Mu Li
Mu Li
A few minor API tweaks, which I believe to improve usability. I'd like to add it to the 0.6 milestone, but not necessary to address all by the release. I'll...
## Background Most d2l chapters follows the data/network/loss/training/prediction structure. Codes are reused by saving into the d2l package. However, APIs are not consistent and some functions have a lot of...
Hi 各位， 感谢将D2L翻译到TensorFlow。目前我们在着手在d2l.ai的英文版里面加入tensorflow和pytorch的实现。现在的pytorch版的一个demo在http://pytorch.d2l.ai.s3-website-us-west-2.amazonaws.com/chapter_preface/index.html 和 http://pytorch.d2l.ai.s3-website-us-west-2.amazonaws.com/chapter_linear-networks/linear-regression-scratch.html，代码在 https://github.com/d2l-ai/d2l-en/tree/pytorch 不知道你有没有兴趣来贡献tensorflow的实现。 （我之前发过信到各位的pku邮箱，各位可能没注意）
Very interesting work! I’m wonder if you are interested in reimplement the symbol codes in gluon and contribute into gluoncv https://gluon-cv.mxnet.io ?
hi guys, probably it's due to my driver problem. i found sometimes it's extremely slow to get the message such as "finish initialization with 2 devices" for example, it takes...
hi guys, is it possible to write the net configure into models, so that a user doesn't need to specify the model in the prediction conf file? for example, save...
hi guys, is it possible to having xavier in the server node? https://github.com/dmlc/cxxnet/blob/master/src/nnet/nnet_ps_server.cpp#L127 currently a server nodes can get the same args as workers, it would be like if a...
we are still working on porting the codes from https://github.com/dmlc/wormhole/tree/master/learn/difacto and also adding new learning algorithms: - [x] logit / fm loss: `src/loss/` - [x] minibatch sgd: `src/sgd/` - [x]...
the notebooks should be grouped into three levels - for beginners: basic usages for how to define (symbol) and train (module) a neural network. - for power users: more mechanisms,...
- [x] APA style bib with natbib enabled - [ ] Support runtime - [x] colab, - [ ] mybinder - [ ] ThebeLab - [x] sagemaker - [ ]...