TE
科技回声
首页24小时热榜最新最佳问答展示工作
GitHubTwitter
首页

科技回声

基于 Next.js 构建的科技新闻平台,提供全球科技新闻和讨论内容。

GitHubTwitter

首页

首页最新最佳问答展示工作

资源链接

HackerNews API原版 HackerNewsNext.js

© 2025 科技回声. 版权所有。

PyTorch vs. TensorFlow in Academic Papers

103 点作者 m3at大约 3 年前

8 条评论

brutus1213大约 3 年前
I&#x27;m a professional scientist, so let me give my two cents on this matter. Being able to compare your work against SOTA (state of the art) is pretty critical in academic publications. If everyone else in your area uses framework X, it makes a lot of sense for you to do it too. For the last few years, Pytorch has been king for the topics I care about.<p>However .. one area where Tensorflow shined was the static graph. As our models get even more intensive and needs different parts to execute in parallel, we are seeing some challenges in PyTorch&#x27;s execution model. For example:<p><a href="https:&#x2F;&#x2F;pytorch.org&#x2F;docs&#x2F;stable&#x2F;notes&#x2F;cuda.html#use-nn-parallel-distributeddataparallel-instead-of-multiprocessing-or-nn-dataparallel" rel="nofollow">https:&#x2F;&#x2F;pytorch.org&#x2F;docs&#x2F;stable&#x2F;notes&#x2F;cuda.html#use-nn-paral...</a><p>It appears to me that high performance model execution is a bit tricky if you want to do lots of things in parallels. TorchServe also seems quite simple compared to offerings from Tensorflow. So in summary, I think Tensorflow still has some features unmatched by others. It really depends on what you are doing.
评论 #30665687 未加载
评论 #30664214 未加载
cweill大约 3 年前
Can someone please share the current state of deploying Pytorch models to productions? TensorFlow has TF serving which is excellent and scalable. Last I checked there wasn&#x27;t a PyTorch equivalent. I&#x27;m curious how these charts look for companies that are serving ML in production, not just research. Research is biased towards flexibility and ease of use, not necessarily scalability or having a production ecosystem.
评论 #30667491 未加载
kylebgorman大约 3 年前
If I may, there&#x27;s no real reason to break out ACL vs. NAACL vs. EMNLP, since they&#x27;re all run by the ACL and one would be hard-pressed to say how the EMNLP community might differ from the ACL community at this point. And if you&#x27;re doing NAACL you might want to do EACL and IJCNLP too.
siver_john大约 3 年前
The graph on here seems similar to what I&#x27;ve noticed. My lab mainly uses Tensorflow mainly driven by my knowledge. And the only reason why I learned Tensorflow initially was that PyTorch was just starting when I was choosing a framework and the documentation wasn&#x27;t as established. However, recently I recommended a student who was asking me which framework to probably use PyTorch due to the ease of implementation comparatively.
评论 #30668024 未加载
savant_penguin大约 3 年前
A big mistake on the side of tensorflow was trying to copy theano including those dreadful functional loops whereas in pytorch for loops are not pain to use and very well integrated with the language
jitl大约 3 年前
What about JAX?
评论 #30663471 未加载
评论 #30666093 未加载
jankaul大约 3 年前
I mostly used Tensorflow and I&#x27;m curious what makes PyTorch models easier to implement? With Tensorflow 2 you get the Keras API which is really easy to use.
fartcannon大约 3 年前
Tensorflow was too hard.<p>Keras wasn&#x27;t hard enough.<p>Pytorch was juuuuust right.