質問編集履歴

3 誤字の修正

SuzuAya score 47

2019/04/18 21:13  投稿

Python3 VInvalidArgumentError (see above for traceback): Incompatible shapesのエラー解消方法について

### 前提・実現したいこと

KerasのVAEを自作データセットで実装中、以下のようなエラーが出ました。該当の部分を見ても、どう修正したら良いか分からず、質問させて頂きました。

### 発生している問題・エラーメッセージ

InvalidArgumentError                     Traceback (most recent call last)

InvalidArgumentError: Incompatible shapes: [12800] vs. [450]

### 該当のソースコード

from __future__ import absolute_import

from __future__ import division

from __future__ import print_function

from keras.layers import Dense, Input

from keras.layers import Conv2D, Flatten, Lambda

from keras.layers import Reshape, Conv2DTranspose

from keras.models import Model

from keras.losses import mse, binary_crossentropy

from keras.utils import plot_model

from keras import backend as K

from keras import optimizers

import numpy as np

import matplotlib.pyplot as plt

import argparse

import tensorflow as tf

import random as rn

import os

import easydict

import warnings

warnings.filterwarnings('ignore')

%matplotlib inline

def sampling(args):

z_mean, z_log_var = args

batch = K.shape(z_mean)[0]

dim = K.int_shape(z_mean)[1]

# by default, random_normal has mean=0 and std=1.0

epsilon = K.random_normal(shape=(batch, dim))

return z_mean + K.exp(0.5 * z_log_var) * epsilon

def plot_results(models,

data,

batch_size=50,

model_name="vae_mnist"):

encoder, decoder = models

os.makedirs(model_name, exist_ok=True)

filename = os.path.join(model_name, "vae_mean.png")

z_mean, _, _ = encoder.predict(x_test,

batch_size=batch_size)

plt.figure(figsize=(12, 10))

plt.scatter(z_mean[:, 0], z_mean[:, 1])

plt.colorbar()

plt.xlabel("z[0]")

plt.ylabel("z[1]")

plt.savefig(filename)

plt.show()

filename = os.path.join(model_name, "digits_over_latent.png")

n = 30

digit_size = 224

figure = np.zeros((digit_size * n, digit_size * n))

grid_x = np.linspace(-4, 4, n)

grid_y = np.linspace(-4, 4, n)[::-1]

for i, yi in enumerate(grid_y):

for j, xi in enumerate(grid_x):

z_sample = np.array([[xi, yi]])

x_decoded = decoder.predict(z_sample)

digit = x_decoded[0].reshape(digit_size, digit_size)

figure[i * digit_size: (i + 1) * digit_size,

j * digit_size: (j + 1) * digit_size] = digit

plt.figure(figsize=(10, 10))

start_range = digit_size // 2

end_range = n * digit_size + start_range + 1

pixel_range = np.arange(start_range, end_range, digit_size)

sample_range_x = np.round(grid_x, 1)

sample_range_y = np.round(grid_y, 1)

plt.xticks(pixel_range, sample_range_x)

plt.yticks(pixel_range, sample_range_y)

plt.xlabel("z[0]")

plt.ylabel("z[1]")

plt.imshow(figure, cmap='Greys_r')

plt.savefig(filename)

plt.show()

x_train_tom = np.load('./folder_a.npy')

x_test_tom = np.load('./folder_b.npy')

image_size = x_train_tom.shape[1]

x_train = np.reshape(x_train_tom, [-1, image_size, image_size, 1])

x_test = np.reshape(x_test_tom, [-1, image_size, image_size, 1])

x_train = x_train.astype('float32') / 255

x_test = x_test.astype('float32') / 255

print(x_train.shape,x_test.shape)

input_shape = (image_size,image_size, 1)

batch_size = 50

kernel_size = 3

filters = 16

latent_dim = 2

epochs = 50

inputs = Input(shape=input_shape, name='encoder_input')

x = inputs

for i in range(4):

filters *= 2

x = Conv2D(filters=filters,

kernel_size=kernel_size,

activation='relu',

strides=2,

padding='same')(x)

shape = K.int_shape(x)

