From f473456c19558aaf8552df97a51d4e18cc69dfa8 Mon Sep 17 00:00:00 2001 From: aktersnurra Date: Wed, 22 Jul 2020 23:18:08 +0200 Subject: Working training loop and testing of trained CharacterModel. --- README.md | 24 ++++++++++++++++++++---- 1 file changed, 20 insertions(+), 4 deletions(-) (limited to 'README.md') diff --git a/README.md b/README.md index 848e266..be6576e 100644 --- a/README.md +++ b/README.md @@ -8,8 +8,24 @@ TBC ## Todo - [x] subsampling -- [ ] Be able to run experiments -- [ ] Train models -- [ ] Implement wandb -- [ ] Implement Bayesian hyperparameter search +- [x] Be able to run experiments +- [x] Train models +- [x] Fix input size in base model +- [x] Fix s.t. the best weights are saved +- [x] Implement total training time +- [x] Fix tqdm and logging output +- [x] Fix basic test to load model +- [x] Fix loading previous experiments +- [ ] Check how to pass arguments to unittest (remove B009 then) +- [x] Able to set verbosity level on the logger to terminal output +- [ ] Implement Callbacks for training + - [ ] Implement early stopping + - [ ] Implement wandb + - [ ] Implement lr scheduler as a callback +- [ ] Continuing reimplementing labs - [ ] New models and datasets +- [ ] Check that dataset exists, otherwise download it form the web. Do this in run_experiment.py. +- [ ] Create repr func for data loaders +- [ ] Be able to restart with lr scheduler +- [ ] Implement Bayesian hyperparameter search +- [ ] Try to fix shell cmd security issues S404, S602 -- cgit v1.2.3-70-g09d2