Python tf.keras卷积结构不起作用
下面的问题是我在设计一个基本的自动编码器arch时遇到的一个实际问题的简化。 下面的示例足以完全重现我的错误。 我已经试了大约两天了,但是我找不到任何办法Python tf.keras卷积结构不起作用,python,tensorflow,keras,tensorflow2.0,autoencoder,Python,Tensorflow,Keras,Tensorflow2.0,Autoencoder,下面的问题是我在设计一个基本的自动编码器arch时遇到的一个实际问题的简化。 下面的示例足以完全重现我的错误。 我已经试了大约两天了,但是我找不到任何办法 import tensorflow as tf import random import os RES = [256, 256] def generator_data(n): for i in range(n): for j in range(6): yield tf.zeros((1, 25
import tensorflow as tf
import random
import os
RES = [256, 256]
def generator_data(n):
for i in range(n):
for j in range(6):
yield tf.zeros((1, 256, 256, 3)), tf.zeros((1, 256, 256, 3))
def mymodel():
model = tf.keras.Sequential()
model.add(tf.keras.layers.Conv2D(8, (3, 3), activation='relu', padding='same'))
# 256 x 256 x 8
model.add(tf.keras.layers.MaxPooling2D((2, 2), padding='same'))
# 128 x 128 x 8
model.add(tf.keras.layers.Conv2D(16, (3, 3), activation='relu', padding='same'))
# 128 x 128 x 16
model.add(tf.keras.layers.MaxPooling2D((2, 2), padding='same'))
# 64 x 64 x 16
model.add(tf.keras.layers.Conv2D(32, (3, 3), activation='relu', padding='same'))
# 64 x 64 x 32
model.add(tf.keras.layers.MaxPooling2D((2, 2), padding='same'))
# 32 x 32 x 32
# 32 x 32 x 32
model.add(tf.keras.layers.Conv2D(32, (3, 3), activation='relu', padding='same'))
# 32 x 32 x 32
model.add(tf.keras.layers.UpSampling2D((2, 2)))
# 64 x 64 x 32
model.add(tf.keras.layers.Conv2D(16, (3, 3), activation='relu', padding='same'))
# 64 x 64 x 16
model.add(tf.keras.layers.UpSampling2D((2, 2)))
# 128 x 128 x 16
model.add(tf.keras.layers.Conv2D(8, (3, 3), activation='relu', padding='same'))
# 128 x 128 x 8
model.add(tf.keras.layers.UpSampling2D((2, 2)))
# 256 x 256 x 8
model.add(tf.keras.layers.Conv2D(1, (3, 3), activation='sigmoid', padding='same'))
return model
if __name__ == "__main__":
# import some data to play with
x_val, y_val = zip(*generator_data(20))
model = mymodel()
optimizer = tf.keras.optimizers.Adam(learning_rate=0.001)
model.compile(optimizer=optimizer, loss=tf.keras.losses.MeanSquaredError())
model(tf.zeros((1, 256, 256, 3)))
model.summary()
# generator_data(train_list)
model.fit(x=generator_data(1000),
validation_data=(list(x_val), list(y_val)),
verbose=1, epochs=1000)
首先,我有一个model.summary的奇怪行为,它包含:
Model: "sequential"
_________________________________________________________________
Layer (type) Output Shape Param #
=================================================================
conv2d (Conv2D) multiple 224
_________________________________________________________________
max_pooling2d (MaxPooling2D) multiple 0
_________________________________________________________________
conv2d_1 (Conv2D) multiple 1168
_________________________________________________________________
max_pooling2d_1 (MaxPooling2 multiple 0
_________________________________________________________________
conv2d_2 (Conv2D) multiple 4640
_________________________________________________________________
max_pooling2d_2 (MaxPooling2 multiple 0
_________________________________________________________________
conv2d_3 (Conv2D) multiple 9248
_________________________________________________________________
up_sampling2d (UpSampling2D) multiple 0
_________________________________________________________________
conv2d_4 (Conv2D) multiple 4624
_________________________________________________________________
up_sampling2d_1 (UpSampling2 multiple 0
_________________________________________________________________
conv2d_5 (Conv2D) multiple 1160
_________________________________________________________________
up_sampling2d_2 (UpSampling2 multiple 0
_________________________________________________________________
conv2d_6 (Conv2D) multiple 73
=================================================================
Total params: 21,137
Trainable params: 21,137
Non-trainable params: 0
输出形状上只有多个。
我已经查过了,但解决方法似乎不起作用。
但第二个也是更重要的是,我得到了一个错误:
ValueError: Error when checking model input: the list of Numpy arrays that you are passing to your model is not the size the model expected. Expected to see 1 array(s), for inputs ['input_1'] but instead got the following list of 120 arrays: [<tf.Tensor: shape=(1, 256, 256, 3), dtype=float32, numpy=
array([[[[0., 0., 0.],
[0., 0., 0.],
[0., 0., 0.],
...,
[0., 0., 0.],
[0., 0., 0.],
[0....
