We read every piece of feedback, and take your input very seriously.
To see all available qualifiers, see our documentation.
Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.
By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.
Already on GitHub? Sign in to your account
我在进行recbole-master的训练的时候,不管跑什么模型,我在debug的时候,他的item_seq都是[1, 50]的tensor,item_seq_len为1的tensor,而我在recbole-DA-master训练的时候debug的item_seq是[256, 50]的tensor,我觉得item_seq应该是[256, 50]的tensor,为什么recbole-master的item_seq是[1, 50]的tensor呢 recbole-master的debug结果: recbole-DA-master的debug结果: 我想问一下这是因为配置文件的不同还是因为训练框架的不同
The text was updated successfully, but these errors were encountered:
我也发现了这个问题,换用老版本的recbole则batch_size正常,我估计是新版本的bug?
Sorry, something went wrong.
@saccharin723 你好,我们检查了一下发现训练的时候batch_size是正常的,你看到的batch_size为1的情况是在计算flops。
solved, thanks a lot!
BishopLiu
No branches or pull requests
我在进行recbole-master的训练的时候,不管跑什么模型,我在debug的时候,他的item_seq都是[1, 50]的tensor,item_seq_len为1的tensor,而我在recbole-DA-master训练的时候debug的item_seq是[256, 50]的tensor,我觉得item_seq应该是[256, 50]的tensor,为什么recbole-master的item_seq是[1, 50]的tensor呢
recbole-master的debug结果:
recbole-DA-master的debug结果:
我想问一下这是因为配置文件的不同还是因为训练框架的不同
The text was updated successfully, but these errors were encountered: