https://github.com/eivindarvesen/transfer-learning-demo
Short demo of transfer learning with Inception v3 and TensorFlow
https://github.com/eivindarvesen/transfer-learning-demo
deep-learning demo inception machine-learning neural-network notebook python tensorflow transfer-learning
Last synced: 7 months ago
JSON representation
Short demo of transfer learning with Inception v3 and TensorFlow
- Host: GitHub
- URL: https://github.com/eivindarvesen/transfer-learning-demo
- Owner: EivindArvesen
- Created: 2017-10-18T10:36:09.000Z (about 8 years ago)
- Default Branch: master
- Last Pushed: 2017-11-16T13:35:31.000Z (almost 8 years ago)
- Last Synced: 2025-01-17T15:52:42.988Z (9 months ago)
- Topics: deep-learning, demo, inception, machine-learning, neural-network, notebook, python, tensorflow, transfer-learning
- Language: Jupyter Notebook
- Size: 3.14 MB
- Stars: 1
- Watchers: 3
- Forks: 0
- Open Issues: 0
-
Metadata Files:
- Readme: README.md
Awesome Lists containing this project
README
# Transfer Learning Demo
This repo contains a demo of transfer-learning using Inception v3 and TensorFlow in a Jupyter notebook.
Much of the material is based on Google's Codelab [TensorFlow for Poets](https://codelabs.developers.google.com/codelabs/tensorflow-for-poets)
** If you don't want to set up the project dependencies yourself**, you can view results used in a [presentation](Presentasjon.pdf), with different humanoid species of the Star Trek universe [here](https://github.com/eivind88/transfer-learning-demo/blob/master/Transfer-Learning.ipynb).
## Setup
Clone this repo via
```bash
git clone --recursive git://github.com/foo/bar.git
```or if you've already downloaded it, you *need* to init submodules manually:
```bash
cd
git submodule update --init --recursive
```### Python distribution
Install the [Miniconda](https://conda.io/miniconda.html) (or [Anaconda](https://www.anaconda.com/download/#macos)) Python distribution.
The code has been tested on Python 2.Set up conda environment via `conda env create -n transfer-learning -f environment.yml`
### Dataset
The dataset-folder contains two folders:
"Train" should contain subfolders named after the class of images they contain;
"Test" should contain test images from multiple classes (not present in the training data).You will need to build your dataset;
I just used [Fatkun Batch Download Image](https://chrome.google.com/webstore/detail/fatkun-batch-download-ima/nnjjahlikiabnchcpehcpkdeckfgnohf?hl=en) to handle batch downloading from Google image search results.
## Run
Run the notebook:
```bash
# Activate our Python environment
source activate transfer-learning# Start Jupyter and open the notebook
jupyter notebook
```