uark-aicv / aoe-net Goto Github PK
View Code? Open in Web Editor NEW[IJCV] AOE-Net: Entities Interactions Modeling with Adaptive Attention Mechanism for Temporal Action Proposals Generation
Home Page: https://arxiv.org/abs/2210.02578
[IJCV] AOE-Net: Entities Interactions Modeling with Adaptive Attention Mechanism for Temporal Action Proposals Generation
Home Page: https://arxiv.org/abs/2210.02578
hi, I got the following error when running training, do you know how to solve it?
Traceback (most recent call last):
File "main.py", line 232, in
main(args)
File "main.py", line 223, in main
solver.train(cfg.TRAIN.NUM_EPOCHS)
File "main.py", line 140, in train
self.train_epoch(train_loader, bm_mask, epoch, writer)
File "main.py", line 85, in train_epoch
confidence_map, start, end = self.model(env_features, agent_features, agent_masks, obj_features, obj_masks)
File "/home/gpu/anaconda3/envs/ir/lib/python3.6/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/gpu/anaconda3/envs/ir/lib/python3.6/site-packages/torch/nn/parallel/data_parallel.py", line 161, in forward
outputs = self.parallel_apply(replicas, inputs, kwargs)
File "/home/gpu/anaconda3/envs/ir/lib/python3.6/site-packages/torch/nn/parallel/data_parallel.py", line 171, in parallel_apply
return parallel_apply(replicas, inputs, kwargs, self.device_ids[:len(replicas)])
File "/home/gpu/anaconda3/envs/ir/lib/python3.6/site-packages/torch/nn/parallel/parallel_apply.py", line 86, in parallel_apply
output.reraise()
File "/home/gpu/anaconda3/envs/ir/lib/python3.6/site-packages/torch/_utils.py", line 428, in reraise
raise self.exc_type(msg)
ValueError: Caught ValueError in replica 0 on device 0.
Original Traceback (most recent call last):
File "/home/gpu/anaconda3/envs/ir/lib/python3.6/site-packages/torch/nn/parallel/parallel_apply.py", line 61, in _worker
output = module(*input, **kwargs)
File "/home/gpu/anaconda3/envs/ir/lib/python3.6/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/data1t/liurui/AOE-Net-main/models/model.py", line 140, in forward
agent_fused_features, selected_agents = self.fuse_agent(agent_features, agent_masks, env_features)
ValueError: too many values to unpack (expected 2)
Hi,
First of all, Thank you for sharing your code.
My name is Sorn. I am the researcher. I am currently interested
in Temporal Action Proposal Generation (TAPG) including your
project (AOE-Net). I would like to try your code as reference.
However, I found that there is no object feature for testing, its link
is same as agent feature, in THUMOS dataset. Is it possible to
provide us the object feature for testing?
Thank you in advance
Can you share the code for generating feature data. json files and label data. json files? I don't know how to generate data in this format.
the link of object features of Thumos14 is expired.
could you please reupload the feature?
May I ask what network is used to extract environmental features and participant features, what is the format of the extracted data, and how is it converted into the current data input format of the aoe-net network? Could you please show me some details of data processing?
Hello, I am a graduate student who is very interested in your work. I would like to try implementing your code on my own dataset. Can you provide me with some implementation details for the data feature extraction section, which can help me obtain my own video features for training? Thank you.
i want to reproduce the result on thumos14 dataset,however where can i find thumos_annotations_09.json file? Can you update it to github?
Also i find it diffcult to read and extract feature from my own custom dataset to form as the specific format of your tsn_env_feature,can you provide the code? Why a video has seveal json file and what does the 'segment' means on your feature json file? much thanks!
can you share frm_num.pkl and movie_fps.pkl file?
Hello, I encountered some issues while reproducing the results of your work on the Activity_net dataset. How can I obtain the AUC (test) results? I can get AUC (val) by running the command python main.py --cfg-file config/anet_proposals_CLIP_v1.yaml MODE 'validation' GPU_IDS [0], but I cannot get AUC (test) by running python main.py --cfg-file config/anet_proposals_CLIP_v1.yaml MODE 'testing' GPU_IDS [0]. I don't know how to do it. Can you tell me?
the link of object features of Thumos14 is expired.
could you please reupload the feature?
Hello, I encountered an error while running "detection": FileNotFoundError: [Errno 2] No such file or directory: 'results/classification_ Results. json '
May I ask what content is contained in this classification_results.json? Can you provide this json file?
the link of object features of ActivityNet-1.3 is expired.
could you please reupload the feature?
I would like to reproduce your results on this dataset to help me learn to understand the correlation. Thank you for your help.
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.