Question

我在自己的一些图像上训练VGG。我有以下代码：

img_width, img_height = 512, 512
top_model_weights_path = 'UIP-versus-inconsistent.h5'
train_dir = 'MasterHRCT/Limited-Cuts-UIP-Inconsistent/train'
validation_dir = 'MasterHRCT/Limited-Cuts-UIP-Inconsistent/validation'
nb_train_samples = 1500
nb_validation_samples = 500
epochs = 50
batch_size = 16

def save_bottleneck_features():

        datagen = ImageDataGenerator(rescale=1. / 255)

        model = applications.VGG16(include_top=False, weights='imagenet')

        generator = datagen.flow_from_directory(
            train_dir, 
            target_size=(img_width, img_height), 
            shuffle=False, 
            class_mode=None,
            batch_size=batch_size
        )  

        bottleneck_features_train = model.predict_generator(generator=generator, steps=nb_train_samples // batch_size)

        np.save(file="UIP-versus-inconsistent_train.npy", arr=bottleneck_features_train)

        generator = datagen.flow_from_directory(
            validation_dir, 
            target_size=(img_width, img_height), 
            shuffle=False,
            class_mode=None,  
            batch_size=batch_size,    
        )

        bottleneck_features_validation = model.predict_generator(generator, nb_validation_samples // batch_size)

        np.save(file="UIP-versus-inconsistent_validate.npy", arr=bottleneck_features_validation)

                generator = datagen.flow_from_directory(
                    validation_dir, 
                    target_size=(img_width, img_height), 
                    shuffle=False,
                    class_mode=None,  
                    batch_size=batch_size,    
                )

                bottleneck_features_validation = model.predict_generator(generator, nb_validation_samples // batch_size)

                np.save(file="UIP-versus-inconsistent_validate.npy", arr=bottleneck_features_validation)

执行此操作后，我根据我的目录

按预期进行操作

 Found 1500 images belonging to 2 classes.
 Found 500 images belonging to 2 classes

然后我跑

 train_data = np.load(file="UIP-versus-inconsistent_train.npy")
 train_labels = np.array([0] * 750 + [1] * 750)
 validation_data = np.load(file="UIP-versus-inconsistent_validate.npy")
 validation_labels = np.array([0] * 250 + [1] * 250)

然后检查数据

 print("Train data shape", train_data.shape)
 print("Train_labels shape", train_labels.shape)
 print("Validation_data shape", validation_labels.shape)
 print("Validation_labels", validation_labels.shape)

我得到了

Train data shape (1488, 16, 16, 512)
Train_labels shape (1488,)
Validation_data shape (496,)
Validation_labels (496,)

这是可变的 - 而不是有1500个训练数据示例和500个验证示例，就像我“失去”一些。有时我跑 save_bottleneck_features（）：这些数字是正确的，有时则不然。当这个过程需要很长时间时，它会发生很多。对此有可重复的解释吗？可能是图像损坏了？

Answer 1

很简单：

1488 = (1500 // batch_size) * batch_size
496 = (500 // batch_size) * batch_size

您的损失来自整数除法不准确。

Keras和VGG培训：为什么我会在model.predict_generator之后“丢失”培训和验证示例

1 个答案: