-
Feature issue/branch for the implementation of the Harris et al WGAN into the benchmark framework.
-
Hello,
thank you for your implementation. I'm the author of one of the point transformer methods. I'm wondering why your results differ that much from the reported results in our paper.
One thin…
-
Nice work！Thanks for your released code.
I have a question regarding conducting experiments on the `Barn` scene of the `Tanks` dataset using the default.yaml file, I found that the results were wor…
-
h/t @qxcv
`AdversarialTrainer.train()` will repeatedly call `PPO.learn(total_timesteps=gen_batch_size, reset_num_timesteps=False)` where `gen_batch_size` is usually a small number compared to conv…
-
There's no training code included in the repo, so it's hard to tell exactly how the training was done.
The paper states:
"We use the Pile dataset (L. Gao, Biderman, et al. 2020), and follow the tr…
-
Currently, I have added only two priorities to the library — `background` and `user-visible`. I feel this won't be enough. However, I can't imagine all the use cases the library will be used in. This …
-
I saw that this repo has added the ability to use a validation loss to help figure out the optimal amount of training. Might be an interesting addition.
https://github.com/victorchall/EveryDream2tr…
-
## Why
Machine Learning 輪講は最新の技術や論文を追うことで、エンジニアが「技術で解決できること」のレベルをあげていくことを目的にした会です。
prev. #14
## What
話したいことがある人はここにコメントしましょう！
面白いものを見つけた時点でとりあえず話すという宣言だけでもしましょう！
-
您好，我复现了您的代码，为什么和论文中的结果差距很大，甚至说模型就是无效的，我没有改动您的代码，直接运行的
以下是 CGBERT模型epoch = 29的结果
> `05/07/2021 01:46:20 - INFO - util.train_helper - epoch = 29████████████████████████████▌| 312/314 [00:05
> …
-
### intro
- [x] log consent time
- [x] log elapsed time in training
- [ ] log number of training attempts
- [ ] log individuals who quit partway through training
### stimulus/response task
- […