[英]Why does epoch 2 take 18 times more time than epoch 1?
I have the following neural network in keras (the review of it is probably not necessary to answer my question:我在 keras 中有以下神经网络(对它的审查可能没有必要回答我的问题:
Short summary: It's a neural network that takes images as input and outputs images too.简短摘要:这是一个神经网络,将图像作为输入并输出图像。 The neural network is mostly convolutional.
神经网络主要是卷积的。 I use generators.
我使用发电机。 Also, I have two callbacks: one for TensorBoard and one for chechpoint saving
另外,我有两个回调:一个用于 TensorBoard,另一个用于保存检查点
class modelsClass(object):
def __init__(self, img_rows = 272, img_cols = 480):
self.img_rows = img_rows
self.img_cols = img_cols
def addPadding(self, layer, level): #height, width, level):
w1, h1 = self.img_cols, self.img_rows
w2, h2 = int(w1/2), int(h1/2)
w3, h3 = int(w2/2), int(h2/2)
w4, h4 = int(w3/2), int(h3/2)
h = [h1, h2, h3, h4]
w = [w1, w2, w3, w4]
# Target width and height
tw = w[level-1]
th = h[level-1]
# Source width and height
lsize = keras.int_shape(layer)
sh = lsize[1]
sw = lsize[2]
pw = (0, tw - sw)
ph = (0, th - sh)
layer = ZeroPadding2D(padding=(ph, pw), data_format="channels_last")(layer)
return layer
[I need to break the code with some text here to post the question] [我需要在这里用一些文字打破代码来发布问题]
def getmodel(self):
input_blurred = Input((self.img_rows, self.img_cols,3))
conv1 = Conv2D(64, (3, 3), activation='relu', padding='same')(input_blurred)
conv1 = Conv2D(64, (3, 3), activation='relu', padding='same')(conv1)
pool1 = MaxPooling2D(pool_size=(2, 2))(conv1)
conv2 = Conv2D(128, (3, 3), activation='relu', padding='same')(pool1)
conv2 = Conv2D(128, (3, 3), activation='relu', padding='same')(conv2)
pool2 = MaxPooling2D(pool_size=(2, 2))(conv2)
conv3 = Conv2D(256, (3, 3), activation='relu', padding='same')(pool2)
conv3 = Conv2D(256, (3, 3), activation='relu', padding='same')(conv3)
pool3 = MaxPooling2D(pool_size=(2, 2))(conv3)
conv4 = Conv2D(512, (3, 3), activation='relu', padding='same')(pool3)
conv4 = Conv2D(512, (3, 3), activation='relu', padding='same')(conv4)
pool4 = MaxPooling2D(pool_size=(2, 2))(conv4)
conv5 = Conv2D(1024, (3, 3), activation='relu', padding='same')(pool4)
conv5 = Conv2D(1024, (3, 3), activation='relu', padding='same')(conv5)
up6 = Conv2DTranspose(512, (2, 2), strides=(2, 2), padding='same')(conv5)
up6 = self.addPadding(up6,level=4)
up6 = concatenate([up6,conv4], axis=3)
conv6 = Conv2D(512, (3, 3), activation='relu', padding='same')(up6)
conv6 = Conv2D(512, (3, 3), activation='relu', padding='same')(conv6)
up7 = Conv2DTranspose(256, (2, 2), strides=(2, 2), padding='same')(conv6)
up7 = self.addPadding(up7,level=3)
up7 = concatenate([up7,conv3], axis=3)
conv7 = Conv2D(256, (3, 3), activation='relu', padding='same')(up7)
conv7 = Conv2D(256, (3, 3), activation='relu', padding='same')(conv7)
up8 = Conv2DTranspose(128, (2, 2), strides=(2, 2), padding='same')(conv7)
up8 = self.addPadding(up8,level=2)
up8 = concatenate([up8,conv2], axis=3)
conv8 = Conv2D(128, (3, 3), activation='relu', padding='same')(up8)
conv8 = Conv2D(128, (3, 3), activation='relu', padding='same')(conv8)
up9 = Conv2DTranspose(64, (2, 2), strides=(2, 2), padding='same')(conv8)
up9 = self.addPadding(up9,level=1)
up9 = concatenate([up9,conv1], axis=3)
conv9 = Conv2D(64, (3, 3), activation='relu', padding='same')(up9)
conv9 = Conv2D(64, (3, 3), activation='relu', padding='same')(conv9)
conv10 = Conv2D(3, (1, 1), activation='linear')(conv9)
model = Model(inputs=input_blurred, outputs=conv10)
return model
Then the code is:然后代码是:
models = modelsClass(720, 1280)
model = models.getmodel()
model.compile(optimizer='adam', loss='mean_absolute_error')
model_checkpoint = ModelCheckpoint('checkpoints/cp.ckpt', monitor='val_loss', verbose=0, save_best_only=False, save_weights_only=False, mode='auto', save_freq='epoch')
tensorboard_callback = tf.keras.callbacks.TensorBoard(log_dir='some_dir', histogram_freq=1)
model_history = model.fit_generator(generator_train, epochs=3,
steps_per_epoch=900,
callbacks=[tensorboard_callback, model_checkpoint],
validation_data=generator_val, validation_steps=100)
where generator_train.__len__ = 900
, generator_val.__len__ = 100
, batch size for both = 1.其中
generator_train.__len__ = 900
, generator_val.__len__ = 100
,两者的批量大小 = 1。
Time for epoch 1 is 10 minutes, while epoch 2 takes 3 hours. epoch 1 的时间为 10 分钟,epoch 2 的时间为 3 小时。 I want to know what can be the problem
我想知道可能是什么问题
Here are some general things that can reduce program speed:以下是一些可以降低程序速度的一般事项:
声明:本站的技术帖子网页,遵循CC BY-SA 4.0协议,如果您需要转载,请注明本站网址或者原文地址。任何问题请咨询:yoyou2525@163.com.