raise RuntimeError("Mismatch in shape: grad_output[" RuntimeError: Mismatch in shape: grad_output[0] has a shape of torch.Size([1]) and output[0] has a shape of torch.Size([]).

[xxz-wow]

deer
how to solve it？in the rl.py
autograd.backward(
[critic_loss] + losses,
[torch.ones(1).to(critic_loss.device)]*(1+len(losses)),
)
raise that problem

[alyaa278]

How can i install ROUGE package? what is the DB_file which should be installed?

[luongtrieuvy202]

deer how to solve it？in the rl.py autograd.backward( [critic_loss] + losses, [torch.ones(1).to(critic_loss.device)]*(1+len(losses)), ) raise that problem

have you solve the problem ?

[xxz-wow]

thanks | | ***@***.*** | | ***@***.*** |

…

---- Replied Message ---- | From | ***@***.***> | | Date | 01/14/2023 20:45 | | To | ***@***.***> | | Cc | ***@***.***>***@***.***> | | Subject | Re: [ChenRocks/fast_abs_rl] raise RuntimeError("Mismatch in shape: grad_output[" RuntimeError: Mismatch in shape: grad_output[0] has a shape of torch.Size([1]) and output[0] has a shape of torch.Size([]). (Issue #73) | deer how to solve it？in the rl.py autograd.backward( [critic_loss] + losses, [torch.ones(1).to(critic_loss.device)]*(1+len(losses)), ) raise that problem have you solve the problem ? — Reply to this email directly, view it on GitHub, or unsubscribe. You are receiving this because you authored the thread.Message ID: ***@***.***>

[DengNingyuan]

I meet the same problem

[DengNingyuan]

deer how to solve it？in the rl.py autograd.backward( [critic_loss] + losses, [torch.ones(1).to(critic_loss.device)]*(1+len(losses)), ) raise that problem

have you solve the problem ?