CODEWITHSUNDEEP
pythonnumpyjpegscikit-image
joel.wilson
joel.wilson

Reputation: 8413

Unable to read RGB images into numpy array

I have gone through all SO question on this topic. Facing a strange problem here. I have the image path stored in file_names.

from skimage import io
import numpy as np

X = np.array([np.array(io.imread(i)) for i in file_names])
print(X.shape)
# (50,)
print(X[0].shape)
# (375, 500, 3)

I need X to be (50, 375, 500, 3). I tried reshape, adding np.newaxis etc but all fail. My next step is to use this for CNN. Basically, I want to create a mnist_cnn kind dataset with my images.

Next lines :

model = Sequential()
model.add(Conv2D(64, kernel_size=(3, 3),
                 activation='relu',
                 input_shape = (375, 500, 3)))
model.add(Flatten())
model.add(Dense(num_classes, activation='softmax'))

model.compile(loss='categorical_crossentropy',
              optimizer='adam', metrics=['accuracy'])
model.fit(X, y,   # y is (50,36) using one hot encoding
          batch_size=10,
          epochs=10,
          verbose=2)

Cause this:

ValueError: Error when checking input: expected conv2d_3_input to have 4 dimensions, but got array with shape (50, 1)

Upvotes: 1

Views: 210

Answers (1)

sascha
sascha

Reputation: 33542

The numpy-part looks easy:

from skimage import io
import numpy as np

# assumption: images are homogeneous in terms of dimensions and channels!
files = ['C:/TEMP/pic0.jpg', 'C:/TEMP/pic0.jpg', 'C:/TEMP/pic0.jpg', 'C:/TEMP/pic0.jpg']

image_array = np.stack([io.imread(i) for i in files])                  # default: axis=0
image_array.shape
# (4, 720, 540, 3)

Upvotes: 2

Related Questions