这对我来说毫无意义。我的生成器返回[batch,x-dim,y-dim,channel],我也尝试过[batch,channel,x-dim,y-dim],但也没有运气。在这种情况下,批次等于1,而不是120。
正如我所说,无论发生什么,我都无法解决/调试这些问题,因此我非常感谢您的帮助。
我对DL很陌生,但不熟悉python,我正在使用Tensorflow-2.1.0和python-3.7
非常感谢。这是工作代码
import tensorflow as tf
import random
import os
import numpy as np
RES = [256, 256]
def generator_data(n):
for i in range(n):
for j in range(1):
yield tf.zeros((1, 256, 256, 3)), tf.zeros((1, 256, 256, 3))
def mymodel():
model = tf.keras.Sequential()
model.add(tf.keras.layers.Conv2D(8, (3, 3), activation='relu', padding='same'))
# 256 x 256 x 8
model.add(tf.keras.layers.MaxPooling2D((2, 2), padding='same'))
# 128 x 128 x 8
model.add(tf.keras.layers.Conv2D(16, (3, 3), activation='relu', padding='same'))
# 128 x 128 x 16
model.add(tf.keras.layers.MaxPooling2D((2, 2), padding='same'))
# 64 x 64 x 16
model.add(tf.keras.layers.Conv2D(32, (3, 3), activation='relu', padding='same'))
# 64 x 64 x 32
model.add(tf.keras.layers.MaxPooling2D((2, 2), padding='same'))
# 32 x 32 x 32
# 32 x 32 x 32
model.add(tf.keras.layers.Conv2D(32, (3, 3), activation='relu', padding='same'))
# 32 x 32 x 32
model.add(tf.keras.layers.UpSampling2D((2, 2)))
# 64 x 64 x 32
model.add(tf.keras.layers.Conv2D(16, (3, 3), activation='relu', padding='same'))
# 64 x 64 x 16
model.add(tf.keras.layers.UpSampling2D((2, 2)))
# 128 x 128 x 16
model.add(tf.keras.layers.Conv2D(8, (3, 3), activation='relu', padding='same'))
# 128 x 128 x 8
model.add(tf.keras.layers.UpSampling2D((2, 2)))
# 256 x 256 x 8
model.add(tf.keras.layers.Conv2D(1, (3, 3), activation='sigmoid', padding='same'))
return model
if __name__ == "__main__":
# import some data to play with
z = list(zip(*generator_data(2)))
x_val = z[0][0]
y_val = z[0][1]
model = mymodel()
optimizer = tf.keras.optimizers.Adam(learning_rate=0.001)
model.compile(optimizer=optimizer, loss=tf.keras.losses.MeanSquaredError())
model(tf.zeros((1, 256, 256, 3)))
model.summary()
print(x_val.numpy().shape)
print(y_val.numpy().shape)
model.fit(x=generator_data(10),
validation_data=(x_val, y_val),
verbose=1, epochs=1)
您以错误的方式对生成器使用解压缩。我将输出类型转换为一个列表,以便可以订阅。其中一个有用的技巧是在每个步骤中打印X,y的形状和长度,以找出bug所在的位置
更新:
是的,确实如此,但您需要传递一个形状为[batch,256,256,3]的张量。但是如果a是一个列表,并且a[0]具有形状[1,256,256,3],那么您需要将a[0]传递给模型,这就是我所做的。但是,你通过了a。但是a是一个列表,不是一个numpy数组/张量,即使我们将它键入一个numpy数组,我们也会得到shape=1,1,256,256,3-这是无效的
另外,在生成器_数据中,为什么要使用不必要的第二个循环
def generator_data(n):
for i in range(n):
for j in range(1): # ??????? Why?
