ValueError: Input 0 of layer sequential_1 is incompatible with the layer: : expected min_ndim=4, found ndim=3. Full shape received: [None, 256, 256]

Question

Everything is okay until I convert my image to grayscale. So the rgb's shape is (256, 256, 3) but grayscale has (256, 256). When I feed it, I get that error.

network = Sequential()

network.add(Convolution2D(32, kernel_size=(3, 3),strides=1,activation='relu',input_shape=(256, 256)))
network.add(MaxPooling2D((2, 2)))

# network.add(Convolution2D(32, kernel_size=(3, 3), strides=1, activation='relu'))
# network.add(MaxPooling2D((2, 2)))


network.add(Convolution2D(64, kernel_size=(3, 3), strides=1, activation='relu'))
network.add(MaxPooling2D((2, 2)))

# network.add(Convolution2D(64, kernel_size=(3, 3), strides=1, activation='relu'))
# network.add(MaxPooling2D((2, 2)))


network.add(Convolution2D(128, kernel_size=(3, 3), strides=1, activation='relu'))
network.add(MaxPooling2D((2, 2)))

# network.add(Convolution2D(128, kernel_size=(3, 3), strides=1, activation='relu'))
# network.add(MaxPooling2D((2, 2)))


network.add(Flatten())
network.add(Dense(256, activation = 'relu'))
network.add(Dense(2, activation = 'softmax'))

checkpoint_path = os.path.join("/---------/grayscale", "weights.best.hdf5")
checkpoint = ModelCheckpoint(checkpoint_path, monitor='val_accuracy', verbose=1, save_best_only=True, mode='max')
es = EarlyStopping(monitor='val_loss', mode='min', verbose=1, patience=10)
callbacks_list = [checkpoint, es]

network.compile(optimizer = 'adam', loss = 'categorical_crossentropy', metrics = ['accuracy'])

B Douchet · Accepted Answer · 2020-11-27 19:46:13Z

1

You have to feed images of shape 256x256x1 in your network.

To convert your initial x_train into your new X_train:

X_train=np.reshape(x_train,(x_train.shape[0], x_train.shape[1],x_train.shape[2],1))

and finally change your input_shape from input_shape=(256,256) to input_shape=(256,256,1)

edited Nov 27, 2020 at 19:46

answered Nov 27, 2020 at 19:38

B Douchet

1,0401 gold badge12 silver badges21 bronze badges

Sign up to request clarification or add additional context in comments.

2 Comments

Yonus Over a year ago

tnx. but why should I change it back to (256, 256, 3)?

B Douchet Over a year ago

it's (256,256,1), sorry it was a mistake (edited)

Collectives™ on Stack Overflow

ValueError: Input 0 of layer sequential_1 is incompatible with the layer: : expected min_ndim=4, found ndim=3. Full shape received: [None, 256, 256]

1 Answer 1

2 Comments

Your Answer

Hot Network Questions

Collectives™ on Stack Overflow

1 Answer 1

2 Comments

Your Answer

Sign up or log in

Post as a guest

Related