代碼如下：
model = tf.keras.Sequential()
model.add(tf.keras.layers.Conv2D(filters=32, kernel_size=(3, 3), input_shape=(None, None, 1), activation='relu'))
model.add(tf.keras.layers.Conv2D(filters=32, kernel_size=(3, 3), activation='relu'))
model.add(tf.keras.layers.MaxPool2D(pool_size=(2, 2)))
model.add(tf.keras.layers.Conv2D(filters=64, kernel_size=(3, 3), activation='relu'))
model.add(tf.keras.layers.Conv2D(filters=32, kernel_size=(3, 3), activation='relu'))
model.add(SpatialPyramidPooling([1, 2, 4]))
# model.add(tf.keras.layers.Flatten())
model.add(tf.keras.layers.Dense(10, activation='softmax'))
model.compile(optimizer='adam', loss='categorical_crossentropy', metrics=['accuracy'])
報錯資訊：
raise ValueError('The last dimension of the inputs to `Dense` '
ValueError: The last dimension of the inputs to `Dense` should be defined. Found `None`.
也就是說，在model.add(tf.keras.layers.Dense(10, activation='softmax'))代碼處，說沒有定義shape，請問如何處理？
轉載請註明出處，本文鏈接：https://www.uj5u.com/qita/245356.html
標籤：人工智能技術
下一篇：日常求助