liangcanLiao

编译librbox.cpp.code生成的librbox.so与现成提供的的librbox.so文件应该是不一样的吧，请问你能提供下代码吗，因为我想在window上运行，因此要讲动态库转换成 .dll ,所以需要源代码，谢谢

一些文本乱码

7

### 前置确认 - [X] 我确认我运行的是最新版本的代码，并且安装了所需的依赖，在[FAQS](https://github.com/zhayujie/chatgpt-on-wechat/wiki/FAQs)中也未找到类似问题。 ### ⚠️ 搜索issues中是否已存在类似问题 - [X] 我已经搜索过issues和disscussions，没有跟我遇到的问题相关的issue ### 操作系统类型? Railway ### 运行的python版本是? python 3.7 ### 使用的chatgpt-on-wechat版本是? Latest Release ### 运行的`channel`类型是? wx(个人微信, itchat) ### 复现步骤 🕹 提问：bot...

the iamges resized in 224x24 on your example code for preprocess here https://github.com/onnx/models/blob/main/vision/classification/imagenet_preprocess.py but，it resized into 256x256 in https://github.com/onnx/models/blob/main/vision/classification/imagenet_validation.ipynb I thought the 224x224 is wrong，cause is meaningless to resize image...

How is the initial pose defined of the object ?

2

Rotation and translation are relative to a certain initial pose，so，how is the initial pose defined?

to get highter precision dataset

2

@F2Wang Thank you for your excellent work. I got unsatisfactory preformance when training singlehotpose with my own dataset. I guess it may be related to data annotation, I want you...

overfitting

1

train acc near 1 but validation acc lower than 0.1

objName is not defined

2

I want to get bounding box in training images，so I change the branch to pm-render-bounding-box and run run_create_data got errors below. in master branch everything work well Traceback (most recent...

微信掉线

10

### 前置确认 - [x] 我确认我运行的是最新版本的代码，并且安装了所需的依赖，在[FAQS](https://github.com/zhayujie/chatgpt-on-wechat/wiki/FAQs)中也未找到类似问题。 ### ⚠️ 搜索issues中是否已存在类似问题 - [X] 我已经搜索过issues和disscussions，没有跟我遇到的问题相关的issue ### 操作系统类型? Railway ### 运行的python版本是? python 3.7 ### 使用的chatgpt-on-wechat版本是? Latest Release ### 运行的`channel`类型是? wx(个人微信, itchat) ### 复现步骤 🕹 正常在railway上部署...

Why is the ground truth calculated during training?

1

Why not calculate it before training starts so there are no duplicate calculations?