LutaoChu

Results 9 comments of LutaoChu

[General Issue]

你好，目前没有其他大小的backbone预训练模型，HRNet_W48_NV是从nvidia那边转过来的

Implementation of equibatch?

Hi, great work! Could you share more details about equibatch or its implementation? Thanks very much!

cannot run example

Please take a look

cannot run example

It works. Thx a lot!

Why add the following code snippet since it would bring some errors?

> > 有趣的是，我的 alpaca run 产生了一个 36mb 的文件，并且取得了非常好的结果。然后，当我合并它并尝试微调我自己的自定义数据集时，模型拒绝改进，我的 adapter_model.bin 是字节。 > > 也许 peft 更新也打破了这个？我会尝试验证这是否仍然有必要。 > > +1。在使用 lora on 微调 llama-7b 时，性能也很差`alpaca_data.json`。 我认为这也是peft更新的问题。 > > [我的结果与#326](https://github.com/tloen/alpaca-lora/issues/326)相同。 > > 仅供参考，...

An error was reported when run finetune.py

@dsh54054 Do you solve the problem? I met the same problem

Multi-GPU training for LiDAR and fusion exp

I ran into the same problem. The little difference is that when in fusion modality and batch=1, multi-GPU training is normal. Do you know how to solve this problem? @Song-Jingyu

Multi-GPU training for LiDAR and fusion exp

Thanks for the response. From the error logs it looks like it should be a GPU memory related issue, why do you say it's because of the LIMITED CPU/RAM?

AssertionError: Samples in split doesn't match samples in predictions.

Same question. Please take a look @sczhou21 @kebijuelun @DHuiTnut Do you have a resolution?