Rachel Hu comments

Results 7 comments of


                                            Rachel Hu

translate chapter_appendix-mathematics-for-deep-learning/geometry-linear-algebraic-ops

Hey @xinetzone ! Thanks for the hard work. Could you split this PR to smaller PRs? (i.e. each notebook per PR) That will be easier to review and merge.

translate chapter_appendix-mathematics-for-deep-learning/index.md

Could you only include the `index.md` file for this PR? Thanks!

Why AddNorm() in the Transformer 9.3.3 (line: `self.norm(self.dropout(Y) + X)` ) is different from the Original one (line :` x + self.dropout(sublayer(self.norm(x))) ` ) ?

Hey @kaharjan ! If we carefully read the paper (https://arxiv.org/abs/1706.03762), in section 3.1, it states "We employ a residual connection around each of the two sub-layers, followed by layer normalization"....

Inconsistent learning curves of two NiN trainings

Hi @cuongvng ,can you try to the change the `force_reinit = True` to False at `train_ch6` https://github.com/d2l-ai/d2l-en/blob/4b0ea4bf1821049fa4a044c88fa6e0ec52a0630d/d2l/mxnet.py#L417? I tried with running 7 times and they all work well.

80页排版错误

Hey @PhenixZhang , thanks for raising the issue. I believe this is a formatting issue and need further investigation.

Blocked after typing the wandb options

OOM error with 8*A100 40G... :(

use python 3.9 to 3.11 multiple versions

Thanks for the PR and it looks like it has some compatibility issues with python 3.12 based on the log [here](https://github.com/CambioML/pykoi/actions/runs/6456750661/job/17718081026).