x = Flatten()(x)

x = Dense(64, activation='relu')(x)

z_mean = Dense(latent_dim, name='z_mean')(x)

z_log_var = Dense(latent_dim, name='z_log_var')(x)

z = Lambda(sampling, output_shape=(latent_dim,), name='z')([z_mean, z_log_var])

encoder = Model(inputs, [z_mean, z_log_var, z], name='encoder')

encoder.summary()

plot_model(encoder, to_file='vae_cnn_encoder.png', show_shapes=True)

latent_inputs = Input(shape=(latent_dim,), name='z_sampling')

x = Dense(shape[1] * shape[2] * shape[3], activation='relu')(latent_inputs)

x = Reshape((shape[1], shape[2], shape[3]))(x)

for i in range(4):

x = Conv2DTranspose(filters=filters,

kernel_size=kernel_size,

activation='relu',

strides=2,

padding='same')(x)

filters //= 2

outputs = Conv2DTranspose(filters=1,

kernel_size=kernel_size,

activation='sigmoid',

padding='same',

name='decoder_output')(x)

decoder = Model(latent_inputs, outputs, name='decoder')

decoder.summary()

plot_model(decoder, to_file='vae_cnn_decoder.png', show_shapes=True)

outputs = decoder(encoder(inputs)[2])

vae = Model(inputs, outputs, name='vae')

def plot_history(history):

plt.plot(history.history['loss'])

plt.plot(history.history['val_loss'])

plt.title('model accuracy')

plt.xlabel('epoch')

plt.ylabel('accuracy')

plt.legend(['acc', 'val_acc'], loc='lower right')

plt.show()

plt.plot(history.history['loss'])

plt.plot(history.history['val_loss'])

plt.title('model loss')

plt.xlabel('epoch')

plt.ylabel('loss')

plt.legend(['loss', 'val_loss'], loc='lower right')

plt.savefig('loss.png') # -----(2)

plt.show()

if __name__ == '__main__':

args = easydict.EasyDict({

"batchsize": 50,

"epoch": 50,

"gpu": 0,

"out": "result",

"resume": False,

"unit": 1000

})

models = (encoder, decoder)

os.environ['PYTHONHASHSEED'] = '0'

np.random.seed(5)

rn.seed(5)

config = tf.ConfigProto(

gpu_options=tf.GPUOptions(

visible_device_list="0,1",

allow_growth=True

)

)

tf.set_random_seed(5)

sess = tf.Session(graph=tf.get_default_graph(), config=config)

K.set_session(sess)

reconstruction_loss = binary_crossentropy(K.flatten(inputs),

K.flatten(outputs))

reconstruction_loss *= image_size * image_size

kl_loss = 1 + z_log_var - K.square(z_mean) - K.exp(z_log_var)

kl_loss = K.sum(kl_loss, axis=-1)

kl_loss *= -0.5

vae_loss = K.mean(reconstruction_loss + kl_loss)

vae.add_loss(vae_loss)

Adam = optimizers.Adam(lr=0.0005)

vae.compile(optimizer=Adam)

vae.summary()

plot_model(vae, to_file='vae_cnn.png', show_shapes=True)

history = vae.fit(x_train,

epochs=epochs,

batch_size=batch_size,

validation_data=(x_test, None))

open('vae_cnn.json', "w").write(vae.to_json())

vae.save('vae_cnn.h5')

plot_results(models, data, batch_size=batch_size, model_name="vae_cnn")

plot_history(history)

#補足

kerasやtensorflowのバージョンが問題になっている場合もあるようですが、上手くいった人のバージョンに変更しても変化がありませんでした。

コードが長くてお手数をおかけしますが、アドバイス頂けると幸いです。どうぞよろしくお願い致します。

Python 3.x 16151 questions Python 3はPythonプログラミング言語の最新バージョンであり、2008年12月3日にリリースされました。 Myタグに追加

2 誤字の修正

SuzuAya score 47

2019/04/18 21:13  投稿

Python3 VInvalidArgumentError (see above for traceback): Incompatible shapesのエラー解消方法について

