def compile_and_train(model: training.Model,
num_epochs: int) -> Tuple[History, str]:
accuracies = []
losses = []
model.compile(loss=categorical_crossentropy,
optimizer=Adam(),
metrics=['acc'])
filepath = 'weights/' + model.name + '.hdf5'
checkpoint = ModelCheckpoint(filepath,
monitor='loss',
verbose=0,
save_weights_only=True,
save_best_only=True,
mode='auto',
save_freq=1,
period=1)
tensor_board = TensorBoard(log_dir='logs/', histogram_freq=0, batch_size=5)
history = model.fit(x=x_train,
y=y_train,
batch_size=32,
epochs=num_epochs,
verbose=1,
callbacks=[checkpoint, tensor_board],
validation_split=0.2)
weight_files = glob.glob(os.path.join(os.getcwd(), 'weights/*'))
weight_file = max(weight_files, key=os.path.getctime) # most recent file
return history, weight_file
def test_stateful_metrics(self):
with self.cached_session():
np.random.seed(1334)
class BinaryTruePositives(layers.Layer):
"""Stateful Metric to count the total true positives over all batches.
Assumes predictions and targets of shape `(samples, 1)`.
Arguments:
threshold: Float, lower limit on prediction value that counts as a
positive class prediction.
name: String, name for the metric.
"""
def __init__(self, name='true_positives', **kwargs):
super(BinaryTruePositives, self).__init__(name=name,
**kwargs)
self.true_positives = K.variable(value=0, dtype='int32')
self.stateful = True
def reset_states(self):
K.set_value(self.true_positives, 0)
def __call__(self, y_true, y_pred):
"""Computes the number of true positives in a batch.
Args:
y_true: Tensor, batch_wise labels
y_pred: Tensor, batch_wise predictions
Returns:
The total number of true positives seen this epoch at the
completion of the batch.
"""
y_true = math_ops.cast(y_true, 'int32')
y_pred = math_ops.cast(math_ops.round(y_pred), 'int32')
correct_preds = math_ops.cast(
math_ops.equal(y_pred, y_true), 'int32')
true_pos = math_ops.cast(
math_ops.reduce_sum(correct_preds * y_true), 'int32')
current_true_pos = self.true_positives * 1
self.add_update(state_ops.assign_add(
self.true_positives, true_pos),
inputs=[y_true, y_pred])
return current_true_pos + true_pos
metric_fn = BinaryTruePositives()
config = metrics.serialize(metric_fn)
metric_fn = metrics.deserialize(
config,
custom_objects={'BinaryTruePositives': BinaryTruePositives})
# Test on simple model
inputs = layers.Input(shape=(2, ))
outputs = layers.Dense(1, activation='sigmoid')(inputs)
model = Model(inputs, outputs)
model.compile(optimizer='sgd',
loss='binary_crossentropy',
metrics=['acc', metric_fn])
# Test fit, evaluate
samples = 100
x = np.random.random((samples, 2))
y = np.random.randint(2, size=(samples, 1))
val_samples = 10
val_x = np.random.random((val_samples, 2))
val_y = np.random.randint(2, size=(val_samples, 1))
history = model.fit(x,
y,
epochs=1,
batch_size=10,
validation_data=(val_x, val_y))
outs = model.evaluate(x, y, batch_size=10)
preds = model.predict(x)
def ref_true_pos(y_true, y_pred):
return np.sum(np.logical_and(y_pred > 0.5, y_true == 1))
# Test correctness (e.g. updates should have been run)
self.assertAllClose(outs[2], ref_true_pos(y, preds), atol=1e-5)
# Test correctness of the validation metric computation
val_preds = model.predict(val_x)
val_outs = model.evaluate(val_x, val_y, batch_size=10)
self.assertAllClose(val_outs[2],
ref_true_pos(val_y, val_preds),
atol=1e-5)
self.assertAllClose(val_outs[2],
history.history['val_true_positives'][-1],
atol=1e-5)
# Test with generators
gen = [(np.array([x0]), np.array([y0])) for x0, y0 in zip(x, y)]
val_gen = [(np.array([x0]), np.array([y0]))
for x0, y0 in zip(val_x, val_y)]
history = model.fit_generator(iter(gen),
epochs=1,
steps_per_epoch=samples,
validation_data=iter(val_gen),
validation_steps=val_samples)
outs = model.evaluate_generator(iter(gen), steps=samples)
preds = model.predict_generator(iter(gen), steps=samples)
# Test correctness of the metric results
self.assertAllClose(outs[2], ref_true_pos(y, preds), atol=1e-5)
# Test correctness of the validation metric computation
val_preds = model.predict_generator(iter(val_gen),
steps=val_samples)
val_outs = model.evaluate_generator(iter(val_gen),
steps=val_samples)
self.assertAllClose(val_outs[2],
ref_true_pos(val_y, val_preds),
atol=1e-5)
self.assertAllClose(val_outs[2],
history.history['val_true_positives'][-1],
atol=1e-5)
def test_stateful_metrics(self):
with self.test_session():
np.random.seed(1334)
class BinaryTruePositives(layers.Layer):
"""Stateful Metric to count the total true positives over all batches.
