Created
October 28, 2017 22:23
-
-
Save anonymous/c816eb15daf949543e96dd2c64174670 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
from keras.models import Sequential | |
from keras.layers import Dense | |
import numpy | |
import sklearn.datasets | |
import matplotlib | |
matplotlib.use("TkAgg") | |
import matplotlib.pyplot as plt | |
numpy.random.seed(7) | |
# ----------------------------------------------------------------------------- | |
# generate sinus. | |
# ----------------------------------------------------------------------------- | |
T = 1000 | |
X = numpy.array(range(T)) | |
Y = numpy.sin(3.5 * numpy.pi * X / T) | |
# ----------------------------------------------------------------------------- | |
# Draw training data | |
# ----------------------------------------------------------------------------- | |
plt.scatter(X, Y, s = 10) | |
plt.show() | |
# ----------------------------------------------------------------------------- | |
# Build Keras model (my keras uses TensorFlow backend) | |
# ----------------------------------------------------------------------------- | |
input_dim = 1 | |
model = Sequential() | |
model.add(Dense(10, input_dim = input_dim, activation='tanh')) | |
model.add(Dense(90, activation='tanh')) | |
model.add(Dense(10, activation='tanh')) | |
model.add(Dense(10, activation='tanh')) | |
model.add(Dense(10, activation='tanh')) | |
model.add(Dense(10, activation='tanh')) | |
model.add(Dense(10, activation='tanh')) | |
model.add(Dense(10, activation='tanh')) | |
model.add(Dense(10, activation='tanh')) | |
model.add(Dense(10, activation='tanh')) | |
model.add(Dense(10, activation='tanh')) | |
model.add(Dense(1, activation='tanh')) | |
# ----------------------------------------------------------------------------- | |
# Comile and fit | |
# ----------------------------------------------------------------------------- | |
model.compile(loss='mean_squared_error', optimizer='adam', metrics=['accuracy']) | |
model.fit(X, Y, epochs=50, batch_size=10) | |
# ----------------------------------------------------------------------------- | |
# Evalute | |
# ----------------------------------------------------------------------------- | |
scores = model.evaluate(X, Y) | |
print("-" * 100) | |
print("\n%s: %.2f%%" % (model.metrics_names[0], scores[0]*100)) | |
# ----------------------------------------------------------------------------- | |
# Compare prediction vs groundtruth | |
# ----------------------------------------------------------------------------- | |
pred = model.predict(X) | |
x_plot = X | |
plt.scatter(x_plot, pred, s = 1, c = 'r') | |
plt.scatter(x_plot, Y, s = 1, c = 'b') | |
plt.show() |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment