lixiangMindSpore

Results 36 issues of lixiangMindSpore

2022-03-15 10:16:36.888 | ERROR | yolox.core.launch:_distributed_worker:147 - An error has been caught in function '_distributed_worker', process 'SpawnProcess-1' (6027), thread 'MainThread' (140438034846656): Traceback (most recent call last): File "", line 1,...

### 问题确认 Search before asking - [X] 我已经搜索过问题,但是没有找到解答。I have searched the question and found no related answer. ### 请提出你的问题 Please ask your question 在PP-Picodet的检测头中,为什么没有前景和背景信息?如下图所示 ![image](https://user-images.githubusercontent.com/78945582/184272447-d60287a2-b389-4f37-b9f2-cb2a88f5675f.png)

### 问题确认 Search before asking - [X] 我已经搜索过问题,但是没有找到解答。I have searched the question and found no related answer. ### 请提出你的问题 Please ask your question 基于PP-YOLOE的知识蒸馏方法和代码有吗?多谢专家

### 问题确认 Search before asking - [X] 我已经搜索过问题,但是没有找到解答。I have searched the question and found no related answer. ### 请提出你的问题 Please ask your question 当前有两个基于PP-YOLOE-S训练的模型,一个是检测玩手机的,一个是检测吸烟的,如何将这两个模型的onnx合并,从而得到一个既可以检测玩手机也可以检测吸烟的模型,避免重新训练

**Is your feature request related to a problem? Please describe.** A clear and concise description of what the problem is. Ex. I'm always frustrated when [...] How to use bagua...

![image](https://user-images.githubusercontent.com/78945582/180917869-ca6668f5-a99b-4419-b511-d305469e9631.png) Your experiment is based on COCO dataset? If it is true, some data is not consistent the official data.

![image](https://user-images.githubusercontent.com/78945582/180917571-eb381ece-9085-42ce-be2f-6da780218988.png) Yolov6 is anchor-free,please correct the information.

How to download ViT-L/14 and ViT-L/14@336px? Thank you so much!

## 🚀 Feature A clear and concise description of the feature proposal. How about the FLOPs of Centernet2? vs YOLOX, which is better? ## Motivation & Examples Tell us why...

enhancement

我当前有训练集和验证集,具体格式如下图所示,如何转成CSP-YOLO可训练的数据格式? ![image](https://user-images.githubusercontent.com/78945582/141225852-9e016aa8-fdb6-4303-9a02-93fd659a96c7.png) 其中,txt格式如下所示 class_id cx/w cy/h box_w/w box_h/h 0 0.510814878287011 0.33199194073677063 0.04678068331669093 0.12072434276342392