Assumes predictions and targets of shape `(samples, 1)`.
Arguments:
threshold: Float, lower limit on prediction value that counts as a
positive class prediction.
name: String, name for the metric.
"""
def __init__(self, name='true_positives', **kwargs):
super(BinaryTruePositives, self).__init__(name=name, **kwargs)
self.true_positives = K.variable(value=0, dtype='int32')
self.stateful = True
def reset_states(self):
K.set_value(self.true_positives, 0)
def __call__(self, y_true, y_pred):
"""Computes the number of true positives in a batch.
Args:
y_true: Tensor, batch_wise labels
y_pred: Tensor, batch_wise predictions
Returns:
The total number of true positives seen this epoch at the
completion of the batch.
"""
y_true = math_ops.cast(y_true, 'int32')
y_pred = math_ops.cast(math_ops.round(y_pred), 'int32')
correct_preds = math_ops.cast(math_ops.equal(y_pred, y_true), 'int32')
true_pos = math_ops.cast(
math_ops.reduce_sum(correct_preds * y_true), 'int32')
current_true_pos = self.true_positives * 1
self.add_update(
state_ops.assign_add(self.true_positives, true_pos),
inputs=[y_true, y_pred])
return current_true_pos + true_pos
metric_fn = BinaryTruePositives()
config = metrics.serialize(metric_fn)
metric_fn = metrics.deserialize(
config, custom_objects={'BinaryTruePositives': BinaryTruePositives})
# Test on simple model
inputs = layers.Input(shape=(2,))
outputs = layers.Dense(1, activation='sigmoid')(inputs)
model = Model(inputs, outputs)
model.compile(optimizer='sgd',
loss='binary_crossentropy',
metrics=['acc', metric_fn])
# Test fit, evaluate
samples = 100
x = np.random.random((samples, 2))
y = np.random.randint(2, size=(samples, 1))
val_samples = 10
val_x = np.random.random((val_samples, 2))
val_y = np.random.randint(2, size=(val_samples, 1))
history = model.fit(x, y,
epochs=1,
batch_size=10,
validation_data=(val_x, val_y))
outs = model.evaluate(x, y, batch_size=10)
preds = model.predict(x)
def ref_true_pos(y_true, y_pred):
return np.sum(np.logical_and(y_pred > 0.5, y_true == 1))
# Test correctness (e.g. updates should have been run)
self.assertAllClose(outs[2], ref_true_pos(y, preds), atol=1e-5)
# Test correctness of the validation metric computation
val_preds = model.predict(val_x)
val_outs = model.evaluate(val_x, val_y, batch_size=10)
self.assertAllClose(
val_outs[2], ref_true_pos(val_y, val_preds), atol=1e-5)
self.assertAllClose(
val_outs[2], history.history['val_true_positives'][-1], atol=1e-5)
# Test with generators
gen = [(np.array([x0]), np.array([y0])) for x0, y0 in zip(x, y)]
val_gen = [(np.array([x0]), np.array([y0]))
for x0, y0 in zip(val_x, val_y)]
history = model.fit_generator(iter(gen),
epochs=1,
steps_per_epoch=samples,
validation_data=iter(val_gen),
validation_steps=val_samples)
outs = model.evaluate_generator(iter(gen), steps=samples)
preds = model.predict_generator(iter(gen), steps=samples)
# Test correctness of the metric results
self.assertAllClose(outs[2], ref_true_pos(y, preds), atol=1e-5)
# Test correctness of the validation metric computation
val_preds = model.predict_generator(iter(val_gen), steps=val_samples)
val_outs = model.evaluate_generator(iter(val_gen), steps=val_samples)
