README.md

@@ -2,83 +2,13 @@
 
 > Predicting film genres from their posters with Tensorflow.js
 
-## Dataset
-The dataset used with this demo can be found here:
 
-https://nextcloud.starbeamrainbowlabs.com/index.php/s/wmCdL4tX3HHGAFD
+To use:
-
-The format is as follows:
-
-```
-+ dataset_dir/
-	+ train/
-		+ 1234,Comedy,Fantasy.jpg
-		+ 4321,Western,Short,Drama.jpg
-		+ .....
-	+ validate/
-		+ 6789,Drama,Mystery,Thriller.jpg
-		+ 9876,History,Documentary,Animation.jpg
-		+ .....
-```
-
-The filenames of the images take the following format: `ID,GENRE_1,GENRE_2,GENRE_N.jpg`.
-
-## System / User Requirements
- - [Node.js](https://nodejs.org/)
- - [NPM](https://www.npmjs.com/) (installed by default with Node.js)
- - A relatively decent CPU
- - Basic knowledge of the command-line / terminal
-
- 
-## Installation
-First, clone this git repo:
 
 ```bash
-git clone https://git.starbeamrainbowlabs.com/Demos/film-poster-genres.git
+node src/index.mjs train --input datasets/posters-256/ --output output/
-cd film-poster-genres
+node src/index.mjs predict --input datasets/posters-256/validate/25410,Comedy,Family,Drama.jpg --ai-model output/checkpoints/49 2>/dev/null
-```
-
-Then, install the dependencies:
-
-```bash
-npm install
-```
-
-## Usage
-
-### Training
-To train a new model:
-
-```bash
-node src/index.mjs train --input path/to/dataset_dir --output path/to/output_dir
-```
-
-The output directory will look like this:
-
-```
- + output_dir/
-	+ metrics.stream.json
-	+ checkpoints/
-		+ 0/
-		+ 1/
-		+ 2/
-		+ 3/
 ```
 
 
-## Predicting
+TODO: Fill out this README (and maybe move it to GitHub & make this repo a clone)
-To make a prediction using an existing model:
-
-```bash
-node src/index.mjs predict --input path/to/image.jpg --ai-model path/to/checkpoint_dir/
-```
-
-The result will be written to the standard output. Extra debugging data is written to the standard error, but this can be ignored.
-
-
-## Contributing
-Contributions are very welcome! Git patches are preferred - I can move this repo to GitHub if that makes it easier. Please mention in your contribution that you release your work under the MPL-2.0 (see below).
-
-
-## Licence
-This code is released under the Mozilla Public License 2.0. The full license text is included in the `LICENSE` file in this repository. Tldr legal have a [great summary](https://tldrlegal.com/license/mozilla-public-license-2.0-(mpl-2)) of the license if you're interested.

src/lib/FilmPredictor.mjs

@@ -4,8 +4,6 @@ import path from 'path';
 import fs from 'fs';
 
 import tf from '@tensorflow/tfjs-node';
-// import tf from '@tensorflow/tfjs-node-gpu';
-// import tf from '@tensorflow/tfjs';
 
 import genres from './Genres.mjs';
 

src/lib/Genres.mjs

@@ -1,9 +1,9 @@
 "use strict";
 
 export default [
-	"Action",		// 0
+	"Action",
-	"Adventure",	// 1
+	"Adventure",
-	"Animation",	// 2
+	"Animation",
 	"Biography",
 	"Comedy",
 	"Crime",
@@ -23,5 +23,5 @@ export default [
 	"Sport",
 	"Thriller",
 	"War",
-	"Western"		// 22
+	"Western"
 ];