|
|
113. 【torch】反向传播弃inplace操作
报错：
RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [32, 85742]], which is output 0 of MmBackward, 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).
舍弃inplace操作解决方案总结：
因为新版本torch不再支持inplace操作，所以要更版本或改变代码书写风格
调试过程中使用x.backward()确定产生inplace操作的位置，如某处的该语句不报错，则之前x操作均正确
a -=c
b = a.clone() # tensor复制方式
a = b - c