Auto-encoder Mismatch Dimension Error - keras

I am trying to reconstruct images using Conv Autoencoder, but I get an error related to dimensions, could you find a solution, thanks,
Basically fist I want to test the model on reconstructing the same input data which are images, then if the model worked fine, I need to model images to maps,
In this case, can I just change the data from image_data to map_data as shown in the code below:
from keras.layers import Input, Dense, Conv2D, MaxPooling2D, UpSampling2D
from keras.models import Model
from keras import backend as K
from keras.callbacks import TensorBoard
import numpy as np
from keras.models import Sequential
from keras.layers.core import Dense, Dropout, Activation, Flatten
from keras.utils import np_utils
import matplotlib.pyplot as plt
import matplotlib
import os
from PIL import Image
from numpy import *
from sklearn.utils import shuffle
from sklearn.cross_validation import train_test_split
from keras.preprocessing.image import ImageDataGenerator,array_to_img, img_to_array, load_img
image_data='C:/Users/user_PC/Desktop/Image2Map/Samples'
map_data='C:/Users/user_PC/Desktop/Image2Map/Samples'
K.set_image_dim_ordering('tf')
input_img = Input(batch_shape=(1024, 106, 106,3))
x = Conv2D(16, (3, 3), activation='relu', padding='same')(input_img)
x = MaxPooling2D((2, 2), padding='same')(x)
x = Conv2D(8, (3, 3), activation='relu', padding='same')(x)
x = MaxPooling2D((2, 2), padding='same')(x)
x = Conv2D(8, (3, 3), activation='relu', padding='same')(x)
encoded = MaxPooling2D((2, 2), padding='same')(x)
x = Conv2D(8, (3, 3), activation='relu', padding='same')(encoded)
x = UpSampling2D((2, 2))(x)
x = Conv2D(8, (3, 3), activation='relu', padding='same')(x)
x = UpSampling2D((2, 2))(x)
x = Conv2D(16, (3, 3), activation='relu')(x)
x = UpSampling2D((2, 2))(x)
decoded = Conv2D(1, (3, 3), activation='sigmoid', padding='same')(x)
autoencoder = Model(input_img, decoded)
autoencoder.compile(optimizer='adadelta', loss='binary_crossentropy')
train_datagen = ImageDataGenerator(
rescale=1. / 255)
test_datagen = ImageDataGenerator(rescale=1. / 255)
train_generator = train_datagen.flow_from_directory(
image_data,
target_size=(106, 106),
batch_size=4,
class_mode=None)
validation_generator = test_datagen.flow_from_directory(
image_data,
target_size=(106, 106),
batch_size=4,
class_mode=None)
imgs = np.concatenate([train_generator.next()[0] for i in range(1024)])
autoencoder.fit_generator(generator=(imgs,imgs),
samples_per_epoch=1024 // 4,
epochs=10,
validation_data=(imgs,imgs),
validation_steps=1024 // 4)
decoded_imgs = autoencoder.predict(image_data)
n = 10
plt.figure(figsize=(20, 4))
for i in range(n):
# display original
ax = plt.subplot(2, n, i)
plt.imshow(image_data[i].reshape(106, 106))
plt.gray()
ax.get_xaxis().set_visible(False)
ax.get_yaxis().set_visible(False)
# display reconstruction
ax = plt.subplot(2, n, i + n)
plt.imshow(decoded_imgs[i].reshape(106, 106))
plt.gray()
ax.get_xaxis().set_visible(False)
ax.get_yaxis().set_visible(False)
plt.show()

