Keras ConvLSTM2D：输出层

时间：2018-03-28 00:41:46

标签： python tensorflow keras conv-neural-network lstm

我正在尝试训练2D卷积LSTM，以根据视频数据进行分类预测。但是，我的输出层似乎遇到了问题：

＆＃34; ValueError：检查目标时出错：期望dense_1有5个维度，但得到的数组有形状（1,1939,9）＆＃34;

我目前的模型基于Keras团队提供的ConvLSTM2D example。我认为上述错误是我误解这个例子及其基本原则的结果。

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（色彩通道最后）。这导致输入形状为（None，None，135,240,1），其中两个＆＃34; None＆＃34;值是按该顺序的批量大小和时间步长。如果我在1052帧的单个视频上训练，那么我的输入形状变为（1,1052,135,240,1）。

对于每个帧，模型应预测9个类中0到1之间的值。这意味着我的输出形状是（None，None，9）。如果我在1052帧的单个视频上训练，那么这个形状变为（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)

回溯 

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)

打印批次大小设置为1的样本输入形状为（1,1389,135,240,1）。这个形状符合我上面描述的要求，所以我认为我的Keras Sequence子类（在源代码中为＆＃34; training_sequence＆＃34;）是正确的。

我怀疑这个问题是由我直接从BatchNormalization（）转到Dense（）引起的。毕竟，回溯表明问题发生在dense_1（最后一层）。但是，我不想用初学者的知识引导任何人误入歧途，所以请多考虑一下我的评估。

修改3/27/2018

在阅读涉及类似模型的this thread之后，我更改了最终的ConvLSTM2D图层，以便将return_sequences参数设置为False而不是True。我还在Dense图层之前添加了一个GlobalAveragePooling2D图层。更新的模型如下：

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

以下是追溯的新副本：

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)

我在这次运行中打印了x和y形状。 x为（1,1034,135,240,1），y为（1,1034,9）。这可能会缩小问题范围。看起来问题与y数据而不是x数据有关。具体来说，密集层不像时间暗淡。但是，我不确定如何纠正这个问题。

修改3/28/2018

Yu-Yang的解决方案奏效了。对于有类似问题的人想要查看最终模型的样子，这里是摘要：

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

此外，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'
)

1 个答案:

答案 0 :(得分：2)

如果您想要每帧预测，那么您一定要在最后return_sequences=True层设置ConvLSTM2D。

对于目标形状上的ValueError，请将GlobalAveragePooling2D()图层替换为AveragePooling3D((1, 135, 240))加Reshape((-1, 40))，以使输出形状与目标数组兼容。

相关问题
最新问题