ValueError: Input 0 of layer "sequential_2" is incompatible with the layer: expected shape=(None, 28, 28, 1), found shape=(1, 14, 14, 1) about tensorflow-with-khom

[KhomZ]

https://stackoverflow.com/questions/71038082/valueerror-input-0-of-layer-sequential-is-incompatible-with-the-layer-expect

[KhomZ]

Your input has to match the expected format of the input layer of your model. You can use reshape to get the right format, expected the dimension match, otherwise you'll need to pad the missing dimensions.

[KhomZ]

https://stackoverflow.com/questions/65225918/valueerror-input-0-of-layer-sequential-is-incompatible-with-the-layer-expecte

[KhomZ]

Might be

Problem with this line model.add(layers.Conv2D(32, (3, 3), activation='relu', input_shape=(32, 32, 1))) Input dataset has RGB images input_shape should be (32,32,3) where 3 stands for 3 RGB channels and whereas '1' is used for grayscale image

[KhomZ]

https://stackoverflow.com/questions/66328999/valueerror-input-0-of-layer-sequential-is-incompatible-with-the-layer-expected

[KhomZ]

finally corrected code:

`def make_discriminator_model():
model = tf.keras.Sequential()
model.add(layers.Conv2D(64, (5, 5), strides=(2, 2), padding='same',
input_shape=[14, 14, 1]))
# model.add(layers.Conv2D(64, (5, 5), strides=(2, 2), padding='same',
# input_shape=[28, 28, 1]))

model.add(layers.LeakyReLU())
model.add(layers.Dropout(0.3))

model.add(layers.Conv2D(128, (5, 5), strides=(2, 2), padding='same'))
model.add(layers.LeakyReLU())
model.add(layers.Dropout(0.3))

model.add(layers.Flatten())
model.add(layers.Dense(1))

return model`

[KhomZ]

model.add(layers.Conv2D(64, (5, 5), strides=(2, 2), padding='same',input_shape=[28, 28, 1]))

change this to :

model.add(layers.Conv2D(64, (5, 5), strides=(2, 2), padding='same',input_shape=[14, 14, 1]))