Don't get burned with common torch training errors
Project description
Mitts
- TorchedHops - great beer ML name
- Mitts
- Torch oopsie
- Fire safety
- Smoke alarm
Goal: Prevent “oopsies” with PyTorch
Examples
- All of an input or output are the same (or missing)
- Gradients aren’t updating
- Inputs aren’t normalized
- Vanishing/Exploding gradient?
- Training/Test Overlap
To Deploy python3 -m build python3 -m twine upload dist/*
Release history Release notifications | RSS feed
Download files
Download the file for your platform. If you're not sure which to choose, learn more about installing packages.
Source Distribution
mitts-0.0.1.tar.gz
(2.5 kB
view details)
Built Distribution
mitts-0.0.1-py3-none-any.whl
(2.5 kB
view details)
File details
Details for the file mitts-0.0.1.tar.gz.
File metadata
- Download URL: mitts-0.0.1.tar.gz
- Upload date:
- Size: 2.5 kB
- Tags: Source
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.1 CPython/3.8.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 6414243c5076fd937a8e22da813836da3f8eaeedce74d2724c7743d6aac20815 |
|
| MD5 | ed20ee238a7b0a18e15fe4eb6e1f593d |
|
| BLAKE2b-256 | 686c93670353249ad13ab54c4e885927eb5a72a97d5eb173e0d8dc1df50e9855 |
File details
Details for the file mitts-0.0.1-py3-none-any.whl.
File metadata
- Download URL: mitts-0.0.1-py3-none-any.whl
- Upload date:
- Size: 2.5 kB
- Tags: Python 3
- Uploaded using Trusted Publishing? No
- Uploaded via: twine/4.0.1 CPython/3.8.9
File hashes
| Algorithm | Hash digest | |
|---|---|---|
| SHA256 | 3c80c8368fb48925b0b0e48fe8c98280fae3100dd7eadd1cac7837ee60c7da79 |
|
| MD5 | 400370fa1fe5dbafd25719febaf10b47 |
|
| BLAKE2b-256 | 30cab750d088033526946b2133b7815195efad2ba7bb8fb1a8dc8b40c75402fd |