### 前提・実現したいこと

KerasのVAEを自作データセットで実装中、以下のようなエラーが出ました。該当の部分を見ても、どう修正したら良いか分からず、質問させて頂きました。

### 発生している問題・エラーメッセージ

InvalidArgumentError                     Traceback (most recent call last)

InvalidArgumentError: Incompatible shapes: [12800] vs. [450]

### 該当のソースコード

from __future__ import absolute_import

from __future__ import division

from __future__ import print_function

from keras.layers import Dense, Input

from keras.layers import Conv2D, Flatten, Lambda

from keras.layers import Reshape, Conv2DTranspose

from keras.models import Model

from keras.losses import mse, binary_crossentropy

from keras.utils import plot_model

from keras import backend as K

from keras import optimizers

import numpy as np

import matplotlib.pyplot as plt

import argparse

import tensorflow as tf

import random as rn

import os

import easydict

import warnings

warnings.filterwarnings('ignore')

%matplotlib inline

def sampling(args):

z_mean, z_log_var = args

batch = K.shape(z_mean)[0]

dim = K.int_shape(z_mean)[1]

# by default, random_normal has mean=0 and std=1.0

epsilon = K.random_normal(shape=(batch, dim))

return z_mean + K.exp(0.5 * z_log_var) * epsilon

def plot_results(models,

data,

batch_size=50,

model_name="vae_mnist"):

encoder, decoder = models

#x_test, y_test = data

os.makedirs(model_name, exist_ok=True)

filename = os.path.join(model_name, "vae_mean.png")

z_mean, _, _ = encoder.predict(x_test,

batch_size=batch_size)

plt.figure(figsize=(12, 10))

plt.scatter(z_mean[:, 0], z_mean[:, 1])

plt.colorbar()

plt.xlabel("z[0]")

plt.ylabel("z[1]")

plt.savefig(filename)

plt.show()

filename = os.path.join(model_name, "digits_over_latent.png")

n = 30

digit_size = 224

figure = np.zeros((digit_size * n, digit_size * n))

grid_x = np.linspace(-4, 4, n)

grid_y = np.linspace(-4, 4, n)[::-1]

for i, yi in enumerate(grid_y):

for j, xi in enumerate(grid_x):

z_sample = np.array([[xi, yi]])

x_decoded = decoder.predict(z_sample)

digit = x_decoded[0].reshape(digit_size, digit_size)

figure[i * digit_size: (i + 1) * digit_size,

j * digit_size: (j + 1) * digit_size] = digit

plt.figure(figsize=(10, 10))

start_range = digit_size // 2

end_range = n * digit_size + start_range + 1

pixel_range = np.arange(start_range, end_range, digit_size)

sample_range_x = np.round(grid_x, 1)

sample_range_y = np.round(grid_y, 1)

plt.xticks(pixel_range, sample_range_x)

plt.yticks(pixel_range, sample_range_y)

plt.xlabel("z[0]")

plt.ylabel("z[1]")

plt.imshow(figure, cmap='Greys_r')

plt.savefig(filename)

plt.show()

x_train_tom = np.load('./folder_a.npy')

x_test_tom = np.load('./folder_b.npy')

image_size = x_train_tom.shape[1]

x_train = np.reshape(x_train_tom, [-1, image_size, image_size, 1])

x_test = np.reshape(x_test_tom, [-1, image_size, image_size, 1])

x_train = x_train.astype('float32') / 255

x_test = x_test.astype('float32') / 255

print(x_train.shape,x_test.shape)

input_shape = (image_size,image_size, 1)

batch_size = 50

kernel_size = 3

filters = 16

latent_dim = 2

epochs = 50

inputs = Input(shape=input_shape, name='encoder_input')

x = inputs

for i in range(4):

filters *= 2

x = Conv2D(filters=filters,

kernel_size=kernel_size,

activation='relu',

strides=2,

padding='same')(x)

shape = K.int_shape(x)

x = Flatten()(x)

x = Dense(64, activation='relu')(x)

z_mean = Dense(latent_dim, name='z_mean')(x)

z_log_var = Dense(latent_dim, name='z_log_var')(x)

