Keras 2&x27在哪里；s频道？

我曾经使用keras1（可能是1.0.5）进行多类别分类。我在CNN中的输入是（n，1，24113），113是通道号，内核大小是（1，5）。 代码如下：

X_train = X_train.reshape((-1, 1, SLIDING_WINDOW_LENGTH, NUM_SENSOR_CHANNELS))
X_test = X_test.reshape((-1, 1, SLIDING_WINDOW_LENGTH, NUM_SENSOR_CHANNELS))

# network
inputs = Input(shape=(1, SLIDING_WINDOW_LENGTH, NUM_SENSOR_CHANNELS))
conv1 = ELU()(Convolution2D(NUM_FILTERS, FILTER_SIZE, 1, border_mode='valid', init='normal', activation='relu')(inputs))
conv2 = ELU()(Convolution2D(NUM_FILTERS, FILTER_SIZE, 1, border_mode='valid', init='normal', activation='relu')(conv1))
conv3 = ELU()(Convolution2D(NUM_FILTERS, FILTER_SIZE, 1, border_mode='valid', init='normal', activation='relu')(conv2))
conv4 = ELU()(Convolution2D(NUM_FILTERS, FILTER_SIZE, 1, border_mode='valid', init='normal', activation='relu')(conv3))
reshape1 = Reshape((8, NUM_FILTERS * NUM_SENSOR_CHANNELS))(conv4)
gru1 = GRU(NUM_UNITS_LSTM, return_sequences=True, consume_less='mem')(reshape1)
gru2 = GRU(NUM_UNITS_LSTM, return_sequences=False, consume_less='mem')(gru1)
outputs = Dense(NUM_CLASSES, activation='softmax')(gru2)

# Hardcoded number of sensor channels employed in the OPPORTUNITY challenge
NUM_SENSOR_CHANNELS = 113

# Hardcoded number of classes in the gesture recognition problem
NUM_CLASSES = 18

# Hardcoded length of the sliding window mechanism employed to segment the data
SLIDING_WINDOW_LENGTH = 24

# Length of the input sequence after convolutional operations
FINAL_SEQUENCE_LENGTH = 8

# Hardcoded step of the sliding window mechanism employed to segment the data
SLIDING_WINDOW_STEP = 12

# Batch Size
BATCH_SIZE = 100

# Number filters convolutional layers
NUM_FILTERS = 64

# Size filters convolutional layers
FILTER_SIZE = 5

# Number of unit in the long short-term recurrent layers
NUM_UNITS_LSTM = 128

X_train = X_train.reshape((-1, 1, SLIDING_WINDOW_LENGTH, NUM_SENSOR_CHANNELS))
X_test = X_test.reshape((-1, 1, SLIDING_WINDOW_LENGTH, NUM_SENSOR_CHANNELS))

# network
inputs = Input(shape=(1, SLIDING_WINDOW_LENGTH, NUM_SENSOR_CHANNELS))
conv1 = ELU()(
    Conv2D(filters=NUM_FILTERS, kernel_size=(1, FILTER_SIZE), strides=(1, 1), padding='valid', activation='relu',
           kernel_initializer='normal', data_format='channels_last')(inputs))
conv2 = ELU()(
    Conv2D(filters=NUM_FILTERS, kernel_size=(1, FILTER_SIZE), strides=(1, 1), padding='valid', activation='relu',
           kernel_initializer='normal', data_format='channels_last')(conv1))
conv3 = ELU()(
    Conv2D(filters=NUM_FILTERS, kernel_size=(1, FILTER_SIZE), strides=(1, 1), padding='valid', activation='relu',
           kernel_initializer='normal', data_format='channels_last')(conv2))
conv4 = ELU()(
    Conv2D(filters=NUM_FILTERS, kernel_size=(1, FILTER_SIZE), strides=(1, 1), padding='valid', activation='relu',
           kernel_initializer='normal', data_format='channels_last')(conv3))
# permute1 = Permute((2, 1, 3))(conv4)
reshape1 = Reshape((SLIDING_WINDOW_LENGTH - (FILTER_SIZE - 1) * 4, NUM_FILTERS * 1))(conv4)  # 4 for 4 convs
gru1 = GRU(NUM_UNITS_LSTM, return_sequences=True, implementation=0)(reshape1)
gru2 = GRU(NUM_UNITS_LSTM, return_sequences=False, implementation=0)(gru1)  # implementation=2 for GPU
outputs = Dense(NUM_CLASSES, activation='softmax')(gru2)

这些天我把keras换成了keras 2。网络也没有改变。我的代码是：

X_train = X_train.reshape((-1, 1, SLIDING_WINDOW_LENGTH, NUM_SENSOR_CHANNELS))
X_test = X_test.reshape((-1, 1, SLIDING_WINDOW_LENGTH, NUM_SENSOR_CHANNELS))

