dibschat / tempagg Goto Github PK
View Code? Open in Web Editor NEW[ECCV 2020] Temporal Aggregate Representations for Long-Range Video Understanding
License: MIT License
[ECCV 2020] Temporal Aggregate Representations for Long-Range Video Understanding
License: MIT License
Hi,
I'm having this errorError running Epic-Kitchens-55. Have you encountered this before? Thanks
Save file name anti_mod_rgb_span_6_s1_5_s2_3_s3_2_recent_2_r1_1.6_r2_1.2_r3_0.8_r4_0.4_bs_10_drop_0.3_lr_0.0001_dimLa_512_dimLi_512_epoc_15_vb_nn
Printing Arguments
Namespace(add_noun_loss=True, add_verb_loss=True, alpha=1, batch_size=10, best_model='best', debug_on=False, display_every=10, dropout_rate=0.3, ek100=False, epochs=15, img_tmpl='frame_{:010d}.jpg', json_directory='tempAgg_ant_rec//models_anticipation/', latent_dim=512, linear_dim=512, lr=0.0001, modality='rgb', mode='train', noun_class=352, noun_loss_weight=1.0, num_class=2513, num_workers=0, past_attention=True, path_to_data='/content/drive/MyDrive/Individual_Project/Models/RULSTM/rulstm-master/RULSTM/data/ek55', path_to_models='models_anticipation/ek55', recent_dim=2, recent_sec1=1.6, recent_sec2=1.2, recent_sec3=0.8, recent_sec4=0.4, resume=False, scale=True, scale_factor=-0.5, schedule_epoch=10, schedule_on=1, span_dim1=5, span_dim2=3, span_dim3=2, spanning_sec=6, task='action_anticipation', topK=1, trainval=False, verb_class=125, verb_loss_weight=1.0, verb_noun_scores=True, video_feat_dim=1024, weight_flow=0.1, weight_obj=0.25, weight_rgb=0.4, weight_roi=0.25)
Populating Dataset: 100% 23493/23493 [00:33<00:00, 694.22it/s]
Populating Dataset: 100% 4979/4979 [00:07<00:00, 689.38it/s]
Add verb losses
Add noun losses
/usr/local/lib/python3.7/dist-packages/torch/optim/lr_scheduler.py:134: UserWarning: Detected call of lr_scheduler.step()
before optimizer.step()
. In PyTorch 1.1.0 and later, you should call them in the opposite order: optimizer.step()
before lr_scheduler.step()
. Failure to do this will result in PyTorch skipping the first value of the learning rate schedule. See more details at https://pytorch.org/docs/stable/optim.html#how-to-adjust-learning-rate
"https://pytorch.org/docs/stable/optim.html#how-to-adjust-learning-rate", UserWarning)
/pytorch/aten/src/ATen/native/cuda/Loss.cu:455: nll_loss_backward_reduce_cuda_kernel_2d: block: [0,0,0], thread: [1,0,0] Assertion t >= 0 && t < n_classes
failed.
/pytorch/aten/src/ATen/native/cuda/Loss.cu:455: nll_loss_backward_reduce_cuda_kernel_2d: block: [0,0,0], thread: [4,0,0] Assertion t >= 0 && t < n_classes
failed.
/pytorch/aten/src/ATen/native/cuda/Loss.cu:455: nll_loss_backward_reduce_cuda_kernel_2d: block: [0,0,0], thread: [7,0,0] Assertion t >= 0 && t < n_classes
failed.
Traceback (most recent call last):
File "main_anticipation.py", line 674, in
main()
File "main_anticipation.py", line 531, in main
start_epoch, start_best_perf, schedule_on)
File "main_anticipation.py", line 400, in train_validation
loss.backward()
File "/usr/local/lib/python3.7/dist-packages/torch/_tensor.py", line 307, in backward
torch.autograd.backward(self, gradient, retain_graph, create_graph, inputs=inputs)
File "/usr/local/lib/python3.7/dist-packages/torch/autograd/init.py", line 156, in backward
allow_unreachable=True, accumulate_grad=True) # allow_unreachable flag
RuntimeError: CUDA error: device-side assert triggered
Hi, thank you so much for the awesome work! After getting the results, I tried to generate jsons file for the validation set of ek100. However, I have not seen any file under the folder of anticipation. Could you help me with it! Thank you so much!
command line:
python main_anticipation.py --mode validate_json --json_directory ./jsons/anticipation --ek100 --path_to_data ./RULSTM/data/ek100 --path_to_models ./models_anticipation/ek100/ --modality rgb --num_class 3806 --verb_class 97 --noun_class 300
result:
Save file name anti_mod_rgb_span_6_s1_5_s2_3_s3_2_recent_2_r1_1.6_r2_1.2_r3_0.8_r4_0.4_bs_10_drop_0.3_lr_0.0001_dimLa_512_dimLi_512_epoc_15_vb_nn
Printing Arguments
Namespace(add_noun_loss=True, add_verb_loss=True, alpha=1, batch_size=10, best_model='best', debug_on=False, display_every=10, dropout_rate=0.3, ek100=True, epochs=15, img_tmpl='frame_{:010d}.jpg', json_directory='./jsons/anticipation', latent_dim=512, linear_dim=512, lr=0.0001, modality='rgb', mode='validate_json', noun_class=300, noun_loss_weight=1.0, num_class=3806, num_workers=0, past_attention=True, path_to_data='./RULSTM/data/ek100', path_to_models='./models_anticipation/ek100/', recent_dim=2, recent_sec1=1.6, recent_sec2=1.2, recent_sec3=0.8, recent_sec4=0.4, resume=False, scale=True, scale_factor=-0.5, schedule_epoch=10, schedule_on=1, span_dim1=5, span_dim2=3, span_dim3=2, spanning_sec=6, task='action_anticipation', topK=1, trainval=False, verb_class=97, verb_loss_weight=1.0, verb_noun_scores=True, video_feat_dim=352, weight_flow=0.1, weight_obj=0.25, weight_rgb=0.4, weight_roi=0.25)
However, there are no files in the folder.
Thanks
Hello, thanks for your hard work! It really provides great convenience for reimplementation.
Meanwhile, I would like to know if the TSM-based features for EPIC-100 will be available for download as those of Epic-Kitchens do? Thanks a lot.
Hello, It would be a great help if you can share the I3D features for the Breakfast and 50Salads datasets.
Thanks for your great work! I want to build a multimodal fusion model based on your work. Could you please send me a copy of your trained model of each modal for the Action recognition task of EPIC-KITCHENS-100 if possible? I would be very appreciated if you can help me. Thank you very much!
A declarative, efficient, and flexible JavaScript library for building user interfaces.
๐ 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. ๐๐๐
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 โค๏ธ Open Source for everyone.
Alibaba Open Source for everyone
Data-Driven Documents codes.
China tencent open source team.