PyTorch: An Imperative Style, High-Performance Deep Learning Library [pdf]
1–10 of 17 posts
Re: PyTorch: An Imperative Style, High-Performance Deep Learning Library [pdf]
#2Finally the solution to all of your PyTorch citation problems! :)
Re: PyTorch: An Imperative Style, High-Performance Deep Learning Library [pdf]
#3If you want to read it online - https://www.arxiv-vanity.com/papers/1912.01703/
Re: PyTorch: An Imperative Style, High-Performance Deep Learning Library [pdf]
#4Finally the solution to all of your PyTorch citation problems! :)
Relevant Github issue: https://github.com/pytorch/pytorch/issues/4126
Re: PyTorch: An Imperative Style, High-Performance Deep Learning Library [pdf]
#5If you want to read it online - https://www.arxiv-vanity.com/papers/1912.01703/
ah, yes, why squint at a PDF when you can squint at LaTeX compile errors instead
Re: PyTorch: An Imperative Style, High-Performance Deep Learning Library [pdf]
#6Man it’s kinda sad as a Lua fan to see so much interest in a project where the main goal is just to not use Lua.
I guess academics like familiarity and Lua insistently refuses to be like other languages (arrays and maps in one type, 1-based arrays, nonstandard builtin patterns, etc).
Re: PyTorch: An Imperative Style, High-Performance Deep Learning Library [pdf]
#7It's a bit funny to call it imperative, when really at the end of the day, the objective is to get something where you have very little insight into what the neural net. is doing to the state.
Re: PyTorch: An Imperative Style, High-Performance Deep Learning Library [pdf]
#8Man it’s kinda sad as a Lua fan to see so much interest in a project where the main goal is just to not use Lua. I guess academics like familiarity and Lua insistently refuses to be like other languages (arrays and maps in one type, 1-based arrays, nonstandard builtin patterns, etc).
Academics simply don't have the time to learn languages that do not have substantial ecosystems and relative ease-of-use.
Re: PyTorch: An Imperative Style, High-Performance Deep Learning Library [pdf]
#9Man it’s kinda sad as a Lua fan to see so much interest in a project where the main goal is just to not use Lua. I guess academics like familiarity and Lua insistently refuses to be like other languages (arrays and maps in one type, 1-based arrays, nonstandard builtin patterns, etc).
> the main goal is just to not use Lua.
I don't think that's accurate. People don't really care about Lua, they don't like or dislike it, they just don't know it. The goal of the project is to use python, because people care about Python.
It just happened that porting (lua) torch to Python was chosen, but it could have been another framework.
Re: PyTorch: An Imperative Style, High-Performance Deep Learning Library [pdf]
#10Is there a typo in Listing 1?
The forward function of the conv net should use:
t3 = self.fc(t2)
instead of:
t3 = self.fc(t1)
AFAIK the nn.functional.relu function is NOT inplace by default [1]