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: 1 month summary

17 点作者 dmonn超过 7 年前

2 条评论

J0-nas超过 7 年前
&gt; A forward() function gets called when the Graph is run.<p>Isn&#x27;t that almost exactly the same in tensorflow? You&#x27;d run your model to generate an output, or&#x2F;and run your optimization operation t optimize the model.<p>&gt; Based on some reviews, PyTorch also shows a better performance on a lot of models compared to TensorFlow.<p>Citation needed. How good are the examples optimized? What does performance mean? Precision or learning iterations per second?<p>If it&#x27;s the later, in which environment? CPU&#x2F;GPU&#x2F;distributed computing?
评论 #15559690 未加载
Svenstaro超过 7 年前
While I think that this is a somewhat useful rough overview, it should have had some more details about the actual differences and in particular how to accomplish the same thing with some code examples in each library.<p>On a side note: I know that I can also link tensorflow directly to a C++ application instead of using it with python. Can the same be done with pytorch?
评论 #15562532 未加载