def train(train_generator,train_size,input_num,dims_num):
print("Start Train Job! ")
start=time.time()
inputs=InputLayer(input_shape=(input_num,dims_num),batch_size=batch_size)
layer1=Dense(100,activation="relu")
layer2=Dense(20,activation="relu")
flatten=Flatten()
layer3=Dense(2,activation="softmax",name="Output")
optimizer=Adam()
model=Sequential()
model.add(inputs)
model.add(layer1)
model.add(Dropout(0.5))
model.add(layer2)
model.add(Dropout(0.5))
model.add(flatten)
model.add(layer3)
call=TensorBoard(log_dir=log_dir,write_grads=True,histogram_freq=1)
model.compile(optimizer,loss="categorical_crossentropy",metrics=["accuracy"])
model.fit_generator(train_generator,steps_per_epoch=train_size//batch_size,epochs=epochs_num,callbacks=[call])
# model.fit_generator(train_generator, steps_per_epoch=5, epochs=5, callbacks=[call])
model.save(model_dir)
end=time.time()
print("Over train job in %f s"%(end-start))
python类InputLayer()的实例源码
def train(train_generator,train_size,input_num,dims_num):
print("Start Train Job! ")
start=time.time()
inputs=InputLayer(input_shape=(input_num,dims_num),batch_size=batch_size)
layer1=LSTM(128)
output=Dense(2,activation="softmax",name="Output")
optimizer=Adam()
model=Sequential()
model.add(inputs)
model.add(layer1)
model.add(Dropout(0.5))
model.add(output)
call=TensorBoard(log_dir=log_dir,write_grads=True,histogram_freq=1)
model.compile(optimizer,loss="categorical_crossentropy",metrics=["accuracy"])
model.fit_generator(train_generator,steps_per_epoch=train_size//batch_size,epochs=epochs_num,callbacks=[call])
# model.fit_generator(train_generator, steps_per_epoch=5, epochs=5, callbacks=[call])
model.save(model_dir)
end=time.time()
print("Over train job in %f s"%(end-start))
def fsrcnn(x, d=56, s=12, m=4, scale=3):
"""Build an FSRCNN model.
See https://arxiv.org/abs/1608.00367
"""
model = Sequential()
model.add(InputLayer(input_shape=x.shape[-3:]))
c = x.shape[-1]
f = [5, 1] + [3] * m + [1]
n = [d, s] + [s] * m + [d]
for ni, fi in zip(n, f):
model.add(Conv2D(ni, fi, padding='same',
kernel_initializer='he_normal', activation='relu'))
model.add(Conv2DTranspose(c, 9, strides=scale, padding='same',
kernel_initializer='he_normal'))
return model
def nsfsrcnn(x, d=56, s=12, m=4, scale=3, pos=1):
"""Build an FSRCNN model, but change deconv position.
See https://arxiv.org/abs/1608.00367
"""
model = Sequential()
model.add(InputLayer(input_shape=x.shape[-3:]))
c = x.shape[-1]
f1 = [5, 1] + [3] * pos
n1 = [d, s] + [s] * pos
f2 = [3] * (m - pos - 1) + [1]
n2 = [s] * (m - pos - 1) + [d]
f3 = 9
n3 = c
for ni, fi in zip(n1, f1):
model.add(Conv2D(ni, fi, padding='same',
kernel_initializer='he_normal', activation='relu'))
model.add(Conv2DTranspose(s, 3, strides=scale, padding='same',
kernel_initializer='he_normal'))
for ni, fi in zip(n2, f2):
model.add(Conv2D(ni, fi, padding='same',
kernel_initializer='he_normal', activation='relu'))
model.add(Conv2D(n3, f3, padding='same',
kernel_initializer='he_normal'))
return model
def espcn(x, f=[5, 3, 3], n=[64, 32], scale=3):
"""Build an ESPCN model.
