← Înapoi la Urmăritori

Cel mai recent articol

Ultima verificare

Urmăritori 0 urmăritori
Articole: 20
  1. A Decade of CVPR

    2016 年是我第一次参加 CVPR.

  2. In Python, when a set of objects constructs a reference cycle, none of them would reach a zero refcount.In this case, even if these objects all go out-of-scope and are no longer accessible, they will not be immediately released.

  3. 在过年的这几天, 为了从焦虑的工作中换一个心情, 我给我的 wechat-dump 项目添加了几个当年没做出来的功能, 解决了一些遗留问题.

  4. Meta 与 Google 内部的代码管理工具都支持一种被称作 "stacked diffs / stacked PRs" 的 workflow.

  5. People have many different opinions about config systems.

  6. Since I joined Google Brain, I brought PyTorch to Google's internal infra andowned its maintenance.

  7. 最近学习到了一些 Terminal Escape Sequences, 其中尤其对 OSC52 相见恨晚.

  8. A typical PyTorch training program on 8 GPUs with 4 dataloaderworkers per GPU would create at least processes.A naive use of PyTorch dataset and dataloader can easilyreplicate your dataset's RAM usage by 40 times.

  9. "Loss function" is one of the most basic concepts today in deep learning.Despite that,it is actually not necessarily a good programming abstraction whendesigning general-purpose systems.

  10. Building a library for research and experiments is quite different from building other types of software.A key challenge is that, in research, abstractions and APIs are rarely set in stone:users may want to propose a slight variant or modification to lite…

  11. This post is about a small functionality that is found useful in TensorFlow / JAX / PyTorch.

  12. PyTorch provides two methods to turn an nn.Module into agraph represented in TorchScript format: tracing and scripting.This article will: Compare their pros and cons, with a focus on useful tips for tracing.

  13. 本系列文章 谈谈 Github 上如何交流 (1) 如何科学的报 bug 如何管理 issue {Feature,Pull} Request 这篇文章说说用户怎么提出好的 feature request / pull request, 以及维护者如何对待它们.

  14. 本系列文章 谈谈 Github 上如何交流 (1) 如何科学的报 bug 如何管理 issue {Feature,Pull} Request 我听过不少人凭借爱好开源了自己的项目后, 却对 issue 太乱感到困扰, 甚至想干脆直接禁用 issue.

  15. 本系列文章 谈谈 Github 上如何交流 (1) 如何科学的报 bug 如何管理 issue {Feature,Pull} Request 报告错误 / 报 bug 是用户与开发者间最常见的一类交流, 也是常见的 github issue.

  16. 本系列文章 谈谈 Github 上如何交流 (1) 如何科学的报 bug 如何管理 issue {Feature,Pull} Request 相比传统的邮件列表 / bugzilla/sourceforge 等开源平台, github 把开源社区交流的成本 / 门槛降的很低, 因此交流的质量也常常随之下降.

  17. In large systems, logs can be terrifying: they are huge in volume, and hard to understand.This note lists some suggestions and common misuse of Python's logging module,with the aim of: Reduce redundant logs & spams from libraries.

  18. 本系列文章 Deep Learning Experiments and Claims How To Do Ablation Experiments 延续 上一篇文章, 再说一说怎么科学的在 paper 里做 ablations.

  19. Technically, an image is a function that maps a continuous domain, e.g.a box , to intensities such as (R, G, B).To store it on computer memory, an image is discretized to an array array[H][W], where each elementarray[i][j] is a pixel.

  20. 本系列文章 Deep Learning Experiments and Claims How To Do Ablation Experiments 这几年来, 从 FAIR 的几位大佬身边学习到的最多的是对待 research 的态度.