129 lines
4.5 KiB
Python
129 lines
4.5 KiB
Python
import numpy as np
|
|
import sys
|
|
import time as t
|
|
'''
|
|
from keras.models import Sequential
|
|
from keras.layers import Dense, Dropout, Activation, Flatten, Reshape, Merge, Permute
|
|
from keras.layers import Deconvolution2D, Convolution2D, MaxPooling2D, UpSampling2D, ZeroPadding2D
|
|
from keras.layers import Input
|
|
from keras.layers.normalization import BatchNormalization
|
|
from keras.utils import np_utils
|
|
'''
|
|
from keras import backend as K
|
|
K.set_image_dim_ordering('th')
|
|
np.random.seed(7)
|
|
|
|
'''
|
|
Model definition
|
|
'''
|
|
def FCN():
|
|
## sample structure defined below
|
|
# inputs = Input((1, w, h))
|
|
|
|
# conv1 = Convolution2D(32, 3, 3, activation='relu', border_mode='same')(inputs)
|
|
# conv1 = Convolution2D(32, 3, 3, activation='relu', border_mode='same')(conv1)
|
|
# m_pool1 = MaxPooling2D(pool_size=(2, 2))(conv1)
|
|
|
|
# conv2 = Convolution2D(64, 3, 3, activation='relu', border_mode='same')(m_pool1)
|
|
# drop1 = Dropout(0.2)(conv2)
|
|
# conv2 = Convolution2D(64, 3, 3, activation='relu', border_mode='same')(drop1)
|
|
# m_pool2 = MaxPooling2D(pool_size=(2, 2))(conv2)
|
|
|
|
# conv7 = Convolution2D(512, 3, 3, activation='relu', border_mode='same')(m_pool6)
|
|
# conv7 = Convolution2D(1, 3, 3, activation='relu', border_mode='same')(conv7)
|
|
|
|
# up8x = UpSampling2D(size=(2, 2))(conv16x)
|
|
# merge8x = merge([up8x, m_pool3], mode='concat', concat_axis=1)
|
|
# conv8x = Convolution2D(1, 1, 1, activation='relu', border_mode='same')(merge8x)
|
|
|
|
# up4x = UpSampling2D(size=(2, 2))(conv8x)
|
|
# merge4x = merge([up4x, m_pool2], mode='concat', concat_axis=1)
|
|
# conv4x = Convolution2D(1, 1, 1, activation='relu', border_mode='same')(merge4x)
|
|
|
|
# up4x = UpSampling2D(size=(4, 4))(conv4x)
|
|
# model = Model(input=inputs, output=up4x)
|
|
# # Optimizer uses recommended Adadelta values
|
|
# model.compile(optimizer=Adadelta(lr=0.01), loss='categorical_crossentropy', metrics=['accuracy'])
|
|
return model
|
|
|
|
|
|
## Open data
|
|
im_train = np.load('Waldo_train_data.npy')
|
|
lbl_train = np.load('Waldo_test_lbl.npy')
|
|
im_test = np.load('Waldo_test_data.npy')
|
|
lbl_test = np.load('Waldo_test_lbl.npy')
|
|
|
|
## Define model
|
|
model = FCN()
|
|
|
|
## Define training parameters
|
|
epochs = 40 # an epoch is one forward pass and back propogation of all training data
|
|
batch_size = 5
|
|
#lrate = 0.01
|
|
#decay = lrate/epochs
|
|
# epoch - one forward pass and one backward pass of all training data
|
|
# batch size - number of training example used in one forward/backward pass
|
|
# (higher batch size uses more memory)
|
|
# learning rate - controls magnitude of weight changes in training the NN
|
|
|
|
## Train model
|
|
# Purely superficial output
|
|
sys.stdout.write("\nFitting model")
|
|
sys.stdout.flush()
|
|
for i in range(0, 3):
|
|
t.sleep(0.8)
|
|
sys.stdout.write('.')
|
|
sys.stdout.flush()
|
|
print()
|
|
|
|
# Outputs the model structure
|
|
for i in range(0, len(model.layers)):
|
|
print("Layer {}: {}".format(i, model.layers[i].output))
|
|
print('-'*30)
|
|
|
|
filepath = "checkpoint.hdf5" # Defines the model checkpoint file
|
|
checkpoint = ModelCheckpoint(filepath, verbose=1, save_best_only=False) # Defines the checkpoint process
|
|
callbacks_list = [checkpoint] # Adds the checkpoint process to the list of action performed during training
|
|
start = t.time() # Records time before training
|
|
|
|
# Fits model based on initial parameters
|
|
model.fit(im_train, lbl_train, nb_epoch=epochs, batch_size=batch_size,
|
|
verbose=2, shuffle=True, callbacks=callbacks_list)
|
|
# If getting a value error here, output of network and corresponding lbl_train
|
|
# data probably don't match
|
|
end = t.time() # Records time after tranining
|
|
|
|
print('Training Duration: {}'.format(end-start))
|
|
print('-'*30)
|
|
print("*** Saving FCN model and weights ***")
|
|
|
|
'''
|
|
# *To save model and weights seperately:
|
|
# save model as json file
|
|
model_json = model.to_json()
|
|
with open("UNet_model.json", "w") as json_file:
|
|
json_file.write(model_json)
|
|
# save weights as h5 file
|
|
model.save_weights("UNet_weights.h5")
|
|
print("\nModel weights and structure have been saved.\n")
|
|
'''
|
|
# Save model as one file
|
|
model.save('Waldo.h5')
|
|
print("\nModel weights and structure have been saved.\n")
|
|
|
|
## Testing the model
|
|
# Load test data
|
|
im_test, lbl_test = Load_Images()
|
|
# Show data stats
|
|
print('*'*30)
|
|
print(im_test.shape)
|
|
print(lbl_test.shape)
|
|
print('*'*30)
|
|
start = t.time()
|
|
# Passes the dataset through the model
|
|
pred_lbl = model.predict(im_test, verbose=1, batch_size=batch_size)
|
|
end = t.time()
|
|
print("Images generated in {} seconds".format(end - start))
|
|
np.save('Test/predicted_results.npy', pred_lbl)
|
|
|