admin 管理员组

文章数量: 1184232

RuntimeError: Trying to backward through the graph a second time (or directly access saved tensors after they have already been freed). Saved intermediate values of the graph are freed when you call .backward() or autograd.grad(). Specify retain_graph=True if you need to backward through the graph a second time or if you need to access saved tensors after calling backward.

其中一种思路：检查是否存在计算图的leaf被重新输入新的网络进行跟踪梯度，诸如此类，解决办法参考：

out = model_1(inputs=inputs_1)
out_2 = model_2(inputs=inputs_2, labels=out.detach())
loss = loss_fn(out_2, gts)

本文标签： RuntimeError Graph Time

版权声明：本文标题：RuntimeError: Trying to backward through the graph a second time 内容由网友自发贡献，该文观点仅代表作者本人， 转载请联系作者并注明出处：http://roclinux.cn/b/1755027837a3062415.html， 本站仅提供信息存储空间服务，不拥有所有权，不承担相关法律责任。如发现本站有涉嫌抄袭侵权/违法违规的内容，一经查实，本站将立刻删除。