See https://arxiv.org/abs/1609.05158
"""
assert len(f) == len(n) + 1
model = Sequential()
model.add(InputLayer(input_shape=x.shape[1:]))
c = x.shape[-1]
for ni, fi in zip(n, f):
model.add(Conv2D(ni, fi, padding='same',
kernel_initializer='he_normal', activation='tanh'))
model.add(Conv2D(c * scale ** 2, f[-1], padding='same',
kernel_initializer='he_normal'))
model.add(Conv2DSubPixel(scale))
return model
def make_model_full(inshape, num_classes, weights_file=None):
model = Sequential()
model.add(KL.InputLayer(input_shape=inshape[1:]))
# model.add(KL.Conv2D(32, (3, 3), padding='same', input_shape=inshape[1:]))
model.add(KL.Conv2D(32, (3, 3), padding='same'))
model.add(KL.Activation('relu'))
model.add(KL.Conv2D(32, (3, 3)))
model.add(KL.Activation('relu'))
model.add(KL.MaxPooling2D(pool_size=(2, 2)))
model.add(KL.Dropout(0.25))
model.add(KL.Conv2D(64, (3, 3), padding='same'))
model.add(KL.Activation('relu'))
model.add(KL.Conv2D(64, (3, 3)))
model.add(KL.Activation('relu'))
model.add(KL.MaxPooling2D(pool_size=(2, 2)))
model.add(KL.Dropout(0.25))
model.add(KL.Flatten())
model.add(KL.Dense(512))
model.add(KL.Activation('relu'))
model.add(KL.Dropout(0.5))
model.add(KL.Dense(num_classes))
model.add(KL.Activation('softmax'))
if weights_file is not None and os.path.exists(weights_file):
model.load_weights(weights_file)
return model
def make_model_small(inshape, num_classes, weights_file=None):
'''Small model for debugging device placements.'''
model = Sequential()
model.add(KL.InputLayer(input_shape=inshape[1:]))
model.add(KL.Conv2D(32, (3, 3), padding='same'))
model.add(KL.Activation('relu'))
model.add(KL.Flatten())
# model.add(Dropout(0.5))
model.add(KL.Dense(num_classes))
model.add(KL.Activation('softmax'))
if weights_file is not None and os.path.exists(weights_file):
model.load_weights(weights_file)
return model
def make_model(train_input, num_classes, weights_file=None):
'''
:param train_input: Either tensorflow Tensor or tuple/list shape. Bad style
since the parameter can be of different types, but seems Ok here.
:type train_input: tf.Tensor or tuple/list
'''
model = Sequential()
# model.add(KL.InputLayer(input_shape=inshape[1:]))
if isinstance(train_input, tf.Tensor):
model.add(KL.InputLayer(input_tensor=train_input))
else:
model.add(KL.InputLayer(input_shape=train_input))
model.add(KL.Conv2D(32, (3, 3), padding='same'))
model.add(KL.Activation('relu'))
model.add(KL.Conv2D(32, (3, 3)))
model.add(KL.Activation('relu'))
model.add(KL.MaxPooling2D(pool_size=(2, 2)))
model.add(KL.Dropout(0.25))
model.add(KL.Conv2D(64, (3, 3), padding='same'))
model.add(KL.Activation('relu'))
model.add(KL.Conv2D(64, (3, 3)))
model.add(KL.Activation('relu'))
model.add(KL.MaxPooling2D(pool_size=(2, 2)))
model.add(KL.Dropout(0.25))
model.add(KL.Flatten())
model.add(KL.Dense(512))
model.add(KL.Activation('relu'))
model.add(KL.Dropout(0.5))
model.add(KL.Dense(num_classes))
model.add(KL.Activation('softmax'))
if weights_file is not None and os.path.exists(weights_file):
model.load_weights(weights_file)
return model
def make_model_full(inshape, num_classes, weights_file=None):
model = Sequential()
model.add(KL.InputLayer(input_shape=inshape[1:]))
# model.add(KL.Conv2D(32, (3, 3), padding='same', input_shape=inshape[1:]))
model.add(KL.Conv2D(32, (3, 3), padding='same'))
model.add(KL.Activation('relu'))
model.add(KL.Conv2D(32, (3, 3)))
model.add(KL.Activation('relu'))
model.add(KL.MaxPooling2D(pool_size=(2, 2)))
model.add(KL.Dropout(0.25))
model.add(KL.Conv2D(64, (3, 3), padding='same'))
