RileyLazarou

def main():
    from time import time
    epochs = 600
    batches = 10
    generator = Generator(1)
    discriminator = Discriminator(1, [64, 32, 1])
    noise_fn = lambda x: torch.rand((x, 1), device='cpu')
    data_fn = lambda x: torch.randn((x, 1), device='cpu')
    gan = VanillaGAN(generator, discriminator, noise_fn, data_fn, device='cpu')
    loss_g, loss_d_real, loss_d_fake = [], [], []

RileyLazarou

class VanillaGAN():
    def __init__(self, generator, discriminator, noise_fn, data_fn,
                 batch_size=32, device='cpu', lr_d=1e-3, lr_g=2e-4):
        """A GAN class for holding and training a generator and discriminator

        Args:
            generator: a Ganerator network
            discriminator: A Discriminator network
            noise_fn: function f(num: int) -> pytorch tensor, (latent vectors)
            data_fn: function f(num: int) -> pytorch tensor, (real samples)

RileyLazarou

class Discriminator(nn.Module):
    def __init__(self, input_dim, layers):
        """A discriminator for discerning real from generated samples.

        params:
            input_dim (int): width of the input
            layers (List[int]): A list of layer widths including output width

        Output activation is Sigmoid.
        """

RileyLazarou

class Generator(nn.Module):
    def __init__(self, latent_dim, output_activation=None):
        """A generator for mapping a latent space to a sample space.

        Args:
            latent_dim (int): latent dimension ("noise vector")
            layers (List[int]): A list of layer widths including output width
            output_activation: torch activation function or None
        """
        super(Generator, self).__init__()

RileyLazarou

import numpy as np
from tensorflow.keras.layers import Input, Dense, BatchNormalization, Activation, LeakyReLU
from tensorflow.keras.models import Model
from tensorflow.keras.optimizers import Adam
import tensorflow as tf
import matplotlib.pyplot as plt

def build_G(batchnorm_momentum=0.9):
    input_layer = Input(shape=(2,))
    for i in range(4):

RileyLazarou

# Set up the environment and collect the observation space and action space sizes
env = gym.make("CartPole-v1")
observation_space = env.observation_space.shape[0]
action_space = env.action_space.n

# The function for creating the initial population
organism_creator = lambda : Organism([observation_space, 16, 16, 16, action_space], output='softmax')

def simulate_and_evaluate(organism, trials=1):
    """

RileyLazarou

# Load the data
df = pd.read_csv('iris.csv')
# Enumerate the classes
unique_classes = sorted(list(set(df['variety'])))
class_number = {y : x for x,y in enumerate(unique_classes)}
df['variety'] = [class_number[x] for x in df['variety']]
# Convert to numpy array and standardize the features
data_X = df[['sepal.length', 'sepal.width', 'petal.length', 'petal.width']].values
data_Y = df[['variety']].values
data_X = data_X - np.min(data_X, axis=0)

RileyLazarou

# The function to create the initial population
organism_creator = lambda : Organism([1, 16, 16, 16, 1], output='linear')
# The function we are trying to learn. numpy doesn't have tau...
true_function = lambda x : np.sin(2 * np.pi * x) #
# The loss function, mean squared error, will serve as the negative fitness
loss_function = lambda y_true, y_estimate : np.mean((y_true - y_estimate)**2)

def simulate_and_evaluate(organism, replicates=1):
    """
    Randomly generate `replicates` samples in [0,1],

RileyLazarou

import copy

import numpy as np

class Organism():
    def __init__(self, dimensions, use_bias=True, output='softmax'):
        self.layers = []
        self.biases = []
        self.use_bias = use_bias
        self.output = self._activation(output)

RileyLazarou

class Organism():
    # [Some code removed here]
    
    def mutate(self, stdev=0.03):
        for i in range(len(self.layers)):
            self.layers[i] += np.random.normal(0, stdev, self.layers[i].shape)
            if self.use_bias:
                self.biases[i] += np.random.normal(0, stdev, self.biases[i].shape)