https://github.com/spandan-madan/pytorch_fine_tuning_tutorial
A short tutorial on performing fine tuning or transfer learning in PyTorch.
https://github.com/spandan-madan/pytorch_fine_tuning_tutorial
deep-learning image-classification pytorch-tutorials tutorial
Last synced: 6 months ago
JSON representation
A short tutorial on performing fine tuning or transfer learning in PyTorch.
- Host: GitHub
- URL: https://github.com/spandan-madan/pytorch_fine_tuning_tutorial
- Owner: Spandan-Madan
- Created: 2017-08-23T02:38:50.000Z (about 8 years ago)
- Default Branch: master
- Last Pushed: 2018-09-14T06:46:06.000Z (about 7 years ago)
- Last Synced: 2025-04-13T08:17:45.137Z (6 months ago)
- Topics: deep-learning, image-classification, pytorch-tutorials, tutorial
- Language: Python
- Homepage:
- Size: 88 MB
- Stars: 281
- Watchers: 11
- Forks: 63
- Open Issues: 5
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README


# Pytorch Tutorial for Fine Tuning/Transfer Learning a Resnet for Image Classification
If you want to do image classification by fine tuning a pretrained mdoel, this is a tutorial will help you out. It shows how to perform fine tuning or transfer learning in PyTorch with your own data. It is based on a bunch of of official pytorch tutorials/examples. I felt that it was not exactly super trivial to perform in PyTorch, and so I thought I'd release my code as a tutorial which I wrote originally for my research.
Highly encourage you to run this on a new data set (read main_fine_tuning.py to know which format to store your data in), but for a sample dataset to start with, you can download a simple 2 class dataset from here - https://download.pytorch.org/tutorial/hymenoptera_data.zip
All Torch and PyTorch specific details have been explained in detail in the file main_fine_tuning.py
Hope this tutorial helps you out! :)
Credits - This tutorial is built on top of mainly on 2 Pytorch tutorials - http://pytorch.org/tutorials/beginner/transfer_learning_tutorial.html and https://github.com/pytorch/examples/tree/master/imagenet.