self.assertAllClose(
val_outs[2], ref_true_pos(val_y, val_preds), atol=1e-5)
self.assertAllClose(
val_outs[2], history.history['val_true_positives'][-1], atol=1e-5)
def run(model):
# Download kitti dataset
build_data.maybe_download_training_img(DATA_DIRECTORY)
x, y = build_data.get_data(TRAINING_DATA_DIRECTORY, IMAGE_SHAPE)
if model is None:
inputs = Input(shape=(IMAGE_SHAPE[0], IMAGE_SHAPE[1], 3))
# Block 1
block1_conv1 = Conv2D(64, (3, 3),
activation='relu',
padding='same',
name='block1_conv1')(inputs)
block1_conv2 = Conv2D(64, (3, 3),
activation='relu',
padding='same',
name='block1_conv2')(block1_conv1)
block1_pool = MaxPooling2D((2, 2), strides=(2, 2),
name='block1_pool')(block1_conv2)
# Block 2
block2_conv1 = Conv2D(128, (3, 3),
activation='relu',
padding='same',
name='block2_conv1')(block1_pool)
block2_conv2 = Conv2D(128, (3, 3),
activation='relu',
padding='same',
name='block2_conv2')(block2_conv1)
block2_pool = MaxPooling2D((2, 2), strides=(2, 2),
name='block2_pool')(block2_conv2)
# Block 3
block3_conv1 = Conv2D(256, (3, 3),
activation='relu',
padding='same',
name='block3_conv1')(block2_pool)
block3_conv2 = Conv2D(256, (3, 3),
activation='relu',
padding='same',
name='block3_conv2')(block3_conv1)
block3_conv3 = Conv2D(256, (3, 3),
activation='relu',
padding='same',
name='block3_conv3')(block3_conv2)
block3_pool = MaxPooling2D((2, 2), strides=(2, 2),
name='block3_pool')(block3_conv3)
# Block 4
block4_conv1 = Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block4_conv1')(block3_pool)
block4_conv2 = Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block4_conv2')(block4_conv1)
block4_conv3 = Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block4_conv3')(block4_conv2)
block4_pool = MaxPooling2D((2, 2), strides=(2, 2),
name='block4_pool')(block4_conv3)
# Block 5
block5_conv1 = Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block5_conv1')(block4_pool)
block5_conv2 = Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block5_conv2')(block5_conv1)
block5_conv3 = Conv2D(512, (3, 3),
activation='relu',
padding='same',
name='block5_conv3')(block5_conv2)
block5_pool = MaxPooling2D((2, 2), strides=(2, 2),
name='block5_pool')(block5_conv3)
pool5_conv1x1 = Conv2D(2, (1, 1), activation='relu',
padding='same')(block5_pool)
upsample_1 = Conv2DTranspose(2,
kernel_size=(4, 4),
strides=(2, 2),
padding="same")(pool5_conv1x1)
pool4_conv1x1 = Conv2D(2, (1, 1), activation='relu',
padding='same')(block4_pool)
add_1 = Add()([upsample_1, pool4_conv1x1])
upsample_2 = Conv2DTranspose(2,
kernel_size=(4, 4),
strides=(2, 2),
padding="same")(add_1)
pool3_conv1x1 = Conv2D(2, (1, 1), activation='relu',
padding='same')(block3_pool)
add_2 = Add()([upsample_2, pool3_conv1x1])
upsample_3 = Conv2DTranspose(2,
kernel_size=(16, 16),
strides=(8, 8),
padding="same")(add_2)
output = Dense(2, activation='softmax')(upsample_3)
model = Model(inputs, output, name='multinet_seg')
adam = Adam(lr=LEARNING_RATE)
model.compile(loss='categorical_crossentropy',
optimizer=adam,
metrics=['accuracy'])
model.fit(x, y, batch_size=BATCH_SIZE, epochs=EPOCHS)
model.save('trained_model/trained_model' + str(time.time()) + '.h5')
