[FIXED] ValueError: Input 0 of layer conv2d is incompatible with the layer: : expected min_ndim=4, found ndim=3. Full shape received: (None, 180, 180)

Issue

Here is my code ,

I tried to build below CNN network , this error i am observing ,

model.add(Conv2D(8,3,activation='relu',padding='same',input_shape=(180,180)))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(16,3,activation='relu',padding='same',input_shape=(180,180)))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(32,3,activation='relu',padding='same',input_shape=(180,180)))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(64,3,activation='relu',padding='same',input_shape=(180,180)))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(128,3,activation='relu',padding='same',input_shape=(180,180)))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Flatten())
model.add(Dense(254, activation='relu'))
model.add(Dense(9, activation='softmax'))

The image_batch is a tensor of the shape (32, 180, 180, 3). This is a batch of 32 images of shape 180x180x3 (the last dimension refers to color channels RGB). The label_batch is a tensor of the shape (32,), these are corresponding labels to the 32 images

Solution

You need to configure the CNN to process the inputs of shape

model.add(layers.Conv2D(8, (3, 3), activation='relu', input_shape=(180, 180, 3)))

The first dimension is considered as the batch_size. If you specify input_shape=(180,180) then it means that image_height=180, image_width=180 and the batch_size=None that means arbitrary number of samples could be given as input during model fit stage.

Answered By - Priya