SkalskiP

# Auxiliary function creating graph of classification boundaries
def save_model_prediction_graph(epoch, logs):
    prediction_probs = model.predict_proba(grid_2d, batch_size=32, verbose=0)
    plt.figure(figsize=(10,10))
    sns.set_style("whitegrid")
    plt.title('Binary classification with KERAS - epoch: ' + makeIndexOfLength(epoch, 3), fontsize=20)
    plt.xlabel('X', fontsize=15)
    plt.ylabel('Y', fontsize=15)
    plt.contourf(X, Y, prediction_probs.reshape(100, 100), alpha = 0.7, cmap=cm.Spectral)
    plt.scatter(X_train[:, 0], X_train[:, 1], c=y_train.ravel(), s=50, cmap=plt.cm.Spectral, edgecolors='black')

SkalskiP

convert -delay 10 -loop 0 *.png keras_class_boundaries.gif

SkalskiP

# Animation creation
anim = FuncAnimation(fig, update, 
    frames=np.arange(0, int(STEPS/STEPS_PER_FRAME)), interval=40)
# Saving animation
anim.save('lorenz_attractor.gif', dpi=80, writer='imagemagick')

SkalskiP

# Updating chart
def update(i):
    frame_end = (i + 1) * STEPS_PER_FRAME
    for plot, dot, data in zip(plots, dots, plots_data):
        xs, ys, zs = data
        # Updating the trajectory
        plot.set_data(xs[:frame_end], ys[:frame_end])
        plot.set_3d_properties(zs[:frame_end])
        # Updating the position of dots
        dot._offsets3d = ([xs[frame_end]], [ys[frame_end]], [zs[frame_end]])

SkalskiP

# Calculation of the points belonging to the three trajectories, 
# based on the given starting conditions
plots_data = [build_lorenz_trajectory(DELTA_T, STEPS, 
    initial_values=initial_conditions[i]) for i in range(3)]

# Creation of an empty chart
fig, ax = create_blank_chart_with_styling(plots_data, PADDING, (8, 8))

# Setting up (for the time being empty) data sequences for each trajectory
plots = [ax.plot([],[],[], color=colors[i], label=str(initial_conditions[i]),

SkalskiP

import numpy as np
import matplotlib.pyplot as plt
from mpl_toolkits.mplot3d import Axes3D
import numpy as np
from matplotlib.animation import FuncAnimation

SkalskiP

def create_frames(dt, steps, padding, output_dir):
    fig, ax = create_blank_chart_with_styling((6, 6))
    # creation of data describing the trajectory 
    xs, ys, zs = build_lorenz_trajectory(dt, steps)
    # setting the fixed range of axes
    ax.set_xlim3d(xs.min() - padding, xs.max() + padding)
    ax.set_ylim3d(ys.min() - padding, ys.max() + padding)
    ax.set_zlim3d(zs.min() - padding, zs.max() + padding)

    for i in range(steps-1):

SkalskiP

from keras.models import Sequential
from keras.layers import Dense

model = Sequential()
model.add(Dense(4, input_dim=2,activation='relu'))
model.add(Dense(6, activation='relu'))
model.add(Dense(6, activation='relu'))
model.add(Dense(4, activation='relu'))
model.add(Dense(1, activation='sigmoid'))

SkalskiP

model.add(Conv2D(
    filters = 32, 
    kernel_size = (5,5),
    padding = 'Same', 
    activation ='relu',
    input_shape = (28,28,1)
))

SkalskiP

<script src="https://cdn.jsdelivr.net/npm/@tensorflow/[email protected]"> </script>