建立模型
1.函数式模型
from keras.layers import Input, Dense
from keras.models import Model
# This returns a tensor
inputs = Input(shape=(784,))
# a layer instance is callable on a tensor, and returns a tensor
x = Dense(64, activation='relu')(inputs)
x = Dense(64, activation='relu')(x)
predictions = Dense(10, activation='softmax')(x)
# This creates a model that includes
# the Input layer and three Dense layers
model = Model(inputs=inputs, outputs=predictions)
model.compile(optimizer='rmsprop',
loss='categorical_crossentropy',
metrics=['accuracy'])
model.summary()
2.Squential式模型
from keras.models import Sequential
from keras.layers import Dense, Activation
model = Sequential()
model.add(Dense(64, input_shape=(784,),activation='relu'))
#model.add(Activation('relu'))
model.add(Dense(64,activation='relu'))
#model.add(Activation('relu'))
model.add(Dense(10,activation='softmax'))
#model.add(Activation('softmax'))
model.compile(optimizer='rmsprop',
loss='categorical_crossentropy',
metrics=['accuracy'])
model.summary()
from keras.models import Sequential
from keras.layers import Dense, Activation
model = Sequential([
Dense(64,input_shape=(784,)),
Activation('relu'),
Dense(64),
Activation('relu'),
Dense(10),
Activation('softmax'),
])
model.summary()
保存和载入模型
1.简单的demo
import numpy as np
np.random.seed(1337) # for reproducibility
from keras.models import Sequential
from keras.layers import Dense
from keras.models import load_model
# create some data
X = np.linspace(-1, 1, 200)
np.random.shuffle(X) # randomize the data
Y = 0.5 * X + 2 + np.random.normal(0, 0.05, (200, ))
X_train, Y_train = X[:160], Y[:160] # first 160 data points
X_test, Y_test = X[160:], Y[160:] # last 40 data points
model = Sequential()
model.add(Dense(output_dim=1, input_dim=1))
model.compile(loss='mse', optimizer='sgd')
for step in range(301):
cost = model.train_on_batch(X_train, Y_train)
# save
print('test before save: ', model.predict(X_test[0:2]))
model.save('my_model.h5') # HDF5 file, you have to pip3 install h5py if don't have it
del model # deletes the existing model
# load
model = load_model('my_model.h5')
print('test after load: ', model.predict(X_test[0:2]))
2.CNN的demo，主要参考这篇文章
from keras.models import Sequential
from keras.layers import Dense, Conv2D, MaxPooling2D, Flatten, Dropout
from keras.losses import categorical_crossentropy
from keras.optimizers import Adam
from keras.optimizers import SGD
from keras.models import model_from_json
from keras.models import load_model
from keras.utils import np_utils
import numpy as np
import os
from sklearn.model_selection import train_test_split
def load_data(resultpath):
datapath = os.path.join(resultpath, "data10_4.npz")
if os.path.exists(datapath):
data = np.load(datapath)
X, Y = data["X"], data["Y"]
else:
X = np.array(np.arange(432000)).reshape(10, 120, 120, 3)
Y = [0, 0, 1, 1, 2, 2, 3, 3, 2, 0]
X = X.astype('float32')
Y = np_utils.to_categorical(Y, 4)
np.savez(datapath, X=X, Y=Y)
print('Saved dataset to dataset.npz.')
print('X_shape:{}\nY_shape:{}'.format(X.shape, Y.shape))
return X, Y
def define_model():
model = Sequential()
# setup first conv layer
model.add(Conv2D(32, (3, 3), activation="relu",
input_shape=(120, 120, 3), padding='same')) # [10, 120, 120, 32]
# setup first maxpooling layer
model.add(MaxPooling2D(pool_size=(2, 2))) # [10, 60, 60, 32]
# setup second conv layer
model.add(Conv2D(8, kernel_size=(3, 3), activation="relu",
padding='same')) # [10, 60, 60, 8]
# setup second maxpooling layer
model.add(MaxPooling2D(pool_size=(3, 3))) # [10, 20, 20, 8]
# add bianping layer, 3200 = 20 * 20 * 8
model.add(Flatten()) # [10, 3200]
# add first full connection layer
model.add(Dense(512, activation='sigmoid')) # [10, 512]
# add dropout layer
model.add(Dropout(0.5))
# add second full connection layer
model.add(Dense(4, activation='softmax')) # [10, 4]
return model
def train_model(resultpath):
model = define_model()
# if want to use SGD, first define sgd, then set optimizer=sgd
sgd = SGD(lr=0.001, decay=1e-6, momentum=0, nesterov=True)
# select loss\optimizer\
model.compile(loss=categorical_crossentropy,
optimizer=Adam(), metrics=['accuracy'])
model.summary()
# load data
X, Y = load_data(resultpath)
# split train and test data
X_train, X_test, Y_train, Y_test = train_test_split(
X, Y, test_size=0.2, random_state=2)
# input data to model and train
history = model.fit(X_train, Y_train, batch_size=2, epochs=10,
validation_data=(X_test, Y_test), verbose=1, shuffle=True)
# evaluate the model
loss, acc = model.evaluate(X_test, Y_test, verbose=0)
print('Test loss:', loss)
print('Test accuracy:', acc)
return model
def my_save_model(resultpath):
model = train_model(resultpath)
# the first way to save model
model.save(os.path.join(resultpath, 'my_model.h5'))
# the secon way : save trained network structure and weights
model_json = model.to_json()
open(os.path.join(resultpath, 'my_model_structure.json'), 'w').write(model_json)
model.save_weights(os.path.join(resultpath, 'my_model_weights.hd5'))
def my_load_model(resultpath):
# test data
X = np.array(np.arange(86400)).reshape(2, 120, 120, 3)
Y = [0, 1]
X = X.astype('float32')
Y = np_utils.to_categorical(Y, 4)
# the first way of load model
model2 = load_model(os.path.join(resultpath, 'my_model.h5'))
model2.compile(loss=categorical_crossentropy,
optimizer=Adam(), metrics=['accuracy'])
test_loss, test_acc = model2.evaluate(X, Y, verbose=0)
print('Test loss:', test_loss)
print('Test accuracy:', test_acc)
y = model2.predict_classes(X)
print("predicct is: ", y)
# the second way : load model structure and weights
model = model_from_json(open(os.path.join(resultpath, 'my_model_structure.json')).read())
model.load_weights(os.path.join(resultpath, 'my_model_weights.hd5'))
model.compile(loss=categorical_crossentropy,
optimizer=Adam(), metrics=['accuracy'])
test_loss, test_acc = model.evaluate(X, Y, verbose=0)
print('Test loss:', test_loss)
print('Test accuracy:', test_acc)
y = model.predict_classes(X)
print("predicct is: ", y)
def main():
resultpath = "result"
train_model(resultpath)
#my_save_model(resultpath)
#my_load_model(resultpath)
if __name__ == "__main__":
main()