如果输入图像上的input_shape不同，如何使用keras

Question

I want to use keras to make a CNN construct, but my input images' shape will different. After I use small input shape to learning, I recognize image shape will also different.

input_shape = (None, None, 3)

model = Sequential()

model.add(Conv2D(64, (3,3), input_shape=input_shape, padding='same', activation='relu'))

model.add(Conv2D(64, (3,3), padding='same', activation='relu'))
model.add(MaxPooling2D(2,2))

model.add(Conv2D(128, (3,3), padding='same', activation='relu'))

model.add(Conv2D(128, (3,3), padding='same', activation='relu'))

model.add(MaxPooling2D(2,2))

model.add(Conv2D(256, (3,3), padding='same', activation='relu'))

model.add(Conv2D(256, (3,3), padding='same', activation='relu'))

model.add(Conv2D(256, (3,3), padding='same', activation='relu'))

model.add(MaxPooling2D(2,2))

model.add(Conv2D(512, (3,3), padding='same', activation='relu'))

model.add(Conv2D(512, (3,3), padding='same', activation='relu'))

model.add(Conv2D(512, (3,3), padding='same', activation='relu'))

model.add(MaxPooling2D(2,2))

model.add(Conv2D(512, (3,3), padding='same', activation='relu'))

model.add(Conv2D(512, (3,3), padding='same', activation='relu'))

model.add(Conv2D(512, (3,3), padding='same', activation='relu'))

model.add(MaxPooling2D(2,2))

model.add(Flatten())

model.add(Dense(4000, activation='relu'))

model.add(Dense(4000, activation='relu'))

model.add(Dense(30, activation='relu'))

But the program execute to "Flatten()" error. What can I use? Thanks you very much.

Answer 1

您应该将其重塑为一些漂亮的方形...