yield tf.zeros((1, 256, 256, 3)), tf.zeros((1, 256, 256, 3))
这是工作代码
import tensorflow as tf
import random
import os
import numpy as np
RES = [256, 256]
def generator_data(n):
for i in range(n):
for j in range(1):
yield tf.zeros((1, 256, 256, 3)), tf.zeros((1, 256, 256, 3))
def mymodel():
model = tf.keras.Sequential()
model.add(tf.keras.layers.Conv2D(8, (3, 3), activation='relu', padding='same'))
# 256 x 256 x 8
model.add(tf.keras.layers.MaxPooling2D((2, 2), padding='same'))
# 128 x 128 x 8
model.add(tf.keras.layers.Conv2D(16, (3, 3), activation='relu', padding='same'))
# 128 x 128 x 16
model.add(tf.keras.layers.MaxPooling2D((2, 2), padding='same'))
# 64 x 64 x 16
model.add(tf.keras.layers.Conv2D(32, (3, 3), activation='relu', padding='same'))
# 64 x 64 x 32
model.add(tf.keras.layers.MaxPooling2D((2, 2), padding='same'))
# 32 x 32 x 32
# 32 x 32 x 32
model.add(tf.keras.layers.Conv2D(32, (3, 3), activation='relu', padding='same'))
# 32 x 32 x 32
model.add(tf.keras.layers.UpSampling2D((2, 2)))
# 64 x 64 x 32
model.add(tf.keras.layers.Conv2D(16, (3, 3), activation='relu', padding='same'))
# 64 x 64 x 16
model.add(tf.keras.layers.UpSampling2D((2, 2)))
# 128 x 128 x 16
model.add(tf.keras.layers.Conv2D(8, (3, 3), activation='relu', padding='same'))
# 128 x 128 x 8
model.add(tf.keras.layers.UpSampling2D((2, 2)))
# 256 x 256 x 8
model.add(tf.keras.layers.Conv2D(1, (3, 3), activation='sigmoid', padding='same'))
return model
if __name__ == "__main__":
# import some data to play with
z = list(zip(*generator_data(2)))
x_val = z[0][0]
y_val = z[0][1]
model = mymodel()
optimizer = tf.keras.optimizers.Adam(learning_rate=0.001)
model.compile(optimizer=optimizer, loss=tf.keras.losses.MeanSquaredError())
model(tf.zeros((1, 256, 256, 3)))
model.summary()
print(x_val.numpy().shape)
print(y_val.numpy().shape)
model.fit(x=generator_data(10),
validation_data=(x_val, y_val),
verbose=1, epochs=1)
您以错误的方式对生成器使用解压缩。我将输出类型转换为一个列表,以便可以订阅。其中一个有用的技巧是在每个步骤中打印X,y的形状和长度,以找出bug所在的位置
更新:
是的,确实如此,但您需要传递一个形状为[batch,256,256,3]的张量。但是如果a是一个列表,并且a[0]具有形状[1,256,256,3],那么您需要将a[0]传递给模型,这就是我所做的。但是,你通过了a。但是a是一个列表,不是一个numpy数组/张量,即使我们将它键入一个numpy数组,我们也会得到shape=1,1,256,256,3-这是无效的
另外,在生成器_数据中,为什么要使用不必要的第二个循环
def generator_data(n):
for i in range(n):
for j in range(1): # ??????? Why?
