Cong
Print checkpoint and example file names when saving and loading them. including #126
I propose using `docker-compose` instead of `setup_env.sh` since - the format is clean - it's easier to build, start, pause, restart the container - it's easier to customize the container's...
Hi, I'm trying PPLM with XLNet instead of GPT-2 and encountered errors regarding the output format. It seems that the GPT-2 model has 3 output values, but the XLNet model...
Have you compared word2vec and fastText? The README should give some hints about the comparison.
``` Error detected while processing function leetcode#ListProblems: line 30: E121: Undefined variable: s:topics_and_companies E15: Invalid expression: s:topics_and_companies['topics'] ```
Including - #121 - #239 - Add pass_id and task in flags to train.py - Add flag n_token (vocabulary size) to data_utils.py
I ran `train.py` on a TPU pod v3-256 and got the following error: ValueError: TPUConfig.num_shards is not set correctly .... Found in https://cloud.google.com/tpu/docs/training-on-tpu-pods#providing_the_tpu_name_and_region_to_tpuclusterresolver that > For single device training, you...
Hi, I want to try DeepDive with Japanese. Unfortunately, CoreNLP does not suport the language. Can you please give me some advice. Should I use another NLP preprosessor (MeCab or...
Thank you for the library! I have some questions about differences between DeepDive docker images. It looks like that there are 2 kinds of DeepDive docker images in the repository....
[将棋AIで学ぶディープラーニング Kindle版]( https://www.amazon.co.jp/gp/product/B07B7JJ929?ref=dbs_p2d_P_R_popup_yes_alc_T1) に従って、Google Colabでモデルをtrainしています。 https://gist.github.com/vochicong/01bf7709d89816efb7613536969cb072 Colabでは、棋譜データを pickle に保存しようとしているところで何回もフリーズしてしまったので、その部分だけ別の環境（ローカルPCやGCP）で実行できるように切り出しました。