ousheng

yolov3 image Resolution

3

I would like to ask the tutorial to test the mAP results in various resolutions of yolov3, but I use c++ or python interface test, the images are all adapted...

thank you for your share, I ask if the model saved by tensorflow2.0 can be used on 1.x?

How to decode the naked stream of camera directly

1

Thanks for sharing. I have a problem. I get the naked video stream from the webcam SDK and cache it in a buf space. How can I decode it directly...

c++ deploy

2

Will the C++ version be released in the near future?

Will cuDA standalone mode occupy cuda gpu resources?

4

I want to deploy the yolov5 model on both gpu and dla at the same time. Will there be resource competition issues between the two? What I learned before is...

接入硅基流动免费模型

1

感谢这么好的工具 据https://mp.weixin.qq.com/s/QkrJ86WZcOz_M_aoQOqF8w 消息 硅基流动为国内开发者献上一份前所未有的大礼：Qwen2 (7B)、GLM4 (9B)、Yi1.5（9B）等顶尖开源大模型永久免费 其中接口和openai兼容，看评价速度也比较快，期待加入 from openai import OpenAI client = OpenAI(api_key="YOUR_API_KEY", base_url="https://api.siliconflow.cn/v1") response = client.chat.completions.create( model='alibaba/Qwen1.5-110B-Chat', messages=[ {'role': 'user', 'content': "抛砖引玉是什么意思呀"} ], stream=True ) for chunk in...

YOLOv9-e-convert(gelan) serialize error

1

## Env - GPU, jetson orin. - OS, Ubuntu20.04 - Cuda 11.4 - TensorRT 8.6 command: ./yolov9 -s ../yolov9-e1-converted.wts yolov9-e1-converted.engine ge output: 1 ../yolov9-e1-converted.wts ge yolov9-e1-converted.engine [10/17/2024-10:44:05] [W] [TRT] The...

new mAP “(e2e)” result

5

### Search before asking - [x] I have searched the Ultralytics YOLO [issues](https://github.com/ultralytics/ultralytics/issues) and [discussions](https://github.com/orgs/ultralytics/discussions) and found no similar questions. ### Question The new mAP "(e2e)" metric differs from the...