How to use predict in keras tf pretrained network?

Question

Neural networks

Good afternoon, how to use predict in a pre-trained keras tf network?

I trained the finished model by adding

model = Sequential()

model.add(Dense(256, activation='relu', input_dim=5 * 5 * 2048))
model.add(Dropout(0.5))
model.add(Dense(36, activation='softmax'))

Of course, I catch an error

ValueError: Input 0 of layer sequential_3 is incompatible with the layer: expected axis -1 of input shape to have value 51200 but received input with shape [None, 150, 150, 3]

How it is possible to bypass it?