I'm trying to make image2image translation and
my dataset is composed of Mnist(256256) and transformed Mnist(256256)
I am literally suffering from this error:
ValueError: Error when checking target: expected conv2d_transpose_57 to have shape (256, 256, 1) but got array with shape (256, 256, 3)
My layer seems like this :
_______________________________________________________________
Layer (type) Output Shape Param #
=================================================================
conv2d_56 (Conv2D) (None, 256, 256, 17) 476
_________________________________________________________________
conv2d_57 (Conv2D) (None, 256, 256, 32) 4928
_________________________________________________________________
max_pooling2d_37 (MaxPooling (None, 128, 128, 32) 0
_________________________________________________________________
conv2d_58 (Conv2D) (None, 128, 128, 48) 13872
_________________________________________________________________
conv2d_59 (Conv2D) (None, 128, 128, 64) 27712
_________________________________________________________________
max_pooling2d_38 (MaxPooling (None, 64, 64, 64) 0
_________________________________________________________________
max_pooling2d_39 (MaxPooling (None, 32, 32, 64) 0
_________________________________________________________________
conv2d_60 (Conv2D) (None, 32, 32, 96) 55392
_________________________________________________________________
conv2d_61 (Conv2D) (None, 32, 32, 128) 110720
_________________________________________________________________
max_pooling2d_40 (MaxPooling (None, 16, 16, 128) 0
_________________________________________________________________
max_pooling2d_41 (MaxPooling (None, 8, 8, 128) 0
_________________________________________________________________
conv2d_62 (Conv2D) (None, 8, 8, 192) 221376
_________________________________________________________________
conv2d_63 (Conv2D) (None, 8, 8, 256) 442624
_________________________________________________________________
max_pooling2d_42 (MaxPooling (None, 4, 4, 256) 0
_________________________________________________________________
conv2d_64 (Conv2D) (None, 4, 4, 256) 590080
_________________________________________________________________
conv2d_transpose_50 (Conv2DT (None, 8, 8, 256) 262400
_________________________________________________________________
conv2d_transpose_51 (Conv2DT (None, 16, 16, 192) 196800
_________________________________________________________________
conv2d_transpose_52 (Conv2DT (None, 32, 32, 128) 98432
_________________________________________________________________
conv2d_transpose_53 (Conv2DT (None, 64, 64, 64) 32832
_________________________________________________________________
conv2d_transpose_54 (Conv2DT (None, 128, 128, 48) 12336
_________________________________________________________________
conv2d_transpose_55 (Conv2DT (None, 256, 256, 32) 6176
_________________________________________________________________
conv2d_transpose_56 (Conv2DT (None, 256, 256, 17) 561
_________________________________________________________________
conv2d_transpose_57 (Conv2DT (None, 256, 256, 3) 54
=================================================================
Total params: 2,076,771
Trainable params: 2,076,771
Non-trainable params: 0
_________________________________________________________________
Traceback (most recent call last):
idk why this is happening
I changed last layer's output to (None, 256, 256, 1).
And also I changed first layer's input and last layer's output to (None, 256, 256, 1).
but it doesn't work..
import numpy as np
import warnings
import csv
import os
from PIL import Image
import random
from keras.layers import Input
from keras import layers
from keras.layers import Dense
from keras.layers import Activation
from keras.layers import Flatten, Conv2DTranspose
from keras.layers import Conv2D, UpSampling2D
from keras.layers import MaxPooling2D, pooling
from keras.layers import GlobalMaxPooling2D
from keras.layers import ZeroPadding2D
from keras.layers import AveragePooling2D
from keras.layers import GlobalAveragePooling2D
from keras.layers import BatchNormalization
from keras.models import Model
from keras.preprocessing import image
import keras.backend as K
from keras.utils import layer_utils, np_utils
from keras.utils.data_utils import get_file
from keras.applications.imagenet_utils import decode_predictions
from keras.applications.imagenet_utils import preprocess_input
from keras_applications.imagenet_utils import _obtain_input_shape
from keras.engine.topology import get_source_inputs
from keras.models import Sequential
if __name__ == '__main__':
training_file_input = 'C:/Users/my/Desktop/input/train/trainig_tfmed'
training_file_output = 'C:/Users/my/Desktop/input/train/trainig_original'
test_file_input = 'C:/Users/my/Desktop/input/test/test_tfmed'
test_file_output = 'C:/Users/my/Desktop/input/test/test_original'
