python - CNNLSTM2D 实现
问题描述
有 2550 张图像作为训练集，1530 张图像作为测试集。为了将这些图像分为两类，使用了混合深度学习模型，但在运行代码时出现错误，如下所示。我想知道是否有人帮助我知道错误的原因。谢谢你
错误：
检查输入时：预期 conv_lst_m2d_39_input 有 5 个维度，但得到了形状为 (32, 64, 64, 3) 的数组
# importing libraries
from keras.models import Sequential
from keras.layers import Convolution2D
from keras.layers import MaxPooling2D
from keras.layers import Flatten
from keras.layers import Dense
import tensorflow as tf
from keras.layers.convolutional_recurrent import ConvLSTM2D
from keras.layers.normalization import BatchNormalization
#Data_Prprocessing
from keras.preprocessing.image import ImageDataGenerator
train_datagen = ImageDataGenerator(
rescale=1./255,
shear_range=0.2,
zoom_range=0.2,
horizontal_flip=True)
test_datagen = ImageDataGenerator(rescale=1./255)
training_set = train_datagen.flow_from_directory(
'D:\\thesis\\Paper 3\\Feature Extraction\\two_dimension_Feature_extraction\\stft_feature\\Training_set',
target_size=(64, 64),
batch_size=32,
class_mode='binary')
test_set = test_datagen.flow_from_directory(
'D:\\thesis\\Paper 3\\Feature Extraction\\two_dimension_Feature_extraction\\stft_feature\\Test_set',
target_size=(64, 64),
batch_size=32,
class_mode='binary')
#initializing the CNN
classifier = Sequential()
classifier.add(ConvLSTM2D(filters=40, kernel_size=(3, 3),input_shape=(None, 64, 64, 3), padding='same', return_sequences=True))
classifier.add(BatchNormalization())
classifier.add(ConvLSTM2D(filters=40, kernel_size=(3, 3),
padding='same', return_sequences=True))
classifier.add(BatchNormalization())
classifier.add(ConvLSTM2D(filters=40, kernel_size=(3, 3),
padding='same'))
#Full Connection
classifier.add(Dense(output_dim = 128, activation = 'relu'))
classifier.add(Dense(output_dim = 1, activation = 'sigmoid'))
#compiling the CNN
classifier.compile(optimizer = 'adam', loss = 'binary_crossentropy', metrics = ['accuracy'])
#Fitting the CNN to the images
history = classifier.fit_generator(training_set,
steps_per_epoch=2550,
epochs=25,
validation_data= test_set,
validation_steps=510)
import matplotlib.pyplot as plt
acc = history.history['acc']
val_acc = history.history['val_acc']
loss = history.history['loss']
val_loss = history.history['val_loss']
epochs = range(1, len(acc) + 1)
plt.plot(epochs, acc, 'r', label='Training acc')
plt.plot(epochs, val_acc, 'b', label='Validation acc')
plt.title('Training and validation accuracy')
plt.legend()
plt.figure()
plt.plot(epochs, loss, 'r', label='Training loss')
plt.plot(epochs, val_loss, 'b', label='Validation loss')
plt.title('Training and validation loss')
plt.plot()
plt.legend()
plt.show()
test_loss, test_acc = classifier.evaluate(test_set)
print('test_acc:', test_acc)
ERROR:
ValueError: Input 0 is incompatible with layer conv_lst_m2d_23: expected ndim=5, found ndim=6
新错误：
import numpy as np
import glob
from PIL import Image
import tensorflow as tf
images_png = glob.glob("*.png")
images = []
for pic in images_png:
image = tf.read_file(pic)
image = tf.image.decode_png(image, channels=3, dtype=tf.uint16)
image = tf.cast(image, tf.float32)
image = image / 256.0
images.append(image)
img_seq_list = []
for i in range(0, len(images) - 5, 5):
j = i+5
img_seq = np.stack(images[i:j], axis=0)
img_seq_list.append(img_seq)
labels = np.zeros((2,len(img_seq_list) + 1), dtype=int)
labels = np.transpose(labels)
length = len(img_seq_list)/2
length = int(length)
for i in range(0, 255):
if i <= 127:
labels[i][0] = 1
elif i > 127 :
labels[i][1] = 1
import tensorflow as tf
from keras.models import Sequential
from keras.layers import Convolution2D
from keras.layers import MaxPooling2D
from keras.layers import Flatten
from keras.layers import Dense
from keras.layers.convolutional_recurrent import ConvLSTM2D
from keras.layers.normalization import BatchNormalization
classifier = Sequential()
classifier.add(ConvLSTM2D(filters=40, kernel_size=(3, 3),input_shape=(5, 64, 64, 3), padding='same', return_sequences=True))
classifier.add(BatchNormalization())
classifier.add(ConvLSTM2D(filters=40, kernel_size=(3, 3),
padding='same', return_sequences=True))
classifier.add(BatchNormalization())
classifier.add(ConvLSTM2D(filters=40, kernel_size=(3, 3),
padding='same'))
#Full Connection
classifier.add(Dense(output_dim = 128, activation = 'relu'))
classifier.add(Dense(output_dim = 1, activation = 'sigmoid'))
#compiling the CNN
classifier.compile(optimizer = 'adam', loss = 'binary_crossentropy', metrics = ['accuracy'])
train_data = tf.data.Dataset.from_tensor_slices((img_seq_list[0:127], labels[0:127]))
train_data = train_data.shuffle(100).batch(10)
test_data = tf.data.Dataset.from_tensor_slices((img_seq_list[128:254], labels[128:254]))
test_data = train_data.shuffle(100).batch(10)
history = classifier.fit(train_data, validation_data=test_data)
import matplotlib.pyplot as plt
acc = history.history['acc']
val_acc = history.history['val_acc']
loss = history.history['loss']
val_loss = history.history['val_loss']
epochs = range(1, len(acc) + 1)
plt.plot(epochs, acc, 'r', label='Training acc')
plt.plot(epochs, val_acc, 'b', label='Validation acc')
plt.title('Training and validation accuracy')
plt.legend()
plt.figure()
plt.plot(epochs, loss, 'r', label='Training loss')
plt.plot(epochs, val_loss, 'b', label='Validation loss')
plt.title('Training and validation loss')
plt.plot()
plt.legend()
plt.show()
test_loss, test_acc = classifier.evaluate(test_data)
print('test_acc:', test_acc)
解决方案
我认为问题在于卷积 LSTM 层需要一个时间序列的图像，所以它必须有 5 个维度，包括批量维度，所以有一些形状(B, T, H, W, C)。您已将输入形状（忽略批次尺寸）定义为(None, 64, 64, 3)，因此您需要输入形状的批次张量(batch, timesteps, 64, 64, 3)。
另外，我认为fit_generator()不赞成将生成器传递给fit().
编辑：如果您有来自视频流的一系列帧，您可以将它们堆叠成一个多维数组。您必须以正确的顺序从目录中手动获取图像，然后创建一个数据迭代器：
images = <ordered list of 3-D numpy arrays>
img_seq = np.stack(images, axis=0)
# Do the above for each sequence of images in the training data to get N sequences
sequences = <list of sequences of images of length N>
labels = <array of labels of length N>
train_data = tf.data.Dataset.from_tensor_slices((sequence, labels))
train_data = train_data.shuffle(1000).batch(batch_size)
# Do similar for test data
然后，您可以使用tf.data.Datasetin fit()：
model.fit(train_data, validation_data=test_data)