tensorflow - ValueError: 层序号_3 的输入 0 与层不兼容：预期 ndim=5，发现 ndim=4。收到的完整形状：（无、288、432、3）

Question

1. 从数据集加载的图像

training_set = image_dataset_from_directory(
      data_dir,
      validation_split=0.3,
      subset="training",
      seed=123,
      image_size=(img_height, img_width),
      batch_size=batch_size,
      label_mode='categorical',
      color_mode='rgb',
      shuffle=True,
    )

2. 模型

num_classes = 10
model = Sequential()
model.add(ConvLSTM2D(filters=64, kernel_size=(3,3), activation='relu',             
          input_shape=(10,img_height,img_width,3)))
model.add(Dropout(0.2))
model.add(Flatten())
model.add(Dense(100, activation='relu'))
model.add(Dense(num_classes, activation='softmax')) 

model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])

3. model.fit_generator()

   model.fit_generator（生成器=training_set，validation_data=testing_set，verbose=1，callbacks=callbacks，epochs=120）

标签： tensorflowmachine-learningkeraslstmimage-classification