yield tf.zeros((1, 256, 256, 3)), tf.zeros((1, 256, 256, 3))
通过每晚更新到tf-2.2并使用tf.data模块,我成功地解决了这些问题 如果您有相同的问题,请查看此处:
import tensorflow as tf
import random
import os
from functools import partial
RES = [256, 256]
def generator_data(n):
for i in range(n):
for j in range(6):
yield tf.zeros((1, 256, 256, 3)), tf.zeros((1, 256, 256, 3))
def generator_data_val(n):
for i in range(n):
for j in range(6):
yield tf.zeros((256, 256, 3)), tf.zeros((256, 256, 3))
def model():
model = tf.keras.Sequential()
model.add(tf.keras.layers.Conv2D(8, (3, 3), activation='relu', padding='same', input_shape=(256, 256, 3)))
# 256 x 256 x 8
model.add(tf.keras.layers.MaxPooling2D((2, 2), padding='same'))
# 128 x 128 x 8
model.add(tf.keras.layers.Conv2D(16, (3, 3), activation='relu', padding='same'))
# 128 x 128 x 16
model.add(tf.keras.layers.MaxPooling2D((2, 2), padding='same'))
# 64 x 64 x 16
model.add(tf.keras.layers.Conv2D(32, (3, 3), activation='relu', padding='same'))
# 64 x 64 x 32
model.add(tf.keras.layers.MaxPooling2D((2, 2), padding='same'))
# 32 x 32 x 32
# 32 x 32 x 32
model.add(tf.keras.layers.Conv2D(32, (3, 3), activation='relu', padding='same'))
# 32 x 32 x 32
model.add(tf.keras.layers.UpSampling2D((2, 2)))
# 64 x 64 x 32
model.add(tf.keras.layers.Conv2D(16, (3, 3), activation='relu', padding='same'))
# 64 x 64 x 16
model.add(tf.keras.layers.UpSampling2D((2, 2)))
# 128 x 128 x 16
model.add(tf.keras.layers.Conv2D(8, (3, 3), activation='relu', padding='same'))
# 128 x 128 x 8
model.add(tf.keras.layers.UpSampling2D((2, 2)))
# 256 x 256 x 8
model.add(tf.keras.layers.Conv2D(1, (3, 3), activation='sigmoid', padding='same'))
return model
if __name__ == "__main__":
# import some data to play with
x_val, y_val = zip(*generator_data_val(5))
x_val, y_val = list(x_val), list(y_val)
model = model()
optimizer = tf.keras.optimizers.Adam(learning_rate=0.001)
model.compile(optimizer=optimizer, loss=tf.keras.losses.MeanSquaredError())
model(tf.zeros((1, 256, 256, 3)))
model.summary()
train_dataset = generator_data(5)
gen = partial(generator_data, n=5)
train_dataset = tf.data.Dataset.from_generator(
gen, output_types=(tf.float32, tf.float32),
output_shapes=(tf.TensorShape([1, 256, 256, 3]), tf.TensorShape([1, 256, 256, 3]))).repeat()
val_dataset = tf.data.Dataset.from_tensor_slices((x_val, y_val)).batch(2)
# generator_data(train_list)
model.fit(x=train_dataset,
steps_per_epoch=40,
validation_data=val_dataset,
verbose=1, epochs=1000)
通过每晚更新到tf-2.2并使用tf.data模块,我成功地解决了这些问题 如果您有相同的问题,请查看此处:
import tensorflow as tf
import random
import os
from functools import partial
RES = [256, 256]
def generator_data(n):
for i in range(n):
for j in range(6):
yield tf.zeros((1, 256, 256, 3)), tf.zeros((1, 256, 256, 3))
def generator_data_val(n):
for i in range(n):
for j in range(6):
yield tf.zeros((256, 256, 3)), tf.zeros((256, 256, 3))
def model():
model = tf.keras.Sequential()
