning to open source the train code for ActivityNet?
Hello,
thank you for sharing the code. I checked the code and all of the seeds are set.
I further added torch.backends.cudnn.deterministic = True
and torch.backends.cudnn.benchmark = False
to make the code produce the same results in different runs. However, the results differ between different runs.
Do you have any idea why?
Thanks in advance.
Hi @xlliu7,
Interesting paper! I want to know how to combine your model with the classifier? e.g. PGCN in Table 1.
Would you mind sharing the code? Thanks.
Do you have a planed time to release the code of E2E-TAD?
The claimed improvement from actionness regression does not seem to materialize based on my implementation using this code repository. The results with and without actionness regression are very similar.
Upon inspecting the implementation, I noticed a potential issue:
Lines 314 to 325 in 983ae14
Even after correcting this issue, there was still no performance improvement from the actionness regression in my runs (the performance drops a lot actually). Upon my inspection, that because the actionness regression suffers from a serious label imbalance problem as most target IoUs are zero.
Hello, thanks for the nice work.
I have sent an email to request you the codes for ActivityNet.
Could you share your codes?
Best wishes.
https://github.com/xlliu7/TadTR/blob/master/models/transformer.py#L287
这里是在decoder的forward里面计算reference point,
但是在这里
https://github.com/xlliu7/TadTR/blob/master/models/tadtr.py#L185
又重新计算了一次,这两部分应该是重复了
作者您好!最近准备研究这个方向,请问有没有在单个视频上进行推理的代码?
I encountered the above error when trying to run the demo code.
Could you please share the counting code? Thanks!
Can you provide the link to download the features.
Thanks for your great work. When will the training & inference code release? Can you give an approximate date? Thanks!
I'm trying to train on relatively small datasets, mix-up is one way to reduce it from overfitting, but it seems like focal loss is not designed to works with label with probabilities. It seems that this line
Line 274 in 3af0abc
Do you have any idea how to modify focal loss for label with probabilities?
Hi, thank you for your brilliant work!
Can you provided your test results on ActivityNet1.3 dataset?
Thank you very much!
Hi! I'm really interested in using this work for action detection - is there any way I could get access to your training scripts and pretrained weights?
Hello, thank you for your good work!
I want to know how to generate th14_i3d2s_ft_info.json for thumos14 video features. And how to compute ''feature_length", "feature_second" and "feature_fps" for each video?
请问大佬源码什么时候公布呢?
Dear @xlliu7, thank you for your valuable contribution to the community.
I know cleaning code and supporting all datasets require much work.
However, I would greatly appreciate it if you were to release the rest of the code for reproducing results in HACS and ActivityNet.
Could you kindly let me know the time horizon for this?
Best,
Mattia
Thanks open source for this good work.
But, I met a problem.
models/ops/temporal_deform_attn/functions/temporal_deform_attn_func.py", line 40, in backward value, value_spatial_shapes, value_level_start_index, sampling_locations, attention_weights, grad_output, ctx.seq2col_step) RuntimeError: Not implemented
I wonder if it is convenient for you to answer.
Dear researchers,
Thank you for your work.
The links for your networks weights don t work, which prevent us to reproduce your work.
best regards,
Hello, can you provide the TSN features after linear interpolation of activitynet1.3?
Hi Could you tell me how to get the I3D 2stream Feature ? Thanks
Hi. The arxiv paper says code will be made available here. Do you have a date when you plan to release it? Thanks.
I noticed that there are mismatched keys name in weight_dict
, effectively making the losses calculation skipped loss_segments
and loss_actionness
in this line:
Lines 45 to 46 in 3af0abc
Looking at the weight_dict
, loss_seg
is used rather than loss_segments
Lines 498 to 501 in 3af0abc
Line 299 in 3af0abc
For actionness, it's assigned as loss_iou
instead of loss_actionness
, which replaced the loss_iou
by segments loss.
Line 327 in 3af0abc
Are these bugs? Could you confirm it? Thanks.
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.