我们在 YOLO 的输出层使用哪个激活函数？

Question

我已经在 Keras 中构建了一个简单的 YOLO 定位模型，

model_layers = [
    keras.layers.Conv2D( 32 , input_shape=( input_dim , input_dim , 3 ) , kernel_size=( 3 , 3 ) , strides=1 , activation='relu' ),
    keras.layers.Conv2D( 32 , kernel_size=( 3 , 3 ) , strides=1 , activation='relu' ),
    keras.layers.MaxPooling2D( pool_size=( 2 , 2 ) , strides=2 ),
    keras.layers.Conv2D( 64 , kernel_size=( 3 , 3 ) , strides=1 , activation='relu' ),
    keras.layers.Conv2D( 64 , kernel_size=( 3 , 3 ) , strides=1 , activation='relu' ),
    keras.layers.MaxPooling2D( pool_size=( 2 , 2 ) , strides=2 ),
    keras.layers.Conv2D( 64 , kernel_size=( 3 , 3 ) , strides=1 , activation='relu' ),
    keras.layers.Conv2D( 64 , kernel_size=( 3 , 3 ) , strides=1 , activation='relu' ),
    keras.layers.MaxPooling2D( pool_size=( 2 , 2 ) , strides=2 ),
    keras.layers.Conv2D( 128 , kernel_size=( 3 , 3 ) , strides=1 , activation='relu' ),
    keras.layers.Conv2D( 128 , kernel_size=( 3 , 3 ) , strides=1 , activation='relu' ),
    keras.layers.Conv2D( 64 , kernel_size=( 3 , 3 ) , strides=1 , activation='relu' ),
    keras.layers.Conv2D( 64 , kernel_size=( 3 , 3 ) , strides=1 , activation='relu' ),
    keras.layers.Conv2D( 32 , kernel_size=( 3 , 3 ) , strides=1 , activation='relu' ),
    keras.layers.Conv2D( 8 , kernel_size=( 3 , 3 ) , strides=1 ),
]

model = keras.models.Sequential( model_layers ) 
model.compile( loss=yolo_keras_loss , optimizer=keras.optimizers.Adam( lr=0.0001 ) )
model.summary()

据观察，最后一层的激活函数是 'linear'。

But with regards to YOLO's output, all the values ( confidence score, bounding box coordinates and class probabilities ) are normalized. So should I use a sigmoid activation function or a linear activation function?

我在任何有关 YOLO 的资源中都找不到输出层的激活函数。

Answer 1

如果你参考original paper，他们对最后一层使用线性激活。在“2.2.训练”部分您可以找到：

We use a linear activation function for the final layer and all other layers use the following leaky rectified linear activation...

我们在 YOLO 的输出层使用哪个激活函数？

Which activation function do we use in the output layer of YOLO?

classification

object-detection

keras

tensorflow

yolo