def main():
go_board_rows, go_board_cols = 19, 19
num_classes = go_board_rows * go_board_cols
num_games = 100
encoder = OnePlaneEncoder((go_board_rows, go_board_cols)) # <1>
processor = GoDataProcessor(encoder=encoder.name()) # <2>
generator = processor.load_go_data('train', num_games, use_generator=True) # <3>
test_generator = processor.load_go_data('test', num_games, use_generator=True)
# <1> First we create an encoder of board size.
# <2> Then we initialize a Go Data processor with it.
# <3> From the processor we create two data generators, for training and testing.
# end::train_generator_generator[]
# tag::train_generator_model[]
input_shape = (encoder.num_planes, go_board_rows, go_board_cols)
network_layers = small.layers(input_shape)
model = Sequential()
for layer in network_layers:
model.add(layer)
model.add(Dense(num_classes, activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='sgd', metrics=['accuracy'])
# end::train_generator_model[]
# tag::train_generator_fit[]
epochs = 5
batch_size = 128
model.fit_generator(generator=generator.generate(batch_size, num_classes), # <1>
epochs=epochs,
steps_per_epoch=generator.get_num_samples() / batch_size, # <2>
validation_data=test_generator.generate(batch_size, num_classes), # <3>
validation_steps=test_generator.get_num_samples() / batch_size, # <4>
callbacks=[ModelCheckpoint('./checkpoints/small_model_epoch_{epoch}.h5')]) # <5>
try:
with tf.device('/device:GPU:0'):
model.evaluate_generator(generator=test_generator.generate(batch_size, num_classes),
steps=test_generator.get_num_samples() / batch_size) # <6>
except RuntimeError as e:
print(e)
from dlgo.data.parallel_processor import GoDataProcessor
from dlgo.encoders.oneplane import OnePlaneEncoder
from dlgo.networks import small
from keras.models import Sequential
from keras.layers.core import Dense
from keras.callbacks import ModelCheckpoint
if __name__ == '__main__':
go_board_rows, go_board_cols = 19, 19
num_classes = go_board_rows * go_board_cols
num_games = 100
encoder = OnePlaneEncoder((go_board_rows, go_board_cols))
processor = GoDataProcessor(encoder=encoder.name())
generator = processor.load_go_data('train', num_games, use_generator=True)
test_generator = processor.load_go_data('test',
num_games,
use_generator=True)
input_shape = (encoder.num_planes, go_board_rows, go_board_cols)
network_layers = small.layers(input_shape)
model = Sequential()
for layer in network_layers:
model.add(layer)
model.add(Dense(num_classes, activation='softmax'))
model.compile(loss='categorical_crossentropy',
optimizer='adagrad',
metrics=['accuracy'])
def model03():
mainmodel_start_time = datetime.now().strftime('%Y-%m-%d %H:%M:%S')
print('Start model03(): ' + mainmodel_start_time)
optimizer = Adagrad()
# optimizer = Adadelta()
# optimizer = SGD(lr=0.01, momentum=0.9, decay=0.001)
go_board_rows, go_board_cols = 19, 19
num_classes = go_board_rows * go_board_cols
num_games = 100
one_plane_encoder = OnePlaneEncoder((go_board_rows, go_board_cols))
seven_plane_encoder = SevenPlaneEncoder((go_board_rows, go_board_cols))
simple_encoder = SimpleEncoder((go_board_rows, go_board_cols))
encoder = seven_plane_encoder
processor = GoDataProcessor(encoder=encoder.name())
train_generator = processor.load_go_data('train',
num_games,
use_generator=True)
test_generator = processor.load_go_data('test',
num_games,
use_generator=True)
input_shape = (encoder.num_planes, go_board_rows, go_board_cols)
network_large = large
network_small = small
network = network_small
network_layers = network.layers(input_shape)
