maggicl/ml
Archived
1
0
Fork 0
Code Issues Pull requests Projects Releases Wiki Activity

t1-3 done

Browse source
This commit is contained in:
Claudio Maggioni (maggicl) 2021-04-26 12:39:29 +02:00
parent 4e5c75e52c
commit 8a4c98d0d1
1 changed files with 15 additions and 9 deletions
Show stats Download patch file Download diff file Expand all files Collapse all files

24
assignment_1/src/t1.py
View file

@ -7,6 +7,7 @@ from tensorflow.keras.layers import Dense
from tensorflow.keras import losses
from tensorflow import keras
import tensorflow as tf
from sklearn.metrics import mean_squared_error
data = np.load("../data/data.npz")
xs = data["x"] # 2000x2
@ -60,8 +61,11 @@ X_val = X_val[:, 1:]
mean = np.mean(X_train, axis=0)
std = np.std(X_train, axis=0)
y_mean = np.mean(y_train, axis=0)
y_std = np.std(y_train, axis=0)
#y_mean = np.mean(y_train, axis=0)
#y_std = np.std(y_train, axis=0)
y_mean = 0
y_std = 1
X_train -= mean
X_train /= std
@ -74,15 +78,17 @@ y_val -= y_mean
y_val /= y_std
network = Sequential()
network.add(Dense(20, activation='relu'))
network.add(Dense(20, activation='relu'))
network.add(Dense(1, activation='sigmoid'))
network.add(Dense(35, activation='relu'))
network.add(Dense(10, activation='relu'))
network.add(Dense(3, activation='relu'))
network.add(Dense(1, activation='linear'))
network.compile(optimizer='rmsprop', loss='mse', metrics=['mse'])
callback = tf.keras.callbacks.EarlyStopping(monitor='loss', patience=20)
network.fit(X_train, y_train, epochs=2000, verbose=1, batch_size=1000, validation_data=(X_val, y_val), callbacks=[callback])
epochs = 10000
callback = tf.keras.callbacks.EarlyStopping(monitor='loss', patience=1000)
network.fit(X_train, y_train, epochs=epochs, verbose=1, batch_size=100, validation_data=(X_val, y_val), callbacks=[callback])
msq = np.mean(((network.predict(X_val) - y_val) * y_std + y_mean) ** 2)
msq = mean_squared_error(network.predict(X_val), y_val)
print(msq)
X_test = X_test[:, 1:]
@ -90,5 +96,5 @@ X_test -= mean
X_test /= std
y_test -= y_mean
y_test /= y_std
msq = np.mean(((network.predict(X_test) - y_test) * y_std + y_mean) ** 2)
msq = mean_squared_error(network.predict(X_test), y_test)
print(msq)