z = Lambda(sampling, output_shape=(latent_dim,), name='z')([z_mean, z_log_var])

encoder = Model(inputs, [z_mean, z_log_var, z], name='encoder')

encoder.summary()

plot_model(encoder, to_file='vae_cnn_encoder.png', show_shapes=True)

latent_inputs = Input(shape=(latent_dim,), name='z_sampling')

x = Dense(shape[1] * shape[2] * shape[3], activation='relu')(latent_inputs)

x = Reshape((shape[1], shape[2], shape[3]))(x)

for i in range(4):

x = Conv2DTranspose(filters=filters,

kernel_size=kernel_size,

activation='relu',

strides=2,

padding='same')(x)

filters //= 2

outputs = Conv2DTranspose(filters=1,

kernel_size=kernel_size,

activation='sigmoid',

padding='same',

name='decoder_output')(x)

decoder = Model(latent_inputs, outputs, name='decoder')

decoder.summary()

plot_model(decoder, to_file='vae_cnn_decoder.png', show_shapes=True)

outputs = decoder(encoder(inputs)[2])

vae = Model(inputs, outputs, name='vae')

def plot_history(history):

plt.plot(history.history['loss'])

plt.plot(history.history['val_loss'])

plt.title('model accuracy')

plt.xlabel('epoch')

plt.ylabel('accuracy')

plt.legend(['acc', 'val_acc'], loc='lower right')

plt.show()

plt.plot(history.history['loss'])

plt.plot(history.history['val_loss'])

plt.title('model loss')

plt.xlabel('epoch')

plt.ylabel('loss')

plt.legend(['loss', 'val_loss'], loc='lower right')

plt.savefig('loss.png') # -----(2)

plt.show()

if __name__ == '__main__':

args = easydict.EasyDict({

"batchsize": 50,

"epoch": 50,

"gpu": 0,

"out": "result",

"resume": False,

"unit": 1000

})

models = (encoder, decoder)

os.environ['PYTHONHASHSEED'] = '0'

np.random.seed(5)

rn.seed(5)

config = tf.ConfigProto(

gpu_options=tf.GPUOptions(

visible_device_list="0,1",

allow_growth=True

)

)

tf.set_random_seed(5)

sess = tf.Session(graph=tf.get_default_graph(), config=config)

K.set_session(sess)

reconstruction_loss = binary_crossentropy(K.flatten(inputs),

K.flatten(outputs))

reconstruction_loss *= image_size * image_size

kl_loss = 1 + z_log_var - K.square(z_mean) - K.exp(z_log_var)

kl_loss = K.sum(kl_loss, axis=-1)

kl_loss *= -0.5

vae_loss = K.mean(reconstruction_loss + kl_loss)

vae.add_loss(vae_loss)

Adam = optimizers.Adam(lr=0.0005)

vae.compile(optimizer=Adam)

vae.summary()

plot_model(vae, to_file='vae_cnn.png', show_shapes=True)

history = vae.fit(x_train,

epochs=epochs,

batch_size=batch_size,

validation_data=(x_test, None))

open('vae_cnn.json', "w").write(vae.to_json())

vae.save('vae_cnn.h5')

plot_results(models, data, batch_size=batch_size, model_name="vae_cnn")

plot_history(history)

#補足

kerasやtensorflowのバージョンが問題になっている場合もあるようですが、上手くいった人のバージョンに変更しても変化がありませんでした。

コードが長くてお手数をおかけしますが、アドバイス頂けると幸いです。どうぞよろしくお願い致します。

Python 3.x 16151 questions Python 3はPythonプログラミング言語の最新バージョンであり、2008年12月3日にリリースされました。 Myタグに追加

1 エラー内容の変更

SuzuAya score 47

2019/04/18 21:12  投稿

Python3 ValueError: Input 0 is incompatible with layer conv2d_61のエラー解消方法について

Python3 VInvalidArgumentError (see above for traceback): Incompatible shapesのエラー解消方法について

