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。

Efficient Neural Network Loss Landscape Generation

25 点作者 r3tex大约 6 年前

2 条评论

shele大约 6 年前
This brings a wide spectrum of the Julia stack together and underlines the inherent interoperability of Julia solutions:<p>Flux - Elegant Machine Learning Stack<p>Makie - High level plotting on the GPU<p>CuArrays - GPU arrays without code changes<p>WebSockets - Websockets protocol in Julia<p>WebIO - Simple abstraction for displaying and interacting with content<p>Nextjournal - Making this reproducible online
anshuligh大约 6 年前
Cool article!<p>In Makie, you can efficiently put a label on a slider by using<p>`sliderplot, observable = AbstractPlotting.textslider(range, label, start = startvalue)`<p>where sliderplot is the actual Scene object and observable is the value of the observable.