Keras CNN-LSTM：制作y_train时出错

Question

这是我第一次在这里问问题（这意味着我真的需要帮助），很抱歉我的英语不好。我想制作一个cnn lstm层，用于Keras中的视频分类，但我在制作y\U列车时遇到了一个问题。之后我会描述我的问题。我有视频数据集（1个视频有10帧），我将视频转换为图像。首先，我将数据集拆分为xtrain、xtest、ytrain和ytest（20%测试，80%训练），然后我完成了。

X_train, X_test = img_data[:trainco], img_data[trainco:]
y_train, y_test = y[:trainco], y[trainco:]

X_train形状：（2280, 64, 64, 1)-

y\u列车形状：（2280，26）-

然后我必须在进入cnn-lstm过程之前重塑它们。*注意：我对x_test和y_test做同样的事情

time_steps = 10 (because I have 10 frames per video)

X_train = X_train.reshape(int(X_train.shape[0] / time_steps), time_steps, X_train.shape[1], X_train.shape[2], X_train.shape[3])
y_train = y_train.reshape(int(y_train.shape[0] / time_steps), time_steps, y_train.shape[1])

X_train形状：（228, 10, 64, 64, 1)，y_train形状：（228, 10, 26)

然后这是我的模型：

model = Sequential()
model.add(TimeDistributed(Conv2D(32, (3, 3), strides=(2, 2), activation='relu', padding='same'), input_shape=X_train.shape[1:]))
model.add(TimeDistributed(MaxPooling2D((2, 2), strides=(2, 2))))
model.add(TimeDistributed(Conv2D(32, (3, 3), padding='same', activation='relu')))
model.add(TimeDistributed(MaxPooling2D((2, 2), strides=(2, 2))))
model.add(TimeDistributed(Flatten()))
model.add(LSTM(256, return_sequences=False, input_shape=(64, 64)))
model.add(Dense(128))
model.add(Dense(64))
model.add(Dense(num_classes, activation='softmax'))
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=["accuracy"])
checkpoint = ModelCheckpoint(fname, monitor='acc', verbose=1, save_best_only=True, mode='max', save_weights_only=True)
hist = model.fit(X_train, y_train, batch_size=num_batch, nb_epoch=num_epoch, verbose=1, validation_data=(X_test, y_test), callbacks=[checkpoint])

但我发现了一个错误

ValueError: Error when checking target: expected dense_3 to have 2 dimensions, but got array with shape (228, 10, 26)

就像上面说的，应该有两个维度。我将代码更改为

y_train = y_train.reshape(int(y_train.shape[0] / time_steps), y_train.shape[1])

我又犯了一个错误

ValueError: cannot reshape array of size 59280 into shape (228,26)

然后我再次将代码更改为

y_train = y_train.reshape(y_train.shape[0], y_train.shape[1])

我还是有个错误

ValueError: Input arrays should have the same number of samples as target arrays. Found 228 input samples and 2280 target samples.

我该怎么办？我知道这个问题，但我不知道如何解决它。请帮助我。

Answer 1

我重新创建了一个稍微简化的情况，以再现问题。基本上，LSTM层似乎只为整个时间步序列输出一个结果，从而将输出中的维数从3降到2。如果您运行下面的程序，我已经添加了模型。summary（），提供架构的详细信息。

from keras import Sequential
from keras.layers import TimeDistributed, Dense, Conv2D, MaxPooling2D, Flatten, LSTM
import numpy as np

X_train = np.random.random((228, 10, 64, 64, 1))
y_train = np.random.randint(2, size=(228, 10, 26))
num_classes = 26

# Create the model
model = Sequential()
model.add(TimeDistributed(Conv2D(32, (3, 3), strides=(2, 2), activation='relu', padding='same'), input_shape=X_train.shape[1:]))
model.add(TimeDistributed(MaxPooling2D((2, 2), strides=(2, 2))))
model.add(TimeDistributed(Conv2D(32, (3, 3), padding='same', activation='relu')))
model.add(TimeDistributed(MaxPooling2D((2, 2), strides=(2, 2))))
model.add(TimeDistributed(Flatten(),name='Flatten'))
model.add(LSTM(256, return_sequences=False, input_shape=(64, 64)))
model.add(Dense(128))
model.add(Dense(64))
model.add(Dense(num_classes, activation='softmax', name='FinalDense'))
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=["accuracy"])

#
model.summary()
# hist = model.fit(X_train, y_train, epochs=1)

我相信您需要决定是降低y_train（目标）数据的维度以与模型保持一致，还是更改模型。我希望这有所帮助。