# network
inputs = Input(shape=(1, SLIDING_WINDOW_LENGTH, NUM_SENSOR_CHANNELS))
conv1 = ELU()(Convolution2D(NUM_FILTERS, FILTER_SIZE, 1, border_mode='valid', init='normal', activation='relu')(inputs))
conv2 = ELU()(Convolution2D(NUM_FILTERS, FILTER_SIZE, 1, border_mode='valid', init='normal', activation='relu')(conv1))
conv3 = ELU()(Convolution2D(NUM_FILTERS, FILTER_SIZE, 1, border_mode='valid', init='normal', activation='relu')(conv2))
conv4 = ELU()(Convolution2D(NUM_FILTERS, FILTER_SIZE, 1, border_mode='valid', init='normal', activation='relu')(conv3))
reshape1 = Reshape((8, NUM_FILTERS * NUM_SENSOR_CHANNELS))(conv4)
gru1 = GRU(NUM_UNITS_LSTM, return_sequences=True, consume_less='mem')(reshape1)
gru2 = GRU(NUM_UNITS_LSTM, return_sequences=False, consume_less='mem')(gru1)
outputs = Dense(NUM_CLASSES, activation='softmax')(gru2)

# Hardcoded number of sensor channels employed in the OPPORTUNITY challenge
NUM_SENSOR_CHANNELS = 113

# Hardcoded number of classes in the gesture recognition problem
NUM_CLASSES = 18

# Hardcoded length of the sliding window mechanism employed to segment the data
SLIDING_WINDOW_LENGTH = 24

# Length of the input sequence after convolutional operations
FINAL_SEQUENCE_LENGTH = 8

# Hardcoded step of the sliding window mechanism employed to segment the data
SLIDING_WINDOW_STEP = 12

# Batch Size
BATCH_SIZE = 100

# Number filters convolutional layers
NUM_FILTERS = 64

# Size filters convolutional layers
FILTER_SIZE = 5

# Number of unit in the long short-term recurrent layers
NUM_UNITS_LSTM = 128

X_train = X_train.reshape((-1, 1, SLIDING_WINDOW_LENGTH, NUM_SENSOR_CHANNELS))
X_test = X_test.reshape((-1, 1, SLIDING_WINDOW_LENGTH, NUM_SENSOR_CHANNELS))

# network
inputs = Input(shape=(1, SLIDING_WINDOW_LENGTH, NUM_SENSOR_CHANNELS))
conv1 = ELU()(
    Conv2D(filters=NUM_FILTERS, kernel_size=(1, FILTER_SIZE), strides=(1, 1), padding='valid', activation='relu',
           kernel_initializer='normal', data_format='channels_last')(inputs))
conv2 = ELU()(
    Conv2D(filters=NUM_FILTERS, kernel_size=(1, FILTER_SIZE), strides=(1, 1), padding='valid', activation='relu',
           kernel_initializer='normal', data_format='channels_last')(conv1))
conv3 = ELU()(
    Conv2D(filters=NUM_FILTERS, kernel_size=(1, FILTER_SIZE), strides=(1, 1), padding='valid', activation='relu',
           kernel_initializer='normal', data_format='channels_last')(conv2))
conv4 = ELU()(
    Conv2D(filters=NUM_FILTERS, kernel_size=(1, FILTER_SIZE), strides=(1, 1), padding='valid', activation='relu',
           kernel_initializer='normal', data_format='channels_last')(conv3))
# permute1 = Permute((2, 1, 3))(conv4)
reshape1 = Reshape((SLIDING_WINDOW_LENGTH - (FILTER_SIZE - 1) * 4, NUM_FILTERS * 1))(conv4)  # 4 for 4 convs
gru1 = GRU(NUM_UNITS_LSTM, return_sequences=True, implementation=0)(reshape1)
gru2 = GRU(NUM_UNITS_LSTM, return_sequences=False, implementation=0)(gru1)  # implementation=2 for GPU
outputs = Dense(NUM_CLASSES, activation='softmax')(gru2)

速度似乎更快，但形状很奇怪，因为我不知道我的通道在哪里

---

我的代码有什么问题吗？有人能帮忙吗？THX

似乎Keras自己处理通道参数。

你说的奇怪形状是什么意思？@MarcinMożejko在Keras 2下的第二个代码中，输入形状是（？，1，24，113），conv1是（？，1，20，64），然后（？，1，16，64）（，1，12，113）和（？，1，8，113），然后扔进GRU，在keras 1.0.5下的第1个代码中，输入形状是（？，1，24，113）和（？，64，20，113）和（？，64，16，113）。。。那么keras 2中的通道113在哪里？我丢失了这些数据吗？实际上-当通道作为最后一个维度存储时，

Keras 2.0

中的默认

dimension

设置是

tensorflow

aka

channels last

version。在

keras1

中，默认值为

Theano

aka

channelfirst

version。这就是你困惑的原因。@MarcinMożejko我知道关于imgżu dimżu顺序，我的问题是因为我的通道数据似乎丢失了（你可以发现输入形状是（？，1，24，113），conv1是（？，1，20，64），但之前（？，64，20，113））我的模型运行得更快，但valżu acc实际上下降了2%。