-
训练的图片如下图:
![image](https://user-images.githubusercontent.com/29670226/86991469-c7a49880-c1d1-11ea-855f-94861c80e84a.png)
预测结果在conf>0.1时,根本检测不到任何目标
-
📚 This guide explains how to use YOLOv5 🚀 **model ensembling** during testing and inference for improved mAP and Recall. UPDATED 25 September 2022.
From https://www.sciencedirect.com/topics/comput…
-
Hello, I am trying to convert yolov5 model.yaml and weight.pt to .cfg and .weights, I found your excellent work here, and finished the steps of project Readme, but I konw nothing about jupyter script…
-
I train the yolov5x release 6.0, with the project: ultralytics/yolov5
I meet the problem about " no Nvinfer.h"
I tried as bkykent said:
"#include "Nvinfer.h" -> #include "NvInfer.h"
"I" changed lo…
-
What is the position of the attention module added in the network when you conduct the experiment?
-
您好,我想问一下在common.py下的C3TR、TransformerBlock和TransformerLayer类是简化了吗?我在您的debug.py看到了您注释一个Transformer模块,两者之间好像不一样
-
我用的是yolov5x去部署,用训练好的pt模型去检测图片效果很好,但是上板测试效果很差(同一张图片,框的数量明细减少),用的是你的修改的官方接口的后处理代码,我利用Vector Comparison比较过caffemodel和mapper_quant之后的结果,虽然中间个别层余弦相似度低于95但是最后一层能达到98,这种情况是什么原因造成的呢?
-
Hi, do you have some tips for optimized training a model that should detect tiny objects, such as the [tiny person?](https://github.com/ucas-vg/TinyBenchmark)
When training a yolox-x (your coco pr…
-
Hello, awesome repo! I just wanted to clarify if the model weights stored in this repo are different than those found in the FathomNet Model Zoo (i.e., did you fine-tune a model on top of the existing…
-
感谢您参与 X2Paddle 社区! 问题模版为了 X2Paddle 能更好的迭代,例如新功能发布、 RoadMaps 和错误跟踪. :smile_cat:
## 问题描述
- 错误信息
Converting node 666 ... 2022-11-09 06:28:18,955-WARNING: convert failed node:onnx__Concat_649, …