def data_pre(data):
# 得到标签
label = [[i] * len(data[i]) for i in range(len(data))][0]
label = to_categorical(label)
# 切词
context = []
for i in data:
for j in i:
context.append(jieba.lcut(j))
# 构建词典
tokenizer = Tokenizer(num_words=20000)
tokenizer.fit_on_texts(context)
train_tags_title = tokenizer.texts_to_sequences(context)
train_tags_title_preprocessed = pad_sequences(train_tags_title,
maxlen=45,
padding='post')
# 预训练词向量
# embedding_matrix = np.zeros((278028, 30), dtype=np.float32)
# f = open('wiki.zh.text.vector', encoding='utf-8')
# f = f.readlines()
# for text in f:
# text = text.split()
# if text[0] in context:
# embedding_matrix[context[text[0]]] = text[1:]
# 模型
x_1 = Input(shape=(45, )) # 输入数据维度
embed_1 = Embedding(input_dim=45,
output_dim=45)(x_1) # 将索引值转化为稠密向量，且只能做第一层
L_1 = (LSTM(64))(embed_1) # 第一个括号构建一个层 64是输出空间的维度，第二个括号用该层做计算
L_1 = Dropout(0.5)(L_1) # 防止过拟合，0.5在这里是需要丢弃的输入比例
L_1 = Dense(9, activation='softmax')(L_1) # 3是输出空间维度
model_one = Model(x_1, L_1) # x_1输入，L_1输出
model_one.compile(loss='categorical_crossentropy',
optimizer='rmsprop',
metrics=['acc']) # 'binary_crossentropy'
history = model_one.fit(train_tags_title_preprocessed,
label,
batch_size=512,
epochs=20,
validation_split=0.1,
shuffle=True)
# 汇总acc函数历史数据
plt.plot(history.history['acc'])
plt.plot(history.history['val_acc'])
plt.title('model acc')
plt.ylabel('accuracy')
plt.xlabel('epoch')
plt.legend(['train', 'val'], loc='upper left')
plt.show()
# 汇总损失函数历史数据
plt.plot(history.history['loss'])
plt.plot(history.history['val_loss'])
plt.title('model loss')
plt.ylabel('loss')
plt.xlabel('epoch')
plt.legend(['train', 'val'], loc='upper left')
plt.show()
y_train = np_utils.to_categorical(y_train, NUM_CLASSES)
y_test = np_utils.to_categorical(y_test, NUM_CLASSES)
X_train = X_train.astype("float") / 255.0
X_test = X_test.astype("float") / 255.0
# モデルの定義
model = VGG16(weights='imagenet',
include_top=False,
input_shape=(IMAGE_SIZE, IMAGE_SIZE, 3))
top_model = Sequential()
top_model.add(Flatten(input_shape=model.output_shape[1:]))
top_model.add(Dense(256, activation='relu'))
top_model.add(Dropout(0.5))
top_model.add(Dense(NUM_CLASSES, activation='softmax'))
model = Model(inputs=model.input, outputs=top_model(model.output))
for layer in model.layers[:15]:
layer.trainable = False
opt = Adam(lr=0.0001)
model.compile(loss="categorical_crossentropy",
optimizer=opt,
metrics=['accuracy'])
model.fit(X_train, y_train, batch_size=16, epochs=5)
results = model.evaluate(X_test, y_test, batch_size=16)
print("test loss, test acc:", results)
model.save("./AnimalJudgmentModel.h5")
class ChessModel:
"""
The model which can be trained to take observations of a game of chess
and return value and policy predictions. Inpired by https://github.com/Zeta36/chess-alpha-zero/blob/master/src/chess_zero/agent/model_chess.py
Attributes:
:ivar Config config: configuration to use
:ivar Model model: the Keras model to use for predictions
"""
def __init__(self, config):
self.config = config
self.model = None # type: Model
self.digest = None
self.api = None
def build(self):
"""
Builds the full Keras model and stores it in self.model.
