我正在尝试训练2D卷积LSTM，以基于视频数据进行分类预测。但是，我的输出层似乎遇到了问题:
“ValueError:检查目标时出错:预期density_1具有5个维，但数组的形状为(1，1939，9)”
我当前的模型基于Keras Team提供的ConvLSTM2D example。我认为上述错误是由于我误解了示例及其基本原理而导致的。
数据
我有任意数量的视频，其中每个视频包含任意数量的帧。每帧为135x240x1(最后一个颜色 channel )。这将导致输入形状为(None，None，135、240、1)，其中两个“None”值分别是批次大小和时间步长。如果我训练具有1052帧的单个视频，那么我的输入形状将变为(1、1052、135、240、1)。
对于每一帧，模型应在9个类别中预测介于0和1之间的值。这意味着我的输出形状为(None，None，9)。如果我训练具有1052帧的单个视频，则此形状变为(1、1052、9)。
模型
Layer (type) Output Shape Param #
=================================================================
conv_lst_m2d_1 (ConvLSTM2D) (None, None, 135, 240, 40 59200
_________________________________________________________________
batch_normalization_1 (Batch (None, None, 135, 240, 40 160
_________________________________________________________________
conv_lst_m2d_2 (ConvLSTM2D) (None, None, 135, 240, 40 115360
_________________________________________________________________
batch_normalization_2 (Batch (None, None, 135, 240, 40 160
_________________________________________________________________
conv_lst_m2d_3 (ConvLSTM2D) (None, None, 135, 240, 40 115360
_________________________________________________________________
batch_normalization_3 (Batch (None, None, 135, 240, 40 160
_________________________________________________________________
dense_1 (Dense) (None, None, 135, 240, 9) 369
=================================================================
Total params: 290,769
Trainable params: 290,529
Non-trainable params: 240
源代码
model = Sequential()
model.add(ConvLSTM2D(
filters=40,
kernel_size=(3, 3),
input_shape=(None, 135, 240, 1),
padding='same',
return_sequences=True))
model.add(BatchNormalization())
model.add(ConvLSTM2D(
filters=40,
kernel_size=(3, 3),
padding='same',
return_sequences=True))
model.add(BatchNormalization())
model.add(ConvLSTM2D(
filters=40,
kernel_size=(3, 3),
padding='same',
return_sequences=True))
model.add(BatchNormalization())
model.add(Dense(
units=classes,
activation='softmax'
))
model.compile(
loss='categorical_crossentropy',
optimizer='adadelta'
)
model.fit_generator(generator=training_sequence)
追溯
Epoch 1/1
Traceback (most recent call last):
File ".\lstm.py", line 128, in <module>
main()
File ".\lstm.py", line 108, in main
model.fit_generator(generator=training_sequence)
File "C:\Users\matth\Anaconda3\envs\capstone-gpu\lib\site-packages\keras\legacy\interfaces.py", line 91, in wrapper
return func(*args, **kwargs)
File "C:\Users\matth\Anaconda3\envs\capstone-gpu\lib\site-packages\keras\models.py", line 1253, in fit_generator
initial_epoch=initial_epoch)
File "C:\Users\matth\Anaconda3\envs\capstone-gpu\lib\site-packages\keras\legacy\interfaces.py", line 91, in wrapper
return func(*args, **kwargs)
File "C:\Users\matth\Anaconda3\envs\capstone-gpu\lib\site-packages\keras\engine\training.py", line 2244, in fit_generator
class_weight=class_weight)
File "C:\Users\matth\Anaconda3\envs\capstone-gpu\lib\site-packages\keras\engine\training.py", line 1884, in train_on_batch
class_weight=class_weight)
File "C:\Users\matth\Anaconda3\envs\capstone-gpu\lib\site-packages\keras\engine\training.py", line 1487, in _standardize_user_data
exception_prefix='target')
File "C:\Users\matth\Anaconda3\envs\capstone-gpu\lib\site-packages\keras\engine\training.py", line 113, in _standardize_input_data
'with shape ' + str(data_shape))
ValueError: Error when checking target: expected dense_1 to have 5 dimensions, but got array with shape (1, 1939, 9)
批量大小设置为1的示例输入形状为(1、1389、135、240、1)。这种形状符合我上面描述的要求，因此我认为我的Keras Sequence子类(在源代码中为“training_sequence”)是正确的。
我怀疑问题是由我直接从BatchNormalization()转到Dense()引起的。毕竟，回溯表明问题是在density_1(最后一层)中发生的。但是，我不想让任何人误入歧途，所以请带我一分盐。
编辑2018年3月27日
阅读涉及类似模型的this thread之后，我更改了最终的ConvLSTM2D层，以便将return_sequences参数设置为False而不是True。我还在我的Dense层之前添加了GlobalAveragePooling2D层。更新后的模型如下:
Layer (type) Output Shape Param #
=================================================================
conv_lst_m2d_1 (ConvLSTM2D) (None, None, 135, 240, 40 59200
_________________________________________________________________
batch_normalization_1 (Batch (None, None, 135, 240, 40 160
_________________________________________________________________
conv_lst_m2d_2 (ConvLSTM2D) (None, None, 135, 240, 40 115360
