報錯：
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).
舍棄inplace操作解決方案總結(jié)：
因為新版本torch不再支持inplace操作赤兴，所以要更版本或改變代碼書寫風(fēng)格
調(diào)試過程中使用x.backward()確定產(chǎn)生inplace操作的位置硬鞍，如某處的該語句不報錯簇抵，則之前x操作均正確
- 1）torch版本降為0.3.0（不成功）
- 2）在inplace為True的時候，將其改為Flase指厌，如drop()
- 3）去掉所有的inplace操作
- 4）換掉”-=”“+=”之類的操作呀忧，且用b=a代替a = a
a -=c
==>
b = a.clone() # tensor復(fù)制方式
a = b - c - 避免a.operate(**)不賦值的情況等等
