Why the optimizer.step() write twice？

[San-ctuary]

Anomaly-Transformer/solver.py

Lines 189 to 192 in bfe075e

	loss1.backward(retain_graph=True)
	self.optimizer.step()
	loss2.backward()
	self.optimizer.step()

When the first optimizer.step() execute all the gradient relate to loss1 will update，but some variable in loss2 are common in loss1.So this maybe cause some problem.

[xuchunyu123]

你好，我能问下你这个问题最后是怎么解决的吗，我也是在这里报错

[San-ctuary]

作者已经在别的issue里面回答了，应该是pytorch版本问题，如果不降低版本的话直接把第一个.step注释掉就行

[deepConnectionism]

RuntimeError: one of the variables needed for gradient computation has been modified by an inplace operation: [torch.cuda.FloatTensor [512, 25]], which is output 0 of AsStridedBackward0, is at version 2; expected version 1 instead. Hint: enable anomaly detection to find the operation that failed to compute its gradient, with torch.autograd.set_detect_anomaly(True).

通过楼上的方案解决了 感谢