Skip to content

Commit 3c84e86

Browse files
committed
file renames
1 parent 6c6e396 commit 3c84e86

File tree

14 files changed

+8
-4
lines changed

14 files changed

+8
-4
lines changed
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.
File renamed without changes.

README.md

+8-4
Original file line numberDiff line numberDiff line change
@@ -1,19 +1,23 @@
1-
# tensorflow.js Examples
2-
1+
# TensorFlow.js Examples
32

43
## XOR vanilla neural network
54

65
## Doodle Classifier
76
This repo is experimental and in progress. It is an "MNIST"-style classification example using the [Google QuickDraw dataset](https://quickdraw.withgoogle.com/data), [p5js](https://p5js.org/), and [tensorflow.js](https://js.tensorflow.org). It is loosely based on the [tfjs MNIST example](https://github.com/tensorflow/tfjs-examples/tree/master/mnist).
87

9-
## Reference
8+
### Reference
109
* [JS Doodle Classifier video tutorials](https://www.youtube.com/watch?v=pqY_Tn2SIVA&list=PLRqwX-V7Uu6Zs14zKVuTuit6jApJgoYZQ)
1110
* [ml4a ofx Doodle Classifier](https://ml4a.github.io/guides/DoodleClassifier/)
1211

13-
## RoadMap
12+
### RoadMap
1413
* [ ] Simplify model removing convolutional layers. The idea is for this to be a dropdead simple example that I can use to explain tensorflow.js and the layers API. I'd like to cover convolutional neural networks as a secondary example.
1514
* [ ] Incorporate testing data. At the moment [no any validation / testing data](https://github.com/shiffman/Tensorflow-JS-Doodle-Classifier/blob/master/classifier.js#L53) is included during training. For clarity of the example I might like to run the testing as a separate function. What do the results mean me if I give it `null` data?
1615
* [ ] Guess user drawings in real-time.
1716
* [ ] Train with a much larger dataset.
1817
* [ ] Save model using local storage or to JSON file.
1918
* [ ] Bring the idea of a higher level `Classifier` class that wraps keras layers into [ml5](https://ml5js.github.io/).
19+
20+
### Neuro-Evolution
21+
* [Flappy Bird Demo: Learning](https://shiffman.github.io/Tensorflow-JS-Examples/04_neuro_evolution_flappy/)
22+
* [Flappy Bird Demo: Loading Saved Model](https://shiffman.github.io/Tensorflow-JS-Examples/04_neuro_load_flappy/)
23+
* [Steering Ecosystem Simulation Demo](https://shiffman.github.io/Tensorflow-JS-Examples/04_neuro_evolution_steering/)

0 commit comments

Comments
 (0)