### 前提・実現したいこと

KerasのVAEを自作データセットで実装中、以下のようなエラーが出ました。該当の部分を見ても、どう修正したら良いか分からず、また、似たような質問がなかったため質問させて頂きました。

https://github.com/keras-team/keras/blob/master/examples/variational_autoencoder.py

KerasのVAEを自作データセットで実装中、以下のようなエラーが出ました。該当の部分を見ても、どう修正したら良いか分からず、質問させて頂きました。

### 発生している問題・エラーメッセージ

ValueError: Input 0 is incompatible with layer conv2d_61: expected ndim=4, found ndim=2

InvalidArgumentError                     Traceback (most recent call last)

InvalidArgumentError: Incompatible shapes: [12800] vs. [450]

### 該当のソースコード

# build encoder model

from __future__ import absolute_import

from __future__ import division

from __future__ import print_function

from keras.layers import Dense, Input

from keras.layers import Conv2D, Flatten, Lambda

from keras.layers import Reshape, Conv2DTranspose

from keras.models import Model

from keras.losses import mse, binary_crossentropy

from keras.utils import plot_model

from keras import backend as K

from keras import optimizers

import numpy as np

import matplotlib.pyplot as plt

import argparse

import tensorflow as tf

import random as rn

import os

import easydict

import warnings

warnings.filterwarnings('ignore')

%matplotlib inline

def sampling(args):

z_mean, z_log_var = args

batch = K.shape(z_mean)[0]

dim = K.int_shape(z_mean)[1]

# by default, random_normal has mean=0 and std=1.0

epsilon = K.random_normal(shape=(batch, dim))

return z_mean + K.exp(0.5 * z_log_var) * epsilon

def plot_results(models,

data,

batch_size=50,

model_name="vae_mnist"):

encoder, decoder = models

#x_test, y_test = data

os.makedirs(model_name, exist_ok=True)

filename = os.path.join(model_name, "vae_mean.png")

z_mean, _, _ = encoder.predict(x_test,

batch_size=batch_size)

plt.figure(figsize=(12, 10))

plt.scatter(z_mean[:, 0], z_mean[:, 1])

plt.colorbar()

plt.xlabel("z[0]")

plt.ylabel("z[1]")

plt.savefig(filename)

plt.show()

filename = os.path.join(model_name, "digits_over_latent.png")

n = 30

digit_size = 224

figure = np.zeros((digit_size * n, digit_size * n))

grid_x = np.linspace(-4, 4, n)

grid_y = np.linspace(-4, 4, n)[::-1]

for i, yi in enumerate(grid_y):

for j, xi in enumerate(grid_x):

z_sample = np.array([[xi, yi]])

x_decoded = decoder.predict(z_sample)

digit = x_decoded[0].reshape(digit_size, digit_size)

figure[i * digit_size: (i + 1) * digit_size,

j * digit_size: (j + 1) * digit_size] = digit

plt.figure(figsize=(10, 10))

start_range = digit_size // 2

end_range = n * digit_size + start_range + 1

pixel_range = np.arange(start_range, end_range, digit_size)

sample_range_x = np.round(grid_x, 1)

sample_range_y = np.round(grid_y, 1)

plt.xticks(pixel_range, sample_range_x)

plt.yticks(pixel_range, sample_range_y)

plt.xlabel("z[0]")

plt.ylabel("z[1]")

plt.imshow(figure, cmap='Greys_r')

plt.savefig(filename)

plt.show()

x_train_tom = np.load('./folder_a.npy')

x_test_tom = np.load('./folder_b.npy')

image_size = x_train_tom.shape[1]

x_train = np.reshape(x_train_tom, [-1, image_size, image_size, 1])

x_test = np.reshape(x_test_tom, [-1, image_size, image_size, 1])

x_train = x_train.astype('float32') / 255

x_test = x_test.astype('float32') / 255

print(x_train.shape,x_test.shape)

input_shape = (image_size,image_size, 1)

batch_size = 50

kernel_size = 3

filters = 16

latent_dim = 2

epochs = 50

inputs = Input(shape=input_shape, name='encoder_input')

x = inputs

for i in range(4):

filters *= 2

x = Conv2D(filters=filters,kernel_size=kernel_size,activation='relu',strides=2,padding='same')(x)

x = Conv2D(filters=filters,

kernel_size=kernel_size,

activation='relu',

strides=2,

padding='same')(x)

shape = K.int_shape(x)

x = Flatten()(x)

x = Dense(64, activation='relu')(x)

z_mean = Dense(latent_dim, name='z_mean')(x)

z_log_var = Dense(latent_dim, name='z_log_var')(x)

z = Lambda(sampling, output_shape=(latent_dim,), name='z')([z_mean, z_log_var])

encoder = Model(inputs, [z_mean, z_log_var, z], name='encoder')

encoder.summary()

plot_model(encoder, to_file='vae_cnn_encoder.png', show_shapes=True)

latent_inputs = Input(shape=(latent_dim,), name='z_sampling')

x = Dense(shape[1] * shape[2] * shape[3], activation='relu')(latent_inputs)

x = Reshape((shape[1], shape[2], shape[3]))(x)

for i in range(4):

x = Conv2DTranspose(filters=filters,

kernel_size=kernel_size,

activation='relu',

strides=2,

padding='same')(x)

filters //= 2

outputs = Conv2DTranspose(filters=1,

kernel_size=kernel_size,

activation='sigmoid',

padding='same',

name='decoder_output')(x)

decoder = Model(latent_inputs, outputs, name='decoder')

decoder.summary()

plot_model(decoder, to_file='vae_cnn_decoder.png', show_shapes=True)

outputs = decoder(encoder(inputs)[2])

vae = Model(inputs, outputs, name='vae')

def plot_history(history):

plt.plot(history.history['loss'])

plt.plot(history.history['val_loss'])

plt.title('model accuracy')

plt.xlabel('epoch')

plt.ylabel('accuracy')

plt.legend(['acc', 'val_acc'], loc='lower right')

plt.show()

plt.plot(history.history['loss'])

plt.plot(history.history['val_loss'])

plt.title('model loss')

plt.xlabel('epoch')

plt.ylabel('loss')

plt.legend(['loss', 'val_loss'], loc='lower right')

plt.savefig('loss.png') # -----(2)

plt.show()

if __name__ == '__main__':

args = easydict.EasyDict({

"batchsize": 50,

"epoch": 50,

"gpu": 0,

"out": "result",

"resume": False,

"unit": 1000

})

models = (encoder, decoder)

os.environ['PYTHONHASHSEED'] = '0'

np.random.seed(5)

rn.seed(5)

config = tf.ConfigProto(

gpu_options=tf.GPUOptions(

visible_device_list="0,1",

allow_growth=True

)

)

tf.set_random_seed(5)

sess = tf.Session(graph=tf.get_default_graph(), config=config)

K.set_session(sess)

reconstruction_loss = binary_crossentropy(K.flatten(inputs),

K.flatten(outputs))

reconstruction_loss *= image_size * image_size

kl_loss = 1 + z_log_var - K.square(z_mean) - K.exp(z_log_var)

kl_loss = K.sum(kl_loss, axis=-1)

kl_loss *= -0.5

vae_loss = K.mean(reconstruction_loss + kl_loss)

vae.add_loss(vae_loss)

Adam = optimizers.Adam(lr=0.0005)

vae.compile(optimizer=Adam)

vae.summary()

plot_model(vae, to_file='vae_cnn.png', show_shapes=True)

history = vae.fit(x_train,

epochs=epochs,

batch_size=batch_size,

validation_data=(x_test, None))

open('vae_cnn.json', "w").write(vae.to_json())

vae.save('vae_cnn.h5')

plot_results(models, data, batch_size=batch_size, model_name="vae_cnn")

plot_history(history)

#補足

kerasやtensorflowのバージョンが問題になっている場合もあるようですが、上手くいった人のバージョンに変更しても変化がありませんでした。

コードが長くてお手数をおかけしますが、アドバイス頂けると幸いです。どうぞよろしくお願い致します。

Python 3.x 16151 questions Python 3はPythonプログラミング言語の最新バージョンであり、2008年12月3日にリリースされました。 Myタグに追加