Change class_mode from 'None' to 'input'. It should work . read more here

Related

1D CNN input shape and the training data shape

I am getting error trying to feed in the following data into my network. I have issue with reshaping the training data and the input to the network. The error I am getting is:
Error when checking target: expected conv1d_92 to have shape (4, 1) but got array with shape (1, 784)
The code is as follows:
# -*- coding: utf-8 -*-
"""
Created on Wed Mar 17 20:57:51 2021
#author: morte
"""
import keras
from keras import layers
from keras.datasets import mnist
import numpy as np
#(x_train, _), (x_test, _) = mnist.load_data()
#x_train = x_train.astype('float32') / 255.
#x_test = x_test.astype('float32') / 255.
#x_train = x_train.reshape((len(x_train), np.prod(x_train.shape[1:])))
#x_test = x_test.reshape((len(x_test), np.prod(x_test.shape[1:])))
(x_train, _), (x_test, _) = mnist.load_data()
x_train = x_train.astype('float32') / 255.
x_test = x_test.astype('float32') / 255.
x_train = np.reshape(x_train, (len(x_train),1,28*28)) #
x_test = np.reshape(x_test, (len(x_test),1,28*28)) #
input_img = keras.Input(shape=(x_train.shape[1:]))
x = layers.Conv1D(16,(3), activation='relu', padding='same')(input_img)
x = layers.MaxPooling1D(2, padding='same')(x)
x = layers.Conv1D(8,(3), activation='relu', padding='same')(x)
x = layers.MaxPooling1D(2, padding='same')(x)
x = layers.Conv1D(8,(3), activation='relu', padding='same')(x)
encoded = layers.MaxPooling1D(2, padding='same')(x)
# at this point the representation is (4, 4, 8) i.e. 128-dimensional
x = layers.Conv1D(8,(3), activation='relu', padding='same')(encoded)
x = layers.UpSampling1D(2)(x)
x = layers.Conv1D(8,(3), activation='relu', padding='same')(x)
x = layers.UpSampling1D(2)(x)
x = layers.Conv1D(16,(3), activation='relu')(x)
x = layers.UpSampling1D(2)(x)
decoded = layers.Conv1D(1, (3), activation='sigmoid', padding='same')(x)
autoencoder = keras.Model(input_img, decoded)
autoencoder.compile(optimizer='adam', loss='binary_crossentropy')
from keras.datasets import mnist
import numpy as np
from keras.callbacks import TensorBoard
autoencoder.fit(x_train, x_train,
epochs=2,
batch_size=128,
shuffle=True,
validation_data=(x_test, x_test),
)
decoded_imgs = autoencoder.predict(x_test)
import matplotlib.pyplot as plt
n = 10
plt.figure(figsize=(20, 4))
for i in range(1, n + 1):
# Display original
ax = plt.subplot(2, n, i)
plt.imshow(x_test[i].reshape(28, 28))
plt.gray()
ax.get_xaxis().set_visible(False)
ax.get_yaxis().set_visible(False)
# Display reconstruction
ax = plt.subplot(2, n, i + n)
plt.imshow(decoded_imgs[i].reshape(28, 28))
plt.gray()
ax.get_xaxis().set_visible(False)
ax.get_yaxis().set_visible(False)
plt.show()
Since it is an Autoencoder Network, Encoder-Input has to match Decoder-Output.
You are giving a (1,785) shaped Input-array and outputting an (4,1) array.
For more details you can add the line: autoencoder.summary() (for example after the line autoencoder = keras.Model(input_img, decoded))
This will give you information about the shapes of every layer.
An approach would be for example add a Dense Layer at the end of your Decoder.

Making a GIF from an AutoEncoder predicted image in python( matplotlib preferable ) Automatically?

i implemented a vanilla autoencoder in keras like this:
import numpy as np
from keras.preprocessing.image import *
from keras.layers import Input, Dense, Conv2D, MaxPooling2D, UpSampling2D
from keras.models import Model
from my_callback import Histories
input_img = Input(shape=(256, 256, 3)) # adapt this if using `channels_first` image data format
img = load_img('ss.png', target_size=(256,256))
#img.show()
img = np.array(img, dtype=np.float32) / 255 - 0.5
img=np.expand_dims(img,axis=0)
x = Conv2D(128, (3, 3), activation='relu', padding='same')(input_img)
x = MaxPooling2D((2, 2), padding='same')(x)
x = Conv2D(64, (3, 3), activation='relu', padding='same')(x)
x = MaxPooling2D((2, 2), padding='same')(x)
x = Conv2D(32, (3, 3), activation='relu', padding='same')(x)
encoded = MaxPooling2D((2, 2), padding='same')(x)
# at this point the representation is (4, 4, 8) i.e. 128-dimensional
x = Conv2D(32, (3, 3), activation='relu', padding='same')(encoded)
x = UpSampling2D((2, 2))(x)
x = Conv2D(32, (3, 3), activation='relu', padding='same')(x)
x = UpSampling2D((2, 2))(x)
x = Conv2D(64, (3, 3), activation='relu',padding='same')(x)
x = UpSampling2D((2, 2))(x)
decoded = Conv2D(3, (3, 3), activation='sigmoid', padding='same')(x)
autoencoder = Model(input_img, decoded)
autoencoder.compile(optimizer='adam', loss='binary_crossentropy')
h=Histories()
autoencoder.fit(img, img,
epochs=300,
batch_size=10,callbacks=[h])
Now
I had successfully made a GIF through saving each predicted image by autoencoder by keras.callbacks and then use imageio to make a gif with the help of this post programmatically-generate-video-or-animated-gif-in-python .The code was:
**my_callbacks.py**
import keras
import numpy as np
from matplotlib import pyplot as plt
from keras.preprocessing.image import load_img
class Histories(keras.callbacks.Callback):
def on_epoch_end(self, epoch, logs=None):
img = load_img('ss.png', target_size=(256, 256))
img = np.array(img, dtype=np.float32) / 255 - 0.5
img = np.expand_dims(img, axis=0)
pixel = self.model.predict(img)
pixel = pixel.reshape((256, 256, 3))
#plt.imshow(pixel)
#plt.show()
print("saved images------------???????????????????????")
plt.imsave('all_gif/pixelhash{0}.png'.format(epoch), pixel)
return
And then the code to generate a gif of images from a folder.But sadly this code doesn't keep the order of images.Any solution?
import imageio
import os
filenames=os.listdir()
images = []
for filename in filenames:
images.append(imageio.imread(filename))
imageio.mimsave('movie.gif', images)
But Is there any way to generate gif automatically without saving images in python like via matplotlib?

