Question

因此，我试图找出运行模型时Numpy数组长度减少的问题。我总共有2000张图像，分为2类，每类1000张。现在，当我将这些图像通过vgg16模型传递以进行特征提取时，它仅将1998年的图像传递回来。以下是我的代码。

VGG16模型

def load_vgg16(weights_path='vgg16.h5'):
if K.image_data_format() == 'channels_first':
    inputShape = (3, 256, 256)
else:
    inputShape = (256, 256, 3)
model = Sequential()
model.add(ZeroPadding2D((1,1),input_shape = inputShape))
model.add(Convolution2D(64, (3, 3), activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(64, (3, 3), activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))

model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(128, (3, 3), activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(128, (3, 3), activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))

model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(256, (3, 3), activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(256, (3, 3), activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(256, (3, 3), activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))

model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, (3, 3), activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, (3, 3), activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, (3, 3), activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))

model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, (3, 3), activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, (3, 3), activation='relu'))
model.add(ZeroPadding2D((1,1)))
model.add(Convolution2D(512, (3, 3), activation='relu'))
model.add(MaxPooling2D((2,2), strides=(2,2)))

if weights_path:
    model.load_weights(weights_path, by_name= True)

return model

通过瓶颈功能进行特征提取：

def save_bottleneck_features(location):
batch_size = 16
datagen = ImageDataGenerator(rescale= 1./255)
model = load_vgg16()


generator = datagen.flow_from_directory(location+'/training-data/',
                                       target_size=(image_width, image_height),
                                       batch_size = 16,
                                       class_mode = None,
                                       shuffle = False)
bottleneck_features_train = model.predict_generator(
    generator, nb_training_samples / batch_size)
np.save(open(location+'/bottleneck_features_train.npy', 'wb'), bottleneck_features_train)    

# repeat with the validation data
generator = datagen.flow_from_directory(location+'/validation-data/',
                                       target_size=(image_width, image_height),
                                       batch_size=16,
                                       class_mode=None,
                                       shuffle=False)
bottleneck_features_validation = model.predict_generator(
    generator, nb_validation_samples / batch_size)
np.save(open(location+'/bottleneck_features_validation.npy', 'wb'), bottleneck_features_validation)

运行以上功能：

top_model_weights_path='/top_model_weights.h5'

location = 'newdata'
nb_epoch = 50

training_samples= [len(os.listdir('newdata/training-data'+'/'+i)) 
                   for i in sorted(os.listdir('newdata/training-data/'))]
nb_training_samples = sum(training_samples)

#Calucalating number of data prsent in the folders or damage and whole cars in validation folder
validation_samples = [len(os.listdir('newdata/validation-data/' + i)) 
                      for i in sorted(os.listdir('newdata/validation-data/'))]
nb_validation_samples = sum(validation_samples)

print(training_samples)
print(validation_samples)
save_bottleneck_features('newdata')

因此，当我运行上述代码时，我期望数组bottleneck_features_train的总长度为2000，但我只能得到1998。同样，bottleneck_features_validation的总长度为1840，但我希望得到1840（927 + 909）。 training_samples和validation_samples的输出如下。

[1000, 1000]
[927, 909]

我认为我传递了model.predict_generator()中要求的错误步骤数。当我尝试使用此代码标记这些图像时。

training_data = np.load(open(location+'/bottleneck_features_train.npy','rb'))
training_label = np.array([0] * training_samples[0] +
                          [1] * training_samples[1])

validation_data = np.load(open(location+'/bottleneck_features_validation.npy','rb'))
validation_label = np.array([0] * validation_samples[0] +
                           [1] * validation_samples[1])

并尝试拟合模型，然后我收到关于训练数据和训练标签的n个长度不同的错误。

如何解决此问题并开始拟合模型？谢谢你的帮助。干杯！

如何计算model.predict_generator（）中所需的步骤数

0 个答案: