ValueError: Error when checking : expected conv2d_1_input to have shape (28, 28, 1) but got array with shape (58000, 28, 28)

Question

I have successfully built a binary classifier and I am using it to predict some data. All the data are MNIST grayscale digits of size(28,28) and I have 58000 images. My code looks like:

from keras.preprocessing.image import ImageDataGenerator, array_to_img, img_to_array, load_img
from keras.models import Sequential
from keras.layers import Conv2D, MaxPooling2D
from keras.layers import Activation, Dropout, Flatten, Dense
from keras import backend as K
import tensorflow
import glob
from PIL import Image
import numpy as np

img_width, img_height = 28, 28#all MNIST images are of size (28*28)

train_data_dir = '/Binary Classifier/data/train'#train directory generated by train_cla
validation_data_dir = '/Binary Classifier/data/val'#validation directory generated by val_cla
train_samples = 40000
validation_samples = 10000
epochs = 2
batch_size = 512

if K.image_data_format() == 'channels_first':
    input_shape = (1, img_width, img_height)
else:
    input_shape = (img_width, img_height, 1)

#build a sequential model to train data
model = Sequential()
model.add(Conv2D(32, (3, 3), input_shape=input_shape))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(32, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Conv2D(64, (3, 3)))
model.add(Activation('relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))

model.add(Flatten())
model.add(Dense(64))
model.add(Activation('relu'))
model.add(Dropout(0.5))
model.add(Dense(1))
model.add(Activation('sigmoid'))

model.compile(loss='binary_crossentropy',
              optimizer='rmsprop',
              metrics=['accuracy'])

train_datagen = ImageDataGenerator(#train data generator
    rescale=1. / 255,
    shear_range=0.2,
    zoom_range=0.2,
    horizontal_flip=True)

val_datagen = ImageDataGenerator(rescale=1. / 255)#validation data generator

train_generator = train_datagen.flow_from_directory(#train generator
    train_data_dir,
    target_size=(img_width, img_height),
    batch_size=batch_size,
    class_mode='binary',color_mode = 'grayscale')

validation_generator = val_datagen.flow_from_directory(#validation generator
    validation_data_dir,
    target_size=(img_width, img_height),
    batch_size=batch_size,
    class_mode='binary',color_mode = 'grayscale')

model.fit_generator(#fit the generator to train and validate the model
    train_generator,
    steps_per_epoch=train_samples // batch_size,
    epochs=epochs,
    validation_data=validation_generator,
    validation_steps=validation_samples // batch_size)

filelist = glob.glob('/Binary Classifier/data/image_data/*.png')
x = np.array([np.array(Image.open(fname)) for fname in filelist])
ones=model.predict(x)

I got an error at ones=model.predict(x):

ValueError: Error when checking : expected conv2d_1_input to have 4 dimensions, but got array with shape (58000, 28, 28)

To fix this, I add:

x = np.expand_dims(x, axis=0)

before the execution of the last line. But now I received another error:

ValueError: Error when checking : expected conv2d_1_input to have shape (28, 28, 1) but got array with shape (58000, 28, 28)

I have two confusions:

1. Why doesn't np.expand_dims() change my array dimension as it should?
2. Why does model.predict() sometimes ask for a 4D input but sometimes 3D((28,28,1) in my case)? What does the function actually look for?

Thanks in advance!

Answer 1

Reshape your images from (28, 28) to (28, 28, 1) before stacking them up. So you get a final array of shape (5800, 28, 28, 1).

Or maybe you should do

x = np.expand_dims(x, axis=3)