christophreich1996 / deepfoveapp_for_video_reconstruction_and_super_resolution Goto Github PK
View Code? Open in Web Editor NEWDeepFovea++: Reconstruction and Super-Resolution for Natural Foveated Rendered Videos (PyTorch).
License: MIT License
DeepFovea++: Reconstruction and Super-Resolution for Natural Foveated Rendered Videos (PyTorch).
License: MIT License
Hi, I'm trying the full installation, but keep failing.
What are the "exact" versions for your packages (including CUDA).
Thanks.
Have you ever published your paper on any conferences or journals?
It is interesting and related to my ongoing work. I want to cite your work officially but can't find a proper one.
Hi, @ChristophReich1996, I can't start the training process.
After I execute python main.py --train
, I got this
Traceback (most recent call last):
File "main.py", line 81, in <module>
model_wrapper.train(epochs=20)
File "/home/eason/research/DeepFovea++/model_wrapper.py", line 207, in train
self.discriminator_network(label),
File "/home/anaconda3/envs/deepfovea++/lib/python3.7/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/anaconda3/envs/deepfovea++/lib/python3.7/site-packages/torch/nn/parallel/data_parallel.py", line 159, in forward
return self.module(*inputs[0], **kwargs[0])
File "/home/anaconda3/envs/deepfovea++/lib/python3.7/site-packages/torch/nn/modules/module.py", line 727, in _call_impl
result = self.forward(*input, **kwargs)
File "/home/eason/research/DeepFovea++/discriminator.py", line 45, in forward
output = output.view(1, self.in_channels * 2, self.frames, output.shape[2], output.shape[3])
RuntimeError: shape '[1, 6, 6, 192, 256]' is invalid for input of size 3538944
I checked the prediction of the generator and the label and both of their dimension is [2, 18, 768, 1024]
I'm not sure if there's anything missing.
(By the way, I successfully executed validation.)
Thanks.
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.