Created
June 12, 2018 19:28
-
-
Save drorgl/aecfa152a5c6943587370530d87600d8 to your computer and use it in GitHub Desktop.
mnist ~3800 parameters model
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
# 3. Import libraries and modules | |
import numpy as np | |
np.random.seed(123) # for reproducibility | |
from keras.models import Sequential | |
from keras.layers import Dense, Dropout, Activation, Flatten | |
from keras.layers import Convolution1D, Convolution2D, MaxPooling1D,MaxPooling2D,AveragePooling2D,AveragePooling1D, BatchNormalization | |
from keras.utils import np_utils | |
from keras.datasets import mnist | |
from keras.layers.core import Reshape | |
from matplotlib import pyplot as plt | |
#from keras.utils.vis_utils import plot_model | |
# 4. Load pre-shuffled MNIST data into train and test sets | |
(X_train, y_train), (X_test, y_test) = mnist.load_data() | |
orig_x_test = X_test | |
# 5. Preprocess input data | |
X_train = X_train.reshape(X_train.shape[0], 28,28,1) | |
X_test = X_test.reshape(X_test.shape[0], 28,28,1) | |
X_train = X_train.astype('float32') | |
X_test = X_test.astype('float32') | |
X_train /= 255 | |
X_test /= 255 | |
# plt.imshow(X_train[0]) | |
# plt.show() | |
print ("X_train shape1", X_train[0].shape) | |
# 6. Preprocess class labels | |
Y_train = np_utils.to_categorical(y_train, 10) | |
Y_test = np_utils.to_categorical(y_test, 10) | |
#7. Define model architecture | |
model = Sequential() | |
model.add(Convolution2D(20, (5, 5) , activation='relu', input_shape=(28,28,1))) | |
model.add(BatchNormalization(momentum=0.1)) | |
model.add(Dropout(0.1)) | |
model.add(AveragePooling2D(2)) | |
model.add(Convolution2D(10,(1,1) , activation='relu')) | |
model.add(BatchNormalization(momentum=0.1)) | |
model.add(Dropout(0.1)) | |
model.add(AveragePooling2D(2)) | |
model.add(Convolution2D(12,(3,3) , activation='relu')) | |
model.add(BatchNormalization(momentum=0.1)) | |
model.add(Dropout(0.1)) | |
model.add(Convolution2D(10,(1,1) , activation='relu')) | |
model.add(Dropout(0.1)) | |
model.add(Dense(10, activation='relu')) | |
model.add(Flatten()) | |
model.add(Dense(10, activation='softmax')) | |
# 8. Compile model | |
model.compile(loss='categorical_crossentropy', | |
optimizer='adam', | |
metrics=['accuracy']) | |
model.summary() | |
#plot_model(model, to_file='model_plot.png', show_shapes=True, show_layer_names=True) | |
#print ("X_train shape2", X_train.shape) | |
# 9. Fit model on training data | |
# history = model.fit(X_train, Y_train, | |
# batch_size=512, nb_epoch=20, verbose=1,shuffle=True, | |
# validation_data=(X_test, Y_test)) | |
# history = model.fit(X_train, Y_train, | |
# batch_size=128, nb_epoch=10, verbose=1,shuffle=True, | |
# validation_data=(X_test, Y_test)) | |
history = model.fit(X_train, Y_train, | |
batch_size=8, nb_epoch=80, verbose=1,shuffle=True, | |
validation_data=(X_test, Y_test)) | |
print ("history", history.history); | |
#plot history | |
plt.plot(history.history['loss'], label='train') | |
plt.plot(history.history['val_loss'], label='test') | |
plt.legend() | |
#plt.savefig('training.png') | |
plt.show() | |
# 10. Evaluate model on test data | |
test_score = model.evaluate(X_test, Y_test, verbose=0) | |
print ("test score", test_score) | |
print("Test Large CNN Error: %.2f%%" % (100-test_score[1]*100)) | |
train_score = model.evaluate(X_train, Y_train, verbose=0) | |
print ("train score", train_score) | |
print("Train Large CNN Error: %.2f%%" % (100-train_score[1]*100)) | |
# prediction = model.predict(X_test[0:1]) | |
# print("prediction", prediction) | |
# plt.imshow(orig_x_test[0]) | |
# plt.show() | |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment