Deep Learning - Just do it!
see also: /dl-theory
Data #
Tutorials #
- 图像分类任务中的 tricks 总结 (bak)
- 邱锡鹏 教授 2020 神经网络与深度学习
Keywords: CNN, RNN, Attention, Gaussian Mix., RBM, DBN, GAN, RL, TF, PyTorch: equation, pseudocode, exercise …
PDF, PPT, code, exercise & solution, etc. - A collection of various DL deep learning architectures, models, and tips for TensorFlow and PyTorch in Jupyter Notebooks 2019
- 《TensorFlow 2.0 深度学习算法实战 2019》 (pdf version via Python 数据科学)
- ICCV 2019 教程: DL SOTA by MXNET & GluonCV, [github] [cn intor]
- CS294-158 Deep Unsupervised Learning, 14 weeks, slides & youtube, Spring 2019 (overview in CN)
- fast.ai: Cutting Edge Deep Learning For Coders, Part 2 (requires 70 hours)
- Computer Vision Tutorial: Implementing Mask R-CNN for Image Segmentation (with Python Code) (bak) (keywords: Mask RCNN)
- 李沐《动手学深度学习》PyTorch 版开源,瞬间登上 GitHub 热榜!
- AI 研习社「论文」全新域名正式上线 https://paper.yanxishe.com/,功能升级只为热爱学习的你(提供论文复现环境和一站式论文生产管理平台)
- 到底每层每层网络是怎么工作的?下面这些简化图相信可以帮你理清不少思路。
- 实践经验: 深度学习的一些经验总结和建议 | To do v.s Not To Do (bak)
- 一份来自英伟达的越南小姐姐整理的机器学习入门清单 2019.08
- Wandb 用起来,一行 Python 代码实现 Keras 模型可视化 2019.08
News & Tech #
- 性能媲美 BERT,但参数量仅为 1/300,这是谷歌最新的 NLP 模型 PRADO 2020.10.1
- Benchmarking Graph Neural Networks 2020.03
- Two Minute Papers
- 要啥给啥的写作 AI:新闻评论小说都能编,题材风格随便选,真假难辨,16 亿参数模型已开源 CTRL, not GPT-2
- FastBert — A simple Deep Learning library for BERT Models (can run in one GPU) (see also TinyBert in
/dl-theory
)
Ready to Use Software #
- 语音伪装神器,让你跟马云称兄道弟
- super resolution - 二次元图片无损拉伸 waifu2x
- 要啥给啥的写作 AI:新闻评论小说都能编,题材风格随便选,真假难辨,16 亿参数模型已开源: OpenAI 横空出世的 GPT-2
GPU #
Which GPU(s) to Get for Deep Learning: My Experience and Advice for Using GPUs in Deep Learning 2020-09-07 (cn)
...