_________________________________________________________________
batch_normalization_2 (Batch (None, None, 135, 240, 40 160
_________________________________________________________________
conv_lst_m2d_3 (ConvLSTM2D) (None, 135, 240, 40) 115360
_________________________________________________________________
batch_normalization_3 (Batch (None, 135, 240, 40) 160
_________________________________________________________________
global_average_pooling2d_1 ( (None, 40) 0
_________________________________________________________________
dense_1 (Dense) (None, 9) 369
=================================================================
Total params: 290,769
Trainable params: 290,529
Non-trainable params: 240
这是回溯的新副本:
Traceback (most recent call last):
File ".\lstm.py", line 131, in <module>
main()
File ".\lstm.py", line 111, in main
model.fit_generator(generator=training_sequence)
File "C:\Users\matth\Anaconda3\envs\capstone-gpu\lib\site-packages\keras\legacy\interfaces.py", line 91, in wrapper
return func(*args, **kwargs)
File "C:\Users\matth\Anaconda3\envs\capstone-gpu\lib\site-packages\keras\models.py", line 1253, in fit_generator
initial_epoch=initial_epoch)
File "C:\Users\matth\Anaconda3\envs\capstone-gpu\lib\site-packages\keras\legacy\interfaces.py", line 91, in wrapper
return func(*args, **kwargs)
File "C:\Users\matth\Anaconda3\envs\capstone-gpu\lib\site-packages\keras\engine\training.py", line 2244, in fit_generator
class_weight=class_weight)
File "C:\Users\matth\Anaconda3\envs\capstone-gpu\lib\site-packages\keras\engine\training.py", line 1884, in train_on_batch
class_weight=class_weight)
File "C:\Users\matth\Anaconda3\envs\capstone-gpu\lib\site-packages\keras\engine\training.py", line 1487, in _standardize_user_data
exception_prefix='target')
File "C:\Users\matth\Anaconda3\envs\capstone-gpu\lib\site-packages\keras\engine\training.py", line 113, in _standardize_input_data
'with shape ' + str(data_shape))
ValueError: Error when checking target: expected dense_1 to have 2 dimensions, but got array with shape (1, 1034, 9)
我在此运行中打印了x和y形状。 x为(1，1034，135，240，1)，y为(1，1034，9)。这可以缩小问题的范围。看来问题出在y资料，而不是x资料。具体来说，密集层不喜欢时间暗淡。但是，我不确定如何解决此问题。
编辑2018年3月28日
于阳的解决方案行之有效。对于有类似问题的任何人想要查看最终模型的外观，以下是摘要:
Layer (type) Output Shape Param #
=================================================================
conv_lst_m2d_1 (ConvLSTM2D) (None, None, 135, 240, 40 59200
_________________________________________________________________
batch_normalization_1 (Batch (None, None, 135, 240, 40 160
_________________________________________________________________
conv_lst_m2d_2 (ConvLSTM2D) (None, None, 135, 240, 40 115360
_________________________________________________________________
batch_normalization_2 (Batch (None, None, 135, 240, 40 160
_________________________________________________________________
conv_lst_m2d_3 (ConvLSTM2D) (None, None, 135, 240, 40 115360
_________________________________________________________________
batch_normalization_3 (Batch (None, None, 135, 240, 40 160
_________________________________________________________________
average_pooling3d_1 (Average (None, None, 1, 1, 40) 0
_________________________________________________________________
reshape_1 (Reshape) (None, None, 40) 0
_________________________________________________________________
dense_1 (Dense) (None, None, 9) 369
=================================================================
Total params: 290,769
Trainable params: 290,529
Non-trainable params: 240
另外，源代码:
model = Sequential()
model.add(ConvLSTM2D(
filters=40,
kernel_size=(3, 3),
input_shape=(None, 135, 240, 1),
padding='same',
return_sequences=True))
model.add(BatchNormalization())
model.add(ConvLSTM2D(
filters=40,
kernel_size=(3, 3),
padding='same',
return_sequences=True))
model.add(BatchNormalization())
model.add(ConvLSTM2D(
filters=40,
kernel_size=(3, 3),
padding='same',
return_sequences=True))
model.add(BatchNormalization())
model.add(AveragePooling3D((1, 135, 240)))
model.add(Reshape((-1, 40)))
model.add(Dense(
units=9,
activation='sigmoid'))
model.compile(
loss='categorical_crossentropy',
optimizer='adadelta'
)
最佳答案
如果要每帧进行预测，则绝对应该在最后一个return_sequences=True层中设置ConvLSTM2D。
对于目标形状上的ValueError，将GlobalAveragePooling2D()层替换为AveragePooling3D((1, 135, 240))加Reshape((-1, 40))，以使输出形状与目标数组兼容。