部署CNN：训练和测试精度高但预测精度低

Question

刚从ML开始，创建了我的第一个CNN来检测人脸图像的方位。我得到的训练和测试精度高达约96-99%超过2组不同的1000张图片(128x128RGB)。然而，当我自行从测试集中预测一个图像时，模型很少预测正确。我认为在测试和预测期间，我将数据加载到模型中的方式肯定有区别。下面是我如何将数据加载到模型中进行训练和测试：

datagen = ImageDataGenerator()
train_it = datagen.flow_from_directory('twoThousandTransformed/', class_mode='categorical', batch_size=32, color_mode="rgb", target_size=(64,64))
val_it = datagen.flow_from_directory('validation/', class_mode='categorical', batch_size=32, color_mode="rgb", target_size=(64,64))
test_it = datagen.flow_from_directory('test/', class_mode='categorical', batch_size=32, color_mode='rgb', target_size=(64,64))

下面是我如何加载图像来进行预测：

image_path='inputPicture/02001.png'
image = tf.keras.preprocessing.image.load_img(image_path)
input_arr = keras.preprocessing.image.img_to_array(image)
reshaped_image = np.resize(input_arr, (64,64,3))
input_arr = np.array([reshaped_image]) 
predictions = model.predict(input_arr)
print(predictions)
classes = np.argmax(predictions, axis = 1)
print(classes)

ImageDataGenerator处理图像的方式与我在预测中处理图像的方式肯定有一些不同。你们能帮个白痴吗？谢谢！

编辑：下面是我的模型

imageInput = Input(shape=(64,64,3))
conv1 = Conv2D(128, kernel_size=16, activation='relu')(imageInput)
pool1 = MaxPooling2D(pool_size=(2, 2))(conv1)
conv2 = Conv2D(64, kernel_size=12, activation='relu')(pool1)
pool2 = MaxPooling2D(pool_size=(2, 2))(conv2)
conv3 = Conv2D(64, kernel_size=4, activation='relu')(pool2)
pool3 = MaxPooling2D(pool_size=(2, 2))(conv3)
flat = Flatten()(pool3)
hidden1 = Dense(16, activation='relu')(flat)
hidden2 = Dense(16, activation='relu')(hidden1)
hidden3 = Dense(10, activation='relu')(hidden2)
output = Dense(4, activation='softmax')(hidden3)
model = Model(inputs=imageInput, outputs=output)
model.compile(loss='categorical_crossentropy', optimizer='adam', metrics=['accuracy'])
history = model.fit(train_it, steps_per_epoch=16, validation_data=val_it, validation_steps=8, epochs=25)
print('here we go!')
_, accuracy = model.evaluate(test_it)
print('Accuracy: %.2f' % (accuracy*100))

Answer 1

您可以尝试的一件事是复制所选择的图像，使其与您训练模型时使用的批处理大小相似。而且，由于训练精度如此之高，看来你的模型一定是过拟合的。因此，如果第一件事不起作用，尝试添加dropout或减少网络中的层数。