why Keras 2D regression network has constant output

I am working on the some kind of the 2D Regression Deep network with keras, but the network has constant output for every datasets, even I test with handmade dataset in this code I feed the network with a constant 2d values and the output is linear valu of the X (2*X/100) but the out put is constant.
import resource
import glob
import gc
rsrc = resource.RLIMIT_DATA
soft, hard = resource.getrlimit(rsrc)
print ('Soft limit starts as :', soft)
resource.setrlimit(rsrc, (4 * 1024 * 1024 * 1024, hard)) # limit to four giga bytes
soft, hard = resource.getrlimit(rsrc)
print ('Soft limit changed to :', soft)
from keras.models import Sequential
import keras.optimizers
from keras.layers import Dense, Dropout, Activation, Flatten, BatchNormalization
from keras.layers import Convolution2D, MaxPooling2D,AveragePooling2D
import numpy as np
import random
from keras.utils import plot_model
sample_size = 1
batch_size = 50
input_shape = (int(720 / 4), int(1280 / 4), sample_size * 5)
# model
model = Sequential()
model.add(BatchNormalization(input_shape=input_shape))
model.add(Convolution2D(128, (3, 3), activation='relu', dim_ordering="tf", padding="same",kernel_initializer='random_uniform'))
model.add(Convolution2D(128, (3, 3), activation='sigmoid', dim_ordering="tf", padding="same",kernel_initializer='random_uniform'))
model.add(AveragePooling2D(pool_size=(4, 4), dim_ordering="tf"))
model.add(Convolution2D(256, (3, 3), activation='sigmoid', dim_ordering="tf", padding="same",kernel_initializer='random_uniform'))
model.add(Convolution2D(256, (3, 3), activation='sigmoid', dim_ordering="tf", padding="same",kernel_initializer='random_uniform'))
model.add(AveragePooling2D(pool_size=(4, 4), dim_ordering="tf"))
model.add(Convolution2D(512, (3, 3), activation='sigmoid', dim_ordering="tf", padding="same",kernel_initializer='random_uniform'))
model.add(Convolution2D(512, (3, 3), activation='sigmoid', dim_ordering="tf", padding="same",kernel_initializer='random_uniform'))
model.add(AveragePooling2D(pool_size=(4, 4), dim_ordering="tf"))
model.add(Flatten())
model.add(Dense(4096, activation='relu',kernel_initializer='random_uniform'))
#model.add(Dropout(0.5))
model.add(Dense(512, activation='sigmoid',kernel_initializer='random_uniform'))
model.add(Dense(1, activation='sigmoid',kernel_initializer='random_uniform'))
model.compile(loss='mean_absolute_error',
optimizer='adam',
metrics=['mae','mse'])
model.summary()
plot_model(model,to_file='model.png')
def generate_tr(batch_size, is_training=False):
x=np.linspace(0, 10, num=5000).reshape(-1, 1)
counter = 0
print 'start'
while 1:
samples=np.zeros((batch_size, 720/4, 1280/4, 5))
labels=[]
for t in range (batch_size):
i = int(random.randint(0, 4999))
for b in range(sample_size):
samples[t, :,:,b*5:b*5+5] = np.random.rand(720/4,1280/4,5)/10+x[i]
labels.append((2*x[i])/100)
counter += 1
print counter #, labels
yield ((samples), np.asarray(labels))
tt = model.fit_generator(generate_tr(batch_size, True), steps_per_epoch=100, epochs=10,
use_multiprocessing=False, verbose=2)
score = model.predict_generator(generate_tr(batch_size, True), steps=30)
the output is always average of all of the values (here is .10)
do you know why?

