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
作者您好,请问一下您的google drive中的.index(item编码文件)是怎么得到的?我尝试按论文实验setting部分和本仓库结构复现物品编码,经过了如下步骤:
amazon_text_emb.py
plm_checkpoint
huggyllama/llama-7B
dataset.emb-llama-td.npy
run.sh
best_loss_model.pth
best_collision_model.pth
generate_indices.py
dataset.index
上述步骤如无特殊说明均使用默认参数。这样生成的物品编码分布和您提供的编码分布有差距,并且最终推荐效果有下降。想请教一下上面的步骤哪里需要修改,才能得到和google drive中相似的码本?十分感谢!!!
The text was updated successfully, but these errors were encountered:
@mitao-cat 您好! 我们在实验中并没有严格使用best_loss_model.pth或者best_collision_model.pth,而是综合loss和collision在最后的几个ckpt中选择一个进行索引生成。另外,目前的RQ-VAE实现相比于最初版本进行了一些改变,如训练时使用lr_scheduler,因此获得的码本确实无法于google drive中完全一样。
Sorry, something went wrong.
No branches or pull requests
作者您好,请问一下您的google drive中的.index(item编码文件)是怎么得到的?我尝试按论文实验setting部分和本仓库结构复现物品编码,经过了如下步骤:
amazon_text_emb.py
的115行的plm_checkpoint
设为huggingface的huggyllama/llama-7B
并运行,生成dataset.emb-llama-td.npy
run.sh
,生成RQ-VAE的ckpt(包含best_loss_model.pth
和best_collision_model.pth
)generate_indices.py
的line45设置为best_loss_model.pth
然后运行,生成dataset.index
上述步骤如无特殊说明均使用默认参数。这样生成的物品编码分布和您提供的编码分布有差距,并且最终推荐效果有下降。想请教一下上面的步骤哪里需要修改,才能得到和google drive中相似的码本?十分感谢!!!
The text was updated successfully, but these errors were encountered: