我的图像分类模型中LSTM层的形状错误

Question

你好，我正在尝试对灰度图像(224x224(进行分类，并尝试使用LSTM进行分类，但我一直得到形状错误

我的列车数据生成器是这样的：

def train_datagenerator(train_batchsize):
train_datagen = ImageDataGenerator(
rescale=1 / 255.0,
rotation_range=20,
zoom_range=0.05,
width_shift_range=0.05,
height_shift_range=0.05,
shear_range=0.05,
horizontal_flip=True,
fill_mode="nearest")
train_generator = train_datagen.flow_from_directory(train_dir,
target_size=(image_size, image_size),
batch_size=train_batchsize,
class_mode='categorical')
return train_generator

这是我的型号代码：

def LSTM_model():
model = Sequential()
model.add(LSTM(512, input_shape=(224, 224)))
model.add(Flatten())
model.add(Dense(1024))
model.add(Activation('relu'))
model.add(Dense(50))
model.add(Activation('sigmoid'))
model.add(Dense(3))  
model.add(Activation('softmax'))

model.build()
model.summary()
return model 

型号.fit

def train(model):
train_generator = train_datagenerator(train_batchsize)
model.compile(loss='categorical_crossentropy',
#optimizer='sgd',
optimizer='adam',
metrics=['acc'])
train_start = time.clock()
print('Started training...')
history = model.fit_generator(train_generator,
steps_per_epoch=train_generator.samples / train_generator.batch_size,
epochs=epochs,
verbose=1)
train_finish = time.clock()
train_time = train_finish - train_start
print('Training completed in {0:.3f} minutes!'.format(train_time / 60))
print('Saving the trained model...')
model.save('/content/drive/My Drive/Project/trained_models/rnn_model.h5')
print("Saved trained model in 'trained_models/ folder'!")
return model, history

我得到这个错误：层lstm_5的输入0与层不兼容：预期的ndim=3，找到的ndim=2。收到完整形状：[无，150528]

请帮助

Answer 1

我不确定，但你能试试这个吗

model.add(LSTM(512, return_sequences=True, input_shape=(224, 224)))