model.add(tf.keras.layers.Conv2D(8, (3, 3), activation='relu', padding='same', input_shape=(256, 256, 3)))
# 256 x 256 x 8
model.add(tf.keras.layers.MaxPooling2D((2, 2), padding='same'))
# 128 x 128 x 8
model.add(tf.keras.layers.Conv2D(16, (3, 3), activation='relu', padding='same'))
# 128 x 128 x 16
model.add(tf.keras.layers.MaxPooling2D((2, 2), padding='same'))
# 64 x 64 x 16
model.add(tf.keras.layers.Conv2D(32, (3, 3), activation='relu', padding='same'))
# 64 x 64 x 32
model.add(tf.keras.layers.MaxPooling2D((2, 2), padding='same'))
# 32 x 32 x 32
# 32 x 32 x 32
model.add(tf.keras.layers.Conv2D(32, (3, 3), activation='relu', padding='same'))
# 32 x 32 x 32
model.add(tf.keras.layers.UpSampling2D((2, 2)))
# 64 x 64 x 32
model.add(tf.keras.layers.Conv2D(16, (3, 3), activation='relu', padding='same'))
# 64 x 64 x 16
model.add(tf.keras.layers.UpSampling2D((2, 2)))
# 128 x 128 x 16
model.add(tf.keras.layers.Conv2D(8, (3, 3), activation='relu', padding='same'))
# 128 x 128 x 8
model.add(tf.keras.layers.UpSampling2D((2, 2)))
# 256 x 256 x 8
model.add(tf.keras.layers.Conv2D(1, (3, 3), activation='sigmoid', padding='same'))
return model
if __name__ == "__main__":
# import some data to play with
x_val, y_val = zip(*generator_data_val(5))
x_val, y_val = list(x_val), list(y_val)
model = model()
optimizer = tf.keras.optimizers.Adam(learning_rate=0.001)
model.compile(optimizer=optimizer, loss=tf.keras.losses.MeanSquaredError())
model(tf.zeros((1, 256, 256, 3)))
model.summary()
train_dataset = generator_data(5)
gen = partial(generator_data, n=5)
train_dataset = tf.data.Dataset.from_generator(
gen, output_types=(tf.float32, tf.float32),
output_shapes=(tf.TensorShape([1, 256, 256, 3]), tf.TensorShape([1, 256, 256, 3]))).repeat()
val_dataset = tf.data.Dataset.from_tensor_slices((x_val, y_val)).batch(2)
# generator_data(train_list)
model.fit(x=train_dataset,
steps_per_epoch=40,
validation_data=val_dataset,
verbose=1, epochs=1000)
谢谢你的回复。你能提供一个工作示例来实现我的目标吗?对我来说,这只是验证数据问题的一个证明,谢谢。你是从代码中读到的还是从经验中读到的?更重要的是,我不明白为什么输出形状是多重的,以及我应该如何提供数据进行验证。现在你只提供一个张量,这不是我想做的。如果我运行:x_val,y_val=zip*generator_data20a=listx_val b=listy_val,我会得到一个张量列表,在我看来应该是完全正确的。基本上,这与您所做的是等效的,但是您只提供了一个用于验证的张量,而不是一个列表或它们的集合,这是预期的结果。Pdb printtypea Pdb printtypea[0]Pdb printa[0]。形状1、256、256、3 PdbI不使用不必要的第二个循环。在我的初始代码中,我有范围6。我试图复制我的数据,因为这是一个用于测试的示例。无论如何,我找到了一个解决方案,但实际上它必须首先使用tensorflow版本。我首先通过更新到nightly 2.2,然后使用tf.data模块解决了整个问题。谢谢你的回复。你能提供一个工作示例来实现我的目标吗?对我来说,这只是验证数据问题的一个证明,谢谢。你是从代码中读到的还是从经验中读到的?更重要的是,我不明白为什么输出形状是多重的,以及我应该如何提供数据进行验证。现在你只提供一个张量,这不是我想做的。如果我运行:x_val,y_val=zip*generator_data20a=listx_val b=listy_val,我会得到一个张量列表,在我看来应该是完全正确的。基本上,这与您所做的是等效的,但是您只提供了一个用于验证的张量,而不是一个列表或它们的集合,这是预期的结果。Pdb printtypea Pdb printtypea[0]Pdb printa[0]。形状1、256、256、3 PdbI不使用不必要的第二个循环。在我的初始代码中,我有范围6。我试图复制我的数据,因为这是一个用于测试的示例。无论如何,我找到了一个解决方案,但实际上它必须首先使用tensorflow版本。我 首先通过更新到nightly 2.2,然后使用tf.data模块修复了整个问题。