LC-Rec
LC-Rec copied to clipboard
RUCAIBox
Hi,we are training RQ-VAE with the code in this link: https://github.com/RUCAIBox/LC-Rec/tree/main/index Why did total loss go down first and then up, but reconstruction loss went down gradually? We ran experiments...
You have been experimenting with academic datasets, where the entire item set serves as the candidate set. However, the question arises: how do you address the issue of newly added...
Hi, I noticed you use padding_side='right' in training while 'left' in eval. In my previous experience, padding_side is usually set to 'left' for generation models. (as stated in this [link](https://zhuanlan.zhihu.com/p/675273498)...
Thank you for sharing your code and detailed documentation. I am currently using your code and have encountered a few questions regarding the GPU usage. 1. What is the approximate...
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： 1. 将`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` 2. 运行`run.sh`，生成RQ-VAE的ckpt（包含`best_loss_model.pth`和`best_collision_model.pth`） 3. 将`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！！！
