huntersxsx / ranet Goto Github PK
View Code? Open in Web Editor NEWsource code of our RaNet in EMNLP 2021
source code of our RaNet in EMNLP 2021
I try to solve the issue by setting cudnn.enabled=false, change the version of cuda, and I try to reduce the num of workers and batch_size. But the error still occurs. Have you encountered same problems?
`Traceback (most recent call `last):
File "moment_localization/train.py", line 313, in <module>
scheduler=scheduler)
File "/home/gigigi/LJQ/RaNet/moment_localization/../lib/core/engine.py", line 53, in train
state['optimizer'].step(closure)
File "/home/gigigi/anaconda3/envs/torch1/lib/python3.7/site-packages/torch/optim/adam.py", line 58, in step
loss = closure()
File "/home/gigigi/LJQ/RaNet/moment_localization/../lib/core/engine.py", line 42, in closure
loss, output = state['network'](state['sample'])
File "moment_localization/train.py", line 169, in network
prediction, map_mask = model(textual_input, textual_mask, visual_input)
File "/home/gigigi/anaconda3/envs/torch1/lib/python3.7/site-packages/torch/nn/modules/module.py", line 493, in __call__
result = self.forward(*input, **kwargs)
File "/home/gigigi/LJQ/RaNet/moment_localization/../lib/models/ranet.py", line 25, in forward
vis_h, txt_h = self.encoder_layer(visual_input, textual_input, textual_mask)
File "/home/gigigi/anaconda3/envs/torch1/lib/python3.7/site-packages/torch/nn/modules/module.py", line 493, in __call__
result = self.forward(*input, **kwargs)
File "/home/gigigi/LJQ/RaNet/moment_localization/../lib/models/feature_encoder/encoder.py", line 139, in forward
vis_frame = self.frame_encoder(visual_input) # B, C, T
File "/home/gigigi/anaconda3/envs/torch1/lib/python3.7/site-packages/torch/nn/modules/module.py", line 493, in __call__
result = self.forward(*input, **kwargs)
File "/home/gigigi/LJQ/RaNet/moment_localization/../lib/models/feature_encoder/encoder.py", line 44, in forward
vis_h = torch.relu(self.vis_conv(visual_input))
File "/home/gigigi/anaconda3/envs/torch1/lib/python3.7/site-packages/torch/nn/modules/module.py", line 493, in __call__
result = self.forward(*input, **kwargs)
File "/home/gigigi/anaconda3/envs/torch1/lib/python3.7/site-packages/torch/nn/modules/conv.py", line 196, in forward
self.padding, self.dilation, self.groups)
RuntimeError: cuDNN error: CUDNN_STATUS_EXECUTION_FAILED
0%| `
Hello, your project is very innovative. But I did not achieve the effect you provided during the reproduction process.
Are you using the file onlydynamic+8conv+captions.yaml?
And what model of GPU are you using?
Perhaps random seeds can also affect the effect. Is it convenient to know which random seed you are using?
It would be great if you could answer my questions. Thank you very much!
RuntimeError: Error building extension 'rcca'
Hello, your project is very innovative. But I did not achieve the effect you provided during the reproduction process.
Are you using the file onlydynamic+8conv+captions.yaml?
And what model of GPU are you using?
Perhaps random seeds can also affect the effect. Is it convenient to know which random seed you are using?
It would be great if you could answer my questions. Thank you very much!
I don't find train.json fil, could you help me?
RuntimeError: cuDNN error: CUDNN_STATUS_NOT_SUPPORTED. This error may appear if you passed in a non-contiguous input.
when I run the code, an error happened, how to fix 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.