def forward(self, V): self.in_act = V ## We shall use the technique of im2Col as detailed in the notes for the course ## CS231n. However, there are still speed-ups to be had if we could link ## numpy with the BLAS Library A = Vol(self.out_sx, self.out_sy, self.out_depth, 0.0) input_vol = V.w input_vol = input_vol.reshape(V.depth, V.sx, V.sy) inputim2col = im2col(input_vol, [self.filter_sx, self.filter_sy], self.stride) ##Create the filter matrix filtercol = np.zeros((self.out_depth,self.filter_sx*self.filter_sy*self.in_depth)) for i in xrange(self.out_depth): filtercol[i] = self.filters[i].w.flatten() ##Perform the convolution step convolve = np.dot(filtercol, inputim2col) ##Adding biases ##Could be done in a neater fashion for i in xrange(self.out_depth): convolve[i] += self.biases.w[i] A.w = convolve.flatten() self.out_act = A return self.out_act
def forward(self, V): self.in_act = V V2 = Vol(1,1,self.out_depth, 0.0) ##To prevent the exponentials from exploding, ##we follow the advice from the CS231n ##by subtracting the maximum weight ##thereby making the calculation stable V2_weights = V.w max_weight = np.amax(V2_weights) exponentials = np.exp(V2_weights - max_weight) denom = np.sum(exponentials) exponentials /= denom V2.w = exponentials ##We will use the exponentials for backprop self.exponentials = exponentials self.out_act = V2 return self.out_act