"""
mc = self.config
in_x = x = Input((12, 8, 8))
# (batch, channels, height, width)
x = Conv2D(filters=mc.cnn_filter_num,
kernel_size=mc.cnn_first_filter_size,
padding="same",
data_format="channels_first",
use_bias=False,
kernel_regularizer=l2(mc.l2_reg),
name="input_conv-" + str(mc.cnn_first_filter_size) + "-" +
str(mc.cnn_filter_num))(x)
x = BatchNormalization(axis=1, name="input_batchnorm")(x)
x = Activation("relu", name="input_relu")(x)
for i in range(mc.res_layer_num):
x = self._build_residual_block(x, i + 1)
res_out = x
# for policy output
x = Conv2D(filters=2,
kernel_size=1,
data_format="channels_first",
use_bias=False,
kernel_regularizer=l2(mc.l2_reg),
name="policy_conv-1-2")(res_out)
x = BatchNormalization(axis=1, name="policy_batchnorm")(x)
x = Activation("relu", name="policy_relu")(x)
x = Flatten(name="policy_flatten")(x)
policy_out = Dense(self.config.n_labels,
kernel_regularizer=l2(mc.l2_reg),
activation="softmax",
name="policy_out")(x)
# for value output
x = Conv2D(filters=4,
kernel_size=1,
data_format="channels_first",
use_bias=False,
kernel_regularizer=l2(mc.l2_reg),
name="value_conv-1-4")(res_out)
x = BatchNormalization(axis=1, name="value_batchnorm")(x)
x = Activation("relu", name="value_relu")(x)
x = Flatten(name="value_flatten")(x)
x = Dense(mc.value_fc_size,
kernel_regularizer=l2(mc.l2_reg),
activation="relu",
name="value_dense")(x)
value_out = Dense(1,
kernel_regularizer=l2(mc.l2_reg),
activation="tanh",
name="value_out")(x)
self.model = Model(in_x, [policy_out, value_out], name="chess_model")
def _build_residual_block(self, x, index):
# mc = self.config.model
mc = self.config
in_x = x
res_name = "res" + str(index)
x = Conv2D(filters=mc.cnn_filter_num,
kernel_size=mc.cnn_filter_size,
padding="same",
data_format="channels_first",
use_bias=False,
kernel_regularizer=l2(mc.l2_reg),
name=res_name + "_conv1-" + str(mc.cnn_filter_size) + "-" +
str(mc.cnn_filter_num))(x)
x = BatchNormalization(axis=1, name=res_name + "_batchnorm1")(x)
x = Activation("relu", name=res_name + "_relu1")(x)
x = Conv2D(filters=mc.cnn_filter_num,
kernel_size=mc.cnn_filter_size,
padding="same",
data_format="channels_first",
use_bias=False,
kernel_regularizer=l2(mc.l2_reg),
name=res_name + "_conv2-" + str(mc.cnn_filter_size) + "-" +
str(mc.cnn_filter_num))(x)
x = BatchNormalization(axis=1,
name="res" + str(index) + "_batchnorm2")(x)
x = Add(name=res_name + "_add")([in_x, x])
x = Activation("relu", name=res_name + "_relu2")(x)
return x
def compile(self, optimizer, loss, metrics, loss_weights=None):
self.model.compile(optimizer=optimizer,
loss=loss,
metrics=metrics,
loss_weights=loss_weights)
return self.model
def fit(self,
dataset,
y=None,
validation_data=None,
batch_size=None,
epochs=10,
shuffle=True,
val_split=None,
callbacks=None):
self.model.fit(x=dataset,
y=y,
batch_size=batch_size,
epochs=epochs,
shuffle=True,
validation_split=val_split,
validation_data=validation_data,
callbacks=callbacks)
return self.model
def predict(self,
x,
batch_size=None,
steps=None,
callbacks=None,
max_queue_size=10,
workers=1,
use_multiprocessing=False):
value = self.model.predict(x=x,
batch_size=batch_size,
steps=steps,
callbacks=callbacks,
