replace out+=residual with out=out+residual

[QingYunA]

out+=residual is a inplace operation which will cause erros below (pytorch version : 1.13.1),use output=output+residual can solve this error.

RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [4, 32, 64, 64, 64]], which is output 0 of ReluBackward0, is at version 1; expected version 0 instead. Hint: enable anomaly detection to find the operation that failed to compute its gradient, with torch.autograd.set_detect_anomaly(True).