class loss(Function):
@staticmethod
def forward(ctx,x,INPUT):
batch_size = x.shape[0]
X = x.detach().numpy()
input = INPUT.detach().numpy()
Loss = 0
for i in range(batch_size):
t_R_r = input[i,0:4]
R_r = t_R_r[np.newaxis,:]
t_R_i = input[i,4:8]
R_i = t_R_i[np.newaxis,:]
t_H_r = input[i,8:12]
H_r = t_H_r[np.newaxis,:]
t_H_i = input[i,12:16]
H_i = t_H_i[np.newaxis,:]
t_T_r = input[i, 16:32]
T_r = t_T_r.reshape(4,4)
t_T_i = input[i, 32:48]
T_i = t_T_i.reshape(4,4)
R = np.concatenate((R_r, R_i), axis=1)
H = np.concatenate((H_r, H_i), axis=1)
temp_t1 = np.concatenate((T_r,T_i),axis=1)
temp_t2 = np.concatenate((-T_i,T_r),axis=1)
T = np.concatenate((temp_t1,temp_t2),axis=0)
phi_r = np.zeros((4,4))
row, col = np.diag_indices(4)
phi_r[row,col] = X[i,0:4]
phi_i = np.zeros((4, 4))
row, col = np.diag_indices(4)
phi_i[row, col] = 1 - np.power(X[i, 0:4],2)
temp_phi1 = np.concatenate((phi_r,phi_i),axis=1)
temp_phi2 = np.concatenate((-phi_i, phi_r), axis=1)
phi = np.concatenate((temp_phi1,temp_phi2),axis=0)
temp1 = np.matmul(R,phi)
temp2 = np.matmul(temp1,T) # error
H_hat = H + temp2
t_Q_r = np.zeros((4,4))
t_Q_r[np.triu_indices(4,1)] = X[i,4:10]
Q_r = t_Q_r + t_Q_r.T
row,col = np.diag_indices(4)
Q_r[row,col] = X[i,10:14]
Q_i = np.zeros((4,4))
Q_i[np.triu_indices(4,1)] = X[i,14:20]
Q_i = Q_i - Q_i.T
temp_Q1 = np.concatenate((Q_r,Q_i),axis=1)
temp_Q2 = np.concatenate((-Q_i,Q_r),axis=1)
Q = np.concatenate((temp_Q1,temp_Q2),axis=0)
t_H_hat_r = H_hat[0,0:4]
H_hat_r = t_H_hat_r[np.newaxis,:]
t_H_hat_i= H_hat[0,4:8]
H_hat_i = t_H_hat_i[np.newaxis,:]
temp_H1 = np.concatenate((-H_hat_i.T,H_hat_r.T),axis=0)
H_hat_H = np.concatenate((H_hat.T,temp_H1),axis=1)
temp_result1 = np.matmul(H_hat,Q)
temp_result2 = np.matmul(temp_result1,H_hat_H)
Loss += np.log10(1+temp_result2[0][0])
Loss = t.from_numpy(np.array(Loss / batch_size))
return Loss
@staticmethod
def backward(ctx,grad_output):
print('gradient')
return grad_output
def criterion(output,input):
return loss.apply(output,input)
这是我的损失函数。但它显示了错误:追溯(最近一次通话):
文件“ /Users/mrfang/channel_capacity/training.py”,第24行,在loss.backward()文件“ /Users/mrfang/anaconda3/lib/python3.6/site-packages/torch/tensor.py”,150行,向后torch.autograd.backward(自己,渐变,retain_graph,create_graph)文件“ /Users/mrfang/anaconda3/lib/python3.6/site-packages/torch/autograd/init.py”,第99行,向后allow_unreachable = True)#allow_unreachable标志RuntimeError:function lossBackward返回了错误数量的渐变(预期2,得到1)
我该如何解决。非常感谢
您的forward(ctx,x,INPUT)
有两个输入x
和INPUT
,因此backward
也应输出两个梯度,即grad_x
和grad_INPUT
。
另外,在您的代码段中,您并不是真正在计算自定义渐变,因此您可以使用Pytorch的autograd进行计算,而无需定义特殊的Function
。
如果这是有效的代码,并且您要定义自定义损失,这是backward
应该包括的内容的快速样板:
@staticmethod
def forward(ctx, x, INPUT):
# this is required so they're available during the backwards call
ctx.save_for_backward(x, INPUT)
# custom forward
@staticmethod
def backward(ctx, grad_output):
x, INPUT = ctx.saved_tensors
grad_x = grad_INPUT = None
# compute grad here
return grad_x, grad_INPUT
您不需要为不需要的输入返回梯度,因此可以为它们返回None
。