max_queue_size=max_queue_size,
workers=workers,
use_multiprocessing=use_multiprocessing)
return value
def summary(self):
self.model.summary(line_length=None, positions=None, print_fn=None)
def run(self, ctx, exa, train: bool):
session_config = tf.ConfigProto(allow_soft_placement=True,
log_device_placement=False)
session = tf.Session(config=session_config)
tf.keras.backend.set_session(session)
config = self.read_config(exa)
batch_size = config["batch_size"]
epochs = config["epochs"]
steps_per_epoch = ctx.size() // batch_size
use_cache = config["use_cache"]
load_path = None
if "model_load_bucketfs_path" in config:
load_path = config["model_load_bucketfs_path"]
save_url = None
if "model_save_bucketfs_url" in config:
save_url = config["model_save_bucketfs_url"]
save_path = config["model_temporary_save_path"]
dataset = DatasetUtils().create_generator_dataset(
ctx, epochs, batch_size, use_cache, exa.meta.input_columns)
with tf.device(config["device"]):
input_columns, keras_inputs, preprocessed_keras_inputs = \
ColumnEncoder().generate_inputs(
exa.meta.input_columns, config["columns"])
table_network = self.create_table_network(
preprocessed_keras_inputs)
output_columns, keras_outputs, losses, loss_weights, output_metrics = \
ColumnEncoder().generate_outputs(
exa.meta.input_columns, table_network, config["columns"])
session.run(tf.tables_initializer())
dataset = DatasetUtils().create_dataset(dataset, input_columns,
output_columns, batch_size,
use_cache)
session.run(tf.global_variables_initializer())
session.run(tf.local_variables_initializer())
dataset_iterator = dataset.make_initializable_iterator()
session.run(dataset_iterator.initializer)
saver = tf.train.Saver(max_to_keep=1, save_relative_paths=True)
print("load_path", load_path, flush=True)
if load_path is not None and load_path != "":
initial_epoch = Utils().restore_model_and_get_inital_epoch(
session, saver, load_path + "/checkpoints/tmp/save")
else:
initial_epoch = 0
callbacks = Utils().create_callbacks(session, saver, save_path)
model = Model(inputs=keras_inputs, outputs=keras_outputs)
profile = config["profile"]
profile_model_options = Utils().add_profiler(
callbacks, profile, session, save_path)
print(output_metrics, flush=True)
model.compile(optimizer='rmsprop',
loss=losses,
loss_weights=loss_weights,
metrics=output_metrics,
**profile_model_options)
print(model.summary(), flush=True)
if train:
print("Starting training", flush=True)
history = model.fit(dataset_iterator,
steps_per_epoch=steps_per_epoch,
epochs=initial_epoch + epochs,
verbose=2,
callbacks=callbacks,
initial_epoch=initial_epoch)
ctx.emit(str(history.history))
print("save_url", save_url, flush=True)
if save_url != "" and save_url is not None:
tarfile = f"/tmp/save"
os.makedirs(tarfile, exist_ok=True)
self.tar_save(save_path, tarfile)
self.upload_save(save_url, tarfile)
else:
print("Starting prediction", flush=True)
for i in range(steps_per_epoch):
print(f"Predicting Batch {i}/steps_per_epoch", flush=True)
output = model.predict(dataset_iterator, steps=1)
ctx.emit(output)
class ChessModel:
"""
The model which can be trained to take observations of a game of chess and return value and policy
predictions.
