val_accuracy比训练精度高，与val_accuracy和train_accuracy相比，测试精度很低。

Question

我在训练CNN的模特，

1. 培训data=687、验证data=102、测试data=79
2. 验证精度高于训练精度
3. ，测试精度与验证精度和训练损失相比都很低，而

则低于训练损失。

代码片段：

train_datagen = ImageDataGenerator(
                    rescale=1./255,
                    # rotation_range=30,
                    zoom_range=0.1,
                    horizontal_flip=True,
                    # vertical_flip=True,
                    # fill_mode='nearest',
                    validation_split=.15) # set validation split

val_datagen = ImageDataGenerator(rescale=1./255, validation_split=0.15)

train_generator = train_datagen.flow_from_directory(
    train_dir,
    target_size=(height, width),
    batch_size=batch_size,
    class_mode='categorical',
    seed=13
    )

validation_generator = val_datagen.flow_from_directory(
    train_dir, # same directory as training data
    target_size=(height, width),
    batch_size=batch_size,
    class_mode='categorical',
    seed=13,
    subset='validation'
    )
model = Sequential()
model.add(Conv2D(16,3,padding="same", activation="relu", input_shape=(height, width, 3)))
model.add(AveragePooling2D(strides=(2,2), padding="same"))
# model.add(Dropout(0.2))

model.add(Conv2D(32,3,padding="same", activation="relu"))
model.add(AveragePooling2D(strides=(2,2), padding="same"))
# model.add(Dropout(0.2))

model.add(Conv2D(32, 3, padding="same", activation="relu"))
model.add(AveragePooling2D(strides=(2,2), padding="same"))
# model.add(Dropout(0.2))

# model.add(Conv2D(32, 3, padding="same", activation="relu", kernel_regularizer=l2(0.0001)))
# model.add(AveragePooling2D(strides=(2,2), padding="same"))
# model.add(Dropout(0.4))

model.add(Conv2D(64, 3, padding="same", activation="relu"))
model.add(AveragePooling2D(strides=(2,2), padding="same",))
# model.add(Dropout(0.2))

model.add(Conv2D(64, 3, padding="same", activation="relu"))
model.add(AveragePooling2D(strides=(2,2), padding="same"))
# model.add(Dropout(0.2))

model.add(Conv2D(128, 3, padding="same", activation="relu"))
model.add(AveragePooling2D(strides=(2,2), padding="same"))
# model.add(Dropout(0.2))

model.add(Conv2D(128, 3, padding="same", activation="relu"))
model.add(AveragePooling2D(strides=(2,2), padding="same"))
# model.add(Dropout(0.2))

model.add(Conv2D(256, 3, padding="same", activation="relu"))
model.add(AveragePooling2D(strides=(2,2), padding="same"))
# model.add(Dropout(0.2))


model.add(Flatten())
model.add(Dense(256,activation="relu"))
model.add(Dropout(.5))
# model.add(Dense(256,activation="relu"))
# model.add(Dropout(.5))
model.add(Dense(4, activation="softmax"))

model.summary()

Adam(learning_rate=0.0001, name='Adam')
model.compile(optimizer = 'Adam',loss = 'categorical_crossentropy',metrics = ['accuracy'])

为了解决这个问题，我做了几件事：

• I没有在conv层之间使用删除层，
• I缩短了训练较长时间的数据
• 的范围(测试精度下降到62%，val_acc最终达到100%)。

造成这个问题的原因是什么，如何解决呢？如何在Python中显示高精度的测试图像？

Answer 1

您需要在subset='training'中添加train_generator。现在，您正在对培训和验证数据进行培训。

train_generator = train_datagen.flow_from_directory(
    train_dir,
    target_size=(height, width),
    batch_size=batch_size,
    class_mode='categorical',
    seed=13,
    subset='training'
    )