| import pandas as pd | |
| import numpy as np | |
| import seaborn as sns | |
| from keras.layers import Dense | |
| from keras.models import Model, Sequential | |
| from keras import initializers | |
| ## ---------- Create our linear dataset --------------- | |
| ## Set the mean, standard deviation, and size of the dataset, respectively |
| # build your encoder upto here. It can simply be a series of dense layers, a convolutional network | |
| # or even an LSTM decoder. Once made, flatten out the final layer of the encoder, call it hidden. | |
| # we use Keras to build the graph | |
| latent_size = 5 | |
| mean = Dense(latent_size)(hidden) | |
| # we usually don't directly compute the stddev σ | |
| # but the log of the stddev instead, which is log(σ) |
| #-------------------------- | |
| # USER-SPECIFIED DATA | |
| #-------------------------- | |
| # Tune these parameters | |
| num_classes = 2 | |
| image_shape = (160, 576) | |
| EPOCHS = 40 | |
| BATCH_SIZE = 16 |
The application is a simulation of a toy robot moving on a square tabletop, of dimensions 5 units x 5 units.
There are no other obstructions on the table surface.
The robot is free to roam around the surface of the table, but must be prevented from falling to destruction. Any movement that would result in the robot falling from the table must be prevented, however further valid movement commands must still be allowed.