model = Sequential()
for layer in network_layers:
model.add(layer)
model.add(Dense(num_classes, activation='relu'))
model.compile(loss='categorical_crossentropy',
optimizer=optimizer,
metrics=['accuracy'])
epochs = 5
batch_size = 128
model.fit_generator(
generator=train_generator.generate(batch_size, num_classes),
epochs=epochs,
steps_per_epoch=train_generator.get_num_samples() / batch_size,
validation_data=test_generator.generate(batch_size, num_classes),
validation_steps=test_generator.get_num_samples() / batch_size,
callbacks=[
ModelCheckpoint(
filepath=
'D:\\CODE\\Python\\Go\\code\\dlgo\\data\\checkpoints\\small_epoch_{epoch:02d}'
'-acc-{accuracy:.4f}-val_acc_{'
'val_accuracy:.4f}f.h5',
monitor='accuracy')
])
model.evaluate_generator(
generator=test_generator.generate(batch_size, num_classes),
steps=test_generator.get_num_samples() / batch_size)
def mainmodel():
mainmodel_start_time = datetime.now().strftime('%Y-%m-%d %H:%M:%S')
print('Inside mainmodel(): ' + mainmodel_start_time)
go_board_rows, go_board_cols = 19, 19
num_classes = go_board_rows * go_board_cols
num_games = 100
encoder = OnePlaneEncoder((go_board_rows, go_board_cols)) # 1 plane
# encoder = SevenPlaneEncoder((go_board_rows, go_board_cols)) # 7 planes
# encoder = SimpleEncoder((go_board_rows, go_board_cols)) # 11 planes
processor = GoDataProcessor(encoder=encoder.name())
generator = processor.load_go_data('train',
num_games) #, use_generator=True
test_generator = processor.load_go_data('test',
num_games) #, use_generator=True
# generator = processor.load_go_data('train', num_games, use_generator=True)
# test_generator = processor.load_go_data('test', num_games, use_generator=True)
input_shape = (encoder.num_planes, go_board_rows, go_board_cols)
# network_layers = small.layers(input_shape)
network_layers = medium.layers(input_shape)
model = Sequential()
mainmodel_start_time = datetime.now().strftime('%Y-%m-%d %H:%M:%S')
print('Inside mainmodel(): before adding all layers: ' +
mainmodel_start_time)
for layer in network_layers:
mainmodel_start_time = datetime.now().strftime('%Y-%m-%d %H:%M:%S')
print('Before model.add(' + layer.name + '): ' + mainmodel_start_time)
model.add(layer)
mainmodel_start_time = datetime.now().strftime('%Y-%m-%d %H:%M:%S')
print('After model.add(' + layer.name + '): ' + mainmodel_start_time)
mainmodel_start_time = datetime.now().strftime('%Y-%m-%d %H:%M:%S')
print('Inside mainmodel(): after adding all layers: ' +
mainmodel_start_time)
model.add(Dense(num_classes, activation='softmax'))
model.compile(loss='categorical_crossentropy',
optimizer='sgd',
metrics=['accuracy'])
mainmodel_start_time = datetime.now().strftime('%Y-%m-%d %H:%M:%S')
print('Inside mainmodel(): after compiling the model: ' +
mainmodel_start_time)
# For more information:
# https://keras.io/callbacks/
epochs = 2
batch_size = 128
model.fit_generator(
# model.fit(
generator=generator.generate(batch_size, num_classes),
epochs=epochs,
steps_per_epoch=generator.get_num_samples() / batch_size,
validation_data=test_generator.generate(batch_size, num_classes),
validation_steps=test_generator.get_num_samples() / batch_size,
callbacks=[
ModelCheckpoint(
'data\\checkpoints\\small_model_epoch_{epoch:02d}-{val_loss:.2f}.h5'
),
# EarlyStopping(monitor='accuracy'),
# ProgbarLogger(),
# CSVLogger('data\\logs\\training.log'),
# TensorBoard(log_dir='data\\logs', batch_size=128, write_images=True)
])
model.evaluate_generator(
generator=test_generator.generate(batch_size, num_classes),
steps=test_generator.get_num_samples() / batch_size)