x_train = []
y_train = []
nop = np.array([None])
training_file_input_list = os.listdir(training_file_input)
test_file_input_list = os.listdir(test_file_input)
for i in range(1, len(training_file_input_list)+1):
input_filename = training_file_input + '/tfmed_trainig_' + str(i) + '.jpg'
input_image = Image.open(input_filename)
input_image = input_image.convert("RGB")
input_image = input_image.resize((256, 256), Image.ANTIALIAS)
input_image = np.array(input_image, dtype=np.float32)
x_train.append(input_image)
#x_train = np.append(nop, input_image)
output_filename = training_file_output + '/original_trainig_' + str(i) + '.jpg'
output_image = Image.open(output_filename)
output_image = output_image.convert("RGB")
output_image = output_image.resize((256, 256), Image.ANTIALIAS)
output_image = np.array(output_image, dtype=np.float32)
y_train.append(output_image)
#y_train = np.append(nop, input_image)
## loading test files
x_test = []
y_test = []
for i in range(1, len(test_file_input_list)+1):
input_filename = test_file_input + '/tfmed_test_' + str(i) + '.jpg'
input_image = Image.open(input_filename)
input_image = input_image.convert("RGB")
input_image = input_image.resize((256, 256), Image.ANTIALIAS)
input_image = np.array(input_image, dtype=np.float32)
x_test.append(input_image)
#x_test = np.append(nop, input_image)
output_filename = test_file_output + '/original_test_' + str(i) + '.jpg'
output_image = Image.open(output_filename)
output_image = output_image.convert("RGB")
output_image = output_image.resize((256, 256), Image.ANTIALIAS)
output_image = np.array(output_image, dtype=np.float32)
y_test.append(output_image)
#y_test = np.append(nop, input_image)
#
x_train = np.asarray(x_train)
y_train = np.asarray(y_train)
x_test = np.asarray(x_test)
y_test = np.asarray(y_test)
print('Model load')
model=Sequential()
model.add(Conv2D(17, (3, 3), padding='same', strides=(1, 1), activation='relu', input_shape = (256, 256, 1)))
print(model.output_shape)
model.add(Conv2D(32, (3, 3), padding='same', strides=(1, 1), activation='relu'))
print(model.output_shape)
model.add(pooling.MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))
print(model.output_shape)
model.add(Conv2D(48, (3, 3), padding='same', strides=(1, 1), activation='relu'))
print(model.output_shape)
model.add(Conv2D(64, (3, 3), padding='same', strides=(1, 1), activation='relu'))
print(model.output_shape)
model.add(pooling.MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))
print(model.output_shape)
model.add(pooling.MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))
print(model.output_shape)
model.add(Conv2D(96, (3, 3), padding='same', strides=(1, 1), activation='relu'))
print(model.output_shape)
model.add(Conv2D(128, (3, 3), padding='same', strides=(1, 1), activation='relu'))
print(model.output_shape)
model.add(pooling.MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))
print(model.output_shape)
model.add(pooling.MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))
print(model.output_shape)
model.add(Conv2D(192, (3, 3), padding='same', strides=(1, 1), activation='relu'))
print(model.output_shape)
model.add(Conv2D(256, (3, 3), padding='same', strides=(1, 1), activation='relu'))
print(model.output_shape)
model.add(pooling.MaxPooling2D(pool_size=(2, 2), strides=(2, 2)))
print(model.output_shape)
model.add(Conv2D(256, (3, 3), padding='same', strides=(1, 1), activation='relu'))
print(model.output_shape)
model.add(Conv2DTranspose(256, kernel_size=(2, 2), strides=(2, 2), activation='relu'))
print(model.output_shape)
model.add(Conv2DTranspose(192, kernel_size=(2, 2), strides=(2, 2), activation='relu'))
print(model.output_shape)
model.add(Conv2DTranspose(128, kernel_size=(2, 2), strides=(2, 2), activation='relu'))
print(model.output_shape)
model.add(Conv2DTranspose(64, kernel_size=(2, 2), strides=(2, 2), activation='relu'))
print(model.output_shape)
model.add(Conv2DTranspose(48, kernel_size=(2, 2), strides=(2, 2), activation='relu'))
print(model.output_shape)
model.add(Conv2DTranspose(32, kernel_size=(2, 2), strides=(2, 2), activation='relu'))
print(model.output_shape)
model.add(Conv2DTranspose(17, kernel_size=(1, 1), strides=(1, 1), activation='relu'))
print(model.output_shape)
model.add(Conv2DTranspose(1, kernel_size=(1, 1), strides=(1, 1), activation='relu'))
print(model.output_shape)
# model.add(Conv2DTranspose(1, kernel_size=(1, 1), strides=(1, 1), activation='relu'))
# print(model.output_shape)
# model.add(UpSampling2D(1))
# print(model.output_shape)
#
model.summary()
model.compile(loss='sparse_categorical_crossentropy', optimizer='sgd', metrics=['accuracy'])
model.fit(x_train, y_train, epochs=10, batch_size=50)
loss, accuracy = model.evaluate(x_test, y_test)
print('Loss: ' + str(loss))
print('Accuracy: ' + str(accuracy))
It should work and it needs to be learned