Attributes:
:ivar Config config: configuration to use
:ivar Model model: the Keras model to use for predictions
:ivar digest: basically just a hash of the file containing the weights being used by this model
:ivar ChessModelAPI api: the api to use to listen for and then return this models predictions (on a pipe).
"""
def __init__(self, config):
self.config = config
self.model = None # type: Model
self.digest = None
self.api = None
def build(self):
"""
Builds the full Keras model and stores it in self.model.
"""
mc = self.config
in_x = x = Input((12, 8, 8))
# (batch, channels, height, width)
x = Conv2D(filters=mc.cnn_filter_num,
kernel_size=mc.cnn_first_filter_size,
padding="same",
data_format="channels_first",
use_bias=False,
kernel_regularizer=l2(mc.l2_reg),
name="input_conv-" + str(mc.cnn_first_filter_size) + "-" +
str(mc.cnn_filter_num))(x)
x = BatchNormalization(axis=1, name="input_batchnorm")(x)
x = Activation("relu", name="input_relu")(x)
for i in range(mc.res_layer_num):
x = self._build_residual_block(x, i + 1)
res_out = x
# for value output
x = Conv2D(filters=4,
kernel_size=1,
data_format="channels_first",
use_bias=False,
kernel_regularizer=l2(mc.l2_reg),
name="value_conv-1-4")(res_out)
x = BatchNormalization(axis=1, name="value_batchnorm")(x)
x = Activation("relu", name="value_relu")(x)
x = Flatten(name="value_flatten")(x)
x = Dense(mc.value_fc_size,
kernel_regularizer=l2(mc.l2_reg),
activation="relu",
name="value_dense")(x)
value_out = Dense(1,
kernel_regularizer=l2(mc.l2_reg),
activation="tanh",
name="value_out")(x)
self.model = Model(in_x, [value_out], name="chess_model")
def _build_residual_block(self, x, index):
# mc = self.config.model
mc = self.config
in_x = x
res_name = "res" + str(index)
x = Conv2D(filters=mc.cnn_filter_num,
kernel_size=mc.cnn_filter_size,
padding="same",
data_format="channels_first",
use_bias=False,
kernel_regularizer=l2(mc.l2_reg),
name=res_name + "_conv1-" + str(mc.cnn_filter_size) + "-" +
str(mc.cnn_filter_num))(x)
x = BatchNormalization(axis=1, name=res_name + "_batchnorm1")(x)
x = Activation("relu", name=res_name + "_relu1")(x)
x = Conv2D(filters=mc.cnn_filter_num,
kernel_size=mc.cnn_filter_size,
padding="same",
data_format="channels_first",
use_bias=False,
kernel_regularizer=l2(mc.l2_reg),
name=res_name + "_conv2-" + str(mc.cnn_filter_size) + "-" +
str(mc.cnn_filter_num))(x)
x = BatchNormalization(axis=1,
name="res" + str(index) + "_batchnorm2")(x)
x = Add(name=res_name + "_add")([in_x, x])
x = Activation("relu", name=res_name + "_relu2")(x)
return x
def compile(self, optimizer, loss, metrics):
self.model.compile(optimizer=optimizer, loss=loss, metrics=metrics)
return self.model
def fit(self, dataset, batch_size, epochs, shuffle, validation_split,
validation_data, callbacks):
self.model.fit(x=dataset,
batch_size=batch_size,
epochs=epochs,
shuffle=True,
validation_split=validation_split,
validation_data=validation_data,
callbacks=callbacks)
return self.model
def predict(self,
x,
batch_size=None,
steps=None,
callbacks=None,
max_queue_size=10,
workers=1,
use_multiprocessing=False):
value = self.model.predict(x=x,
batch_size=batch_size,
steps=steps,
callbacks=callbacks,
max_queue_size=max_queue_size,
workers=workers,
use_multiprocessing=use_multiprocessing)
return value