# Eddie's Learning Record 33

**Published by:** [Eddie's Learning Records](https://paragraph.com/@eddiehe/)
**Published on:** 2023-02-13
**URL:** https://paragraph.com/@eddiehe/eddies-learning-record-33

## Content

1. DurationMonday, February 6th, 2023 - Saturday, February 11th, 2023 2. Learning Records2.1 Refactor for PyTorchRefactor the code using PyTorch. But it outputs terrible results. I spent two days debugging trying different epochs and batch_size. Finally, I found the validation dataset takes X_train and X_test as inputs, which is the reason for the bad outcomes. 2.2 Build ModelsBuild swin transformer and sl swin transformer using PyTorch. 2.3 Fix the Accuracy CalculationThe calculation is not suitable for the output of one dimension. Just fixed it. 2.4 Record the ResultsFinish one macro expression spotting experiment, which cost 44 hours. At least the result is not bad. I hope I could get better outcomes through some fine-tuning. 3. Feeling3.1 Perplexed44 hours for one experiment. What can I do?

## Publication Information

- [Eddie's Learning Records](https://paragraph.com/@eddiehe/): Publication homepage
- [All Posts](https://paragraph.com/@eddiehe/): More posts from this publication
- [RSS Feed](https://api.paragraph.com/blogs/rss/@eddiehe): Subscribe to updates
- [Twitter](https://twitter.com/eddiehe99): Follow on Twitter

## Optional

- [Collect as NFT](https://paragraph.com/@eddiehe/eddies-learning-record-33): Support the author by collecting this post
- [View Collectors](https://paragraph.com/@eddiehe/eddies-learning-record-33/collectors): See who has collected this post