model.add(KL.Activation('relu'))
model.add(KL.Conv2D(64, (3, 3)))
model.add(KL.Activation('relu'))
model.add(KL.MaxPooling2D(pool_size=(2, 2)))
model.add(KL.Dropout(0.25))
model.add(KL.Flatten())
model.add(KL.Dense(512))
model.add(KL.Activation('relu'))
model.add(KL.Dropout(0.5))
model.add(KL.Dense(num_classes))
model.add(KL.Activation('softmax'))
if weights_file is not None and os.path.exists(weights_file):
model.load_weights(weights_file)
return model
def make_model_small(inshape, num_classes, weights_file=None):
model = Sequential()
model.add(KL.InputLayer(input_shape=inshape[1:]))
model.add(KL.Conv2D(32, (3, 3), padding='same'))
model.add(KL.Activation('relu'))
model.add(KL.Flatten())
# model.add(Dropout(0.5))
model.add(KL.Dense(num_classes))
model.add(KL.Activation('softmax'))
if weights_file is not None and os.path.exists(weights_file):
model.load_weights(weights_file)
return model
def make_model(inshape, num_classes, weights_file=None):
model = Sequential()
model.add(KL.InputLayer(input_shape=inshape[1:]))
# model.add(KL.Conv2D(32, (3, 3), padding='same', input_shape=inshape[1:]))
model.add(KL.Conv2D(32, (3, 3), padding='same'))
model.add(KL.Activation('relu'))
model.add(KL.Conv2D(32, (3, 3)))
model.add(KL.Activation('relu'))
model.add(KL.MaxPooling2D(pool_size=(2, 2)))
model.add(KL.Dropout(0.25))
model.add(KL.Conv2D(64, (3, 3), padding='same'))
model.add(KL.Activation('relu'))
model.add(KL.Conv2D(64, (3, 3)))
model.add(KL.Activation('relu'))
model.add(KL.MaxPooling2D(pool_size=(2, 2)))
model.add(KL.Dropout(0.25))
model.add(KL.Flatten())
model.add(KL.Dense(512))
model.add(KL.Activation('relu'))
model.add(KL.Dropout(0.5))
model.add(KL.Dense(num_classes))
model.add(KL.Activation('softmax'))
if weights_file is not None and os.path.exists(weights_file):
model.load_weights(weights_file)
return model
def make_model_full(inshape, num_classes, weights_file=None):
model = Sequential()
model.add(KL.InputLayer(input_shape=inshape[1:]))
# model.add(KL.Conv2D(32, (3, 3), padding='same', input_shape=inshape[1:]))
model.add(KL.Conv2D(32, (3, 3), padding='same'))
model.add(KL.Activation('relu'))
model.add(KL.Conv2D(32, (3, 3)))
model.add(KL.Activation('relu'))
model.add(KL.MaxPooling2D(pool_size=(2, 2)))
model.add(KL.Dropout(0.25))
model.add(KL.Conv2D(64, (3, 3), padding='same'))
model.add(KL.Activation('relu'))
model.add(KL.Conv2D(64, (3, 3)))
model.add(KL.Activation('relu'))
model.add(KL.MaxPooling2D(pool_size=(2, 2)))
model.add(KL.Dropout(0.25))
model.add(KL.Flatten())
model.add(KL.Dense(512))
model.add(KL.Activation('relu'))
model.add(KL.Dropout(0.5))
model.add(KL.Dense(num_classes))
model.add(KL.Activation('softmax'))
if weights_file is not None and os.path.exists(weights_file):
model.load_weights(weights_file)
return model
def make_model_small(inshape, num_classes, weights_file=None):
model = Sequential()
model.add(KL.InputLayer(input_shape=inshape[1:]))
model.add(KL.Conv2D(32, (3, 3), padding='same'))
model.add(KL.Activation('relu'))
model.add(KL.Flatten())
# model.add(Dropout(0.5))
model.add(KL.Dense(num_classes))
model.add(KL.Activation('softmax'))
if weights_file is not None and os.path.exists(weights_file):
model.load_weights(weights_file)
return model
cifar10_cnn_horovod_tfqueue.py 文件源码
项目：keras_experiments
作者: avolkov1
项目源码
文件源码
阅读 23
收藏 0
点赞 0
评论 0
def make_model(train_input, num_classes, weights_file=None):
'''
:param train_input: Either tensorflow Tensor or tuple/list shape. Bad style
since the parameter can be of different types, but seems Ok here.
