def bprop(self, grad, input, output, outGrad):
if self.dropRate > 0.0:
gpu_copy_to(grad * self.dropMask, grad)
gpu_copy_to(transpose(dot(transpose(grad), self.weight.wt)), outGrad)
self.weight.set_grad(dot(grad, transpose(input)))
add_row_sum_to_vec(self.bias.grad, grad, alpha=0.0)
def bprop(self, grad, input, output, outGrad):
if self.dropRate > 0.0:
gpu_copy_to(grad * self.dropMask, grad)
gpu_copy_to(transpose(dot(transpose(grad), self.weight.wt)), outGrad)
self.weight.set_grad(dot(grad, transpose(input)))
add_row_sum_to_vec(self.bias.grad, grad, alpha=0.0)
def fprop(self, input, output, train=TRAIN):
gpu_copy_to(dot(self.weight.wt, input), output)
add_vec_to_rows(output, self.bias.wt)
if train == TEST:
if self.dropRate > 0.0:
output *= (1.0 - self.dropRate)
else:
if self.dropRate > 0.0:
self.dropMask = to_gpu(np.random.uniform(0, 1, output.size).astype(np.float32).reshape(output.shape))
bigger_than_scaler(self.dropMask, self.dropRate)
gpu_copy_to(output * self.dropMask, output)
if PFout:
print_matrix(output, self.name)
def fprop(self, input, output, train=TRAIN):
gpu_copy_to(dot(self.weight.wt, input), output)
add_vec_to_rows(output, self.bias.wt)
if train == TEST:
if self.dropRate > 0.0:
output *= (1.0 - self.dropRate)
else:
if self.dropRate > 0.0:
self.dropMask = to_gpu(np.random.uniform(0, 1, output.size).astype(np.float32).reshape(output.shape))
bigger_than_scaler(self.dropMask, self.dropRate)
gpu_copy_to(output * self.dropMask, output)
if PFout:
print_matrix(output, self.name)