Caffe python圖層底部字符傳遞實現

Question

我正在寫一個caffe python圖層，它沿着特定軸（附加代碼）轉售[0 255]之間的輸入，並且正向傳遞正常工作。這個圖層是否需要向後傳遞？如果是這樣，我該如何執行它？

caffe_root = 'caffe_root'   
import sys 
sys.path.insert(0, caffe_root + 'python') 
import caffe 
import numpy as np 

class scale_layer(caffe.Layer): 

    def setup(self, bottom, top): 
    assert len(bottom)==1 and len(top)==1, "scale_layer expects a single input and a single output" 

    def reshape(self, bottom, top): 
    top[0].reshape(*bottom[0].data.shape) 

    def forward(self, bottom, top): 
    in_ = np.array(bottom[0].data) 
    x_min = in_.min(axis=(0, 1), keepdims=True) 
    x_max = in_.max(axis=(0, 1), keepdims=True) 
    top[0].data[...] = np.around(255*((in_-x_min)/(x_max-x_min))) 

    def backward(self, top, propagate_down, bottom): 
    # backward pass is not implemented! 
    ??????????????????????????? 
    pass 

Answer 1

你的功能是相當簡單的，如果你願意忽略np.around：

對於x=x_min和x=x_max的導數爲零，對於所有其他x衍生爲255/(x_max-x_min)。

這可以通過

def forward(self, bottom, top): 
    in_ = bottom[0].data 
    self.x_min = in_.min(axis=(0, 1), keepdims=True) # cache min/max for backward 
    self.x_max = in_.max(axis=(0, 1), keepdims=True) 
    top[0].data[...] = 255*((in_-self.x_min)/(self.x_max-self.x_min))) 

def backward(self, top, propagate_down, bottom): 
    in_ = bottom[0].data 
    b, c = in_.shape[:2] 
    diff = np.tile(255/(self.x_max-self.x_min), (b, c, 1, 1)) 
    diff[ in_ == self.x_min ] = 0 
    diff[ in_ == self.x_max ] = 0 
    bottom[0].diff[...] = diff * top[0].diff 

來實現，不要忘記測試這個numberically。這可以通過例如test_gradient_for_python_layer來完成。