Keras: Error when checking input

I am using Keras autoencodes with Theano backend. And want to make autoencode for 720x1080 RGB images.
This is my code
from keras.datasets import mnist
import numpy as np
from keras.layers import Input, LSTM, RepeatVector, Conv2D, MaxPooling2D, UpSampling2D
from keras.models import Model
from PIL import Image
x_train = []
x_train_noisy = []
for i in range(5,1000):
image = Image.open('data/trailerframes/frame' + str(i) + '.jpg', 'r')
x_train.append(np.array(image))
image = Image.open('data/trailerframes_avg/frame' + str(i) + '.jpg', 'r')
x_train_noisy.append(np.array(image))
x_train = np.array(x_train)
x_train = x_train.astype('float32') / 255.
x_train_noisy = np.array(x_train_noisy)
x_train_noisy = x_train_noisy.astype('float32') / 255.
input_img = Input(shape=(720, 1080, 3))
x = Conv2D(32, (3, 3), activation='relu', padding='same')(input_img)
x = MaxPooling2D((2, 2), padding='same')(x)
x = Conv2D(32, (3, 3), activation='relu', padding='same')(x)
encoded = MaxPooling2D((2, 2), padding='same')(x)
x = Conv2D(32, (3, 3), data_format="channels_last", activation='relu', padding='same')(encoded)
x = UpSampling2D((2, 2))(x)
x = Conv2D(32, (3, 3), data_format="channels_last", activation='relu', padding='same')(x)
x = UpSampling2D((2, 2))(x)
decoded = Conv2D(1, (3, 3), data_format="channels_last", activation='sigmoid', padding='same')(x)
autoencoder = Model(input_img, decoded)
autoencoder.compile(optimizer='adadelta', loss='binary_crossentropy')
autoencoder.fit(x_train_noisy, x_train,
epochs=10,
batch_size=128,
shuffle=True,
validation_data=(x_train_noisy, x_train))
But it gives me an error
ValueError: Error when checking input: expected input_7 to have shape (None, 720, 1080, 3) but got array with shape (995, 720, 1280, 3)
Input error:
As simple as:
You defined your input as (720,1080,3)
You're trying to trian your model with data in the form (720,1280,3)
One of them is wrong, and I think it's a typo in the input:
#change 1080 for 1280
input_img = Input(shape=(720, 1280, 3))
Output error (target):
Now, your target data is shaped like (720,1280,3), and your last layer outputs (720,1280,1)
A simple fix is:
decoded = Conv2D(3, (3, 3), data_format="channels_last", activation='sigmoid', padding='same')(x)
Using the encoder:
After training that model, you can create submodels for using only the encoder or the decoder:
encoderModel = Model(input_img, decoded)
decoderInput = Input((shape of the encoder output))
decoderModel = Model(decoderInput,decoded))
These two models will share the exact same weights of the entire model, training one model will affect all three models.
For using them without training, you can use model.predict(data), which will give you the results without training.

high loss rate when training my model

I'm working on image denoising using autoencoders (working with keras tensorflow backend).
when i train my model the loss rate is pretty high and stable(somewhere around 2.x).
i can't understand what i'm doing wrong.
here's my code:
from keras.layers import Input, Dense, Convolution2D, MaxPooling2D,UpSampling2D
from keras.models import Model
from keras.datasets import mnist
from keras.callbacks import TensorBoard
import matplotlib.pyplot as plt
import numpy as np
(x_train, _), (x_test, _) = mnist.load_data()
x_train = x_train.astype('float32') / 255.
x_test = x_test.astype('float32') / 255.
x_train = np.reshape(x_train, (len(x_train), 28, 28, 1))
x_test = np.reshape(x_test, (len(x_test), 28, 28, 1))
# adding noise to images
noise_factor = 0.5
x_train_noisy = x_train + noise_factor * np.random.normal(loc=0.0, scale=1.0, size=x_train.shape)
x_test_noisy = x_test + noise_factor * np.random.normal(loc=0.0, scale=1.0, size=x_test.shape)
x_train_noisy = np.clip(x_train_noisy, 0., 1.)
x_test_noisy = np.clip(x_test_noisy, 0., 1.)
input_img = Input(shape=(28, 28, 1))
x = Convolution2D(32, 3, 3, activation='relu', border_mode='same')(input_img)
x = MaxPooling2D((2, 2), border_mode='same')(x)
x = Convolution2D(32, 3, 3, activation='relu', border_mode='same')(x)
encoded = MaxPooling2D((2, 2), border_mode='same')(x)
# at this point the representation is (32, 7, 7)
x = Convolution2D(32, 3, 3, activation='relu', border_mode='same')(encoded)
x = UpSampling2D((2, 2))(x)
x = Convolution2D(32, 3, 3, activation='relu', border_mode='same')(x)
x = UpSampling2D((2, 2))(x)
decoded = Convolution2D(1, 3, 3, activation='sigmoid', border_mode='same')(x)
autoencoder = Model(input_img, decoded)
autoencoder.compile(optimizer='adadelta', loss='binary_crossentropy')
autoencoder.fit(x_train_noisy, x_train,
nb_epoch=100,
batch_size=128,
shuffle=True,
validation_data=(x_test_noisy, x_test))
any suggestions?

Resources