:type train_input: tf.Tensor or tuple/list
'''
model = Sequential()
# model.add(KL.InputLayer(input_shape=inshape[1:]))
if isinstance(train_input, tf.Tensor):
model.add(KL.InputLayer(input_tensor=train_input))
else:
model.add(KL.InputLayer(input_shape=train_input))
model.add(KL.Conv2D(32, (3, 3), padding='same'))
model.add(KL.Activation('relu'))
model.add(KL.Conv2D(32, (3, 3)))
model.add(KL.Activation('relu'))
model.add(KL.MaxPooling2D(pool_size=(2, 2)))
model.add(KL.Dropout(0.25))
model.add(KL.Conv2D(64, (3, 3), padding='same'))
model.add(KL.Activation('relu'))
model.add(KL.Conv2D(64, (3, 3)))
model.add(KL.Activation('relu'))
model.add(KL.MaxPooling2D(pool_size=(2, 2)))
model.add(KL.Dropout(0.25))
model.add(KL.Flatten())
model.add(KL.Dense(512))
model.add(KL.Activation('relu'))
model.add(KL.Dropout(0.5))
model.add(KL.Dense(num_classes))
model.add(KL.Activation('softmax'))
if weights_file is not None and os.path.exists(weights_file):
model.load_weights(weights_file)
return model
cifar10_cnn_distrib_v2_slurm.py 文件源码
项目：keras_experiments
作者: avolkov1
项目源码
文件源码
阅读 24
收藏 0
点赞 0
评论 0
def make_model(inshape, num_classes, weights_file=None):
model = Sequential()
model.add(KL.InputLayer(input_shape=inshape[1:]))
# model.add(KL.Conv2D(32, (3, 3), padding='same', input_shape=inshape[1:]))
model.add(KL.Conv2D(32, (3, 3), padding='same'))
model.add(KL.Activation('relu'))
model.add(KL.Conv2D(32, (3, 3)))
model.add(KL.Activation('relu'))
model.add(KL.MaxPooling2D(pool_size=(2, 2)))
model.add(KL.Dropout(0.25))
model.add(KL.Conv2D(64, (3, 3), padding='same'))
model.add(KL.Activation('relu'))
model.add(KL.Conv2D(64, (3, 3)))
model.add(KL.Activation('relu'))
model.add(KL.MaxPooling2D(pool_size=(2, 2)))
model.add(KL.Dropout(0.25))
model.add(KL.Flatten())
model.add(KL.Dense(512))
model.add(KL.Activation('relu'))
model.add(KL.Dropout(0.5))
model.add(KL.Dense(num_classes))
model.add(KL.Activation('softmax'))
if weights_file is not None and os.path.exists(weights_file):
model.load_weights(weights_file)
return model
def train(train_generator,train_size,input_num,dims_num):
print("Start Train Job! ")
start=time.time()
inputs=InputLayer(input_shape=(input_num,dims_num),batch_size=batch_size)
layer1=Conv1D(64,3,activation="relu")
layer2=Conv1D(64,3,activation="relu")
layer3=Conv1D(128,3,activation="relu")
layer4=Conv1D(128,3,activation="relu")
layer5=Dense(128,activation="relu")
output=Dense(2,activation="softmax",name="Output")
optimizer=Adam()
model=Sequential()
model.add(inputs)
model.add(layer1)
model.add(layer2)
model.add(MaxPool1D(pool_size=2))
model.add(Dropout(0.5))
model.add(layer3)
model.add(layer4)
model.add(MaxPool1D(pool_size=2))
model.add(Dropout(0.5))
model.add(Flatten())
model.add(layer5)
model.add(Dropout(0.5))
model.add(output)
call=TensorBoard(log_dir=log_dir,write_grads=True,histogram_freq=1)
model.compile(optimizer,loss="categorical_crossentropy",metrics=["accuracy"])
model.fit_generator(train_generator,steps_per_epoch=train_size//batch_size,epochs=epochs_num,callbacks=[call])
# model.fit_generator(train_generator, steps_per_epoch=5, epochs=5, callbacks=[call])
model.save(model_dir)
end=time.time()
print("Over train job in %f s"%(end-start))
def bicubic(x, scale=3):
model = Sequential()
model.add(InputLayer(input_shape=x.shape[-3:]))
model.add(ImageRescale(scale, method=tf.image.ResizeMethod.BICUBIC))
return model
