Cherish

Hello! When I run the demo,I also meet a problem that "you must add the matcaffe in your path", but I don't know how to solve it, I have tried...

@ChangyuHu Thank you for your reply !I also have tried to add the path of caffe_.mexa64 to matlab workplace, but it still remind me that error.

@jlevis73 Hello! I want to train my own dataset, but I don't know how to start training when I have made the dataset. could you please tell me about the...

@jlevis73 Thank you for your reply, I guess I know what you mean, and I have tried to modify the function in voc-release5,it's pascal_data(),I think maybe you have used this...

@wyblmj Hello, I had the same question before, but when I change the (w,h) of the test image, I found detection time is close to the size of image, which...

> > FastLLM Error: Linear's weight's shape error 请问这是什么问题呢？fp16的可以正常运行。 > > int4模型是官方的int4模型吗？ readme里可能没说清楚，from_hf里的模型不能是量化模型，需要使用量化模型可以把dtype指定为int8或者int4 对的，下载int4模型或者从hf加载都不行，那我试一下dtype！谢谢大佬！

@xinxin12345 你好，我是直接百度搜了一个做hdf5数据集的博客，然后跟着上面的思路和自己的对应着修改的，你可以参考一下 [https://www.jianshu.com/p/9f382a1460c6](url) 人脸检测框应该是预处理用来裁剪人脸图像的，所以这个我没有当成标签 关键点和姿态应该都要写进标签里 多标签训练 因为我后来没有采用这个代码的训练方式，所以其他细节就没法回答你啦。

@xinxin12345 不好意思，openface我只了解了理论，没有实际使用到，所以不太清楚呐

> 今天在V100上打算测试一下，发现加载chatglm2失败，model_type不对，就重新下载了glm2，但是gpu上会报错：IndexError: piece id is out of range不知道咋回事儿？ 在llm.py里面decode之前打印了输出，不太对，感觉gpu上模型转换有点问题，输出是： [65023, 65023, 65023, 65023, 65023, 65023, 65023, 65023, 65023, 65023, 65023, 65023, 65023, 65023, 65023, 65023, 65023, 65023, 65023, 65023, 65023,...

> 有试过直接用huggingface上直接转好的flm模型吗 刚刚试了，我这边在cpu上正常运行，gpu上就报这个错，玄学了（哭