-
期待技术同仁的回复
-
我训练的模型是ssd_mobilenet_v1，推理的时候好像没有区分出来background，我直接拍摄背景的图片去推理，也会识别成某个class，请问下这种情况一般是什么原因。
我用的是VOC格式的数据库，自己收集的数据，请问下需要是不是准备一些负样本会好点，负样本的标注文件该怎么写，我没有在paddle的网站上找到相关资料。
谢谢。
-
i have tried to training pp yolo with my own data
here is my training result
2020-08-25 16:14:57,807-INFO: Save model to output/ppyolo/model_final.
2020-08-25 16:15:11,572-INFO: Test iter 0
202…
-
Dear contributors,
Thanks for sharing your excellent work.
It is shown that PPYOLO outperforms YOLOV4. It would be nice if you could make a comparison between PPYOLO and [YOLOv5?](https://github.com…
-
按照下面的网址更新了相关包之后
https://www.paddlepaddle.org.cn/documentation/docs/zh/install/Tables.html#whl-dev
运行：
!CUDA_VISIBLE_DEVICES=0 python tools/train.py -c configs/ppyolo/ppyolo.yml --eval
仍然出错
Er…
-
我的模型参数:
`YOLOv3:`
` backbone: ResNet`
` yolo_head: YOLOv3Head`
`ResNet:`
` norm_type: bn`
` freeze_norm: false`
` norm_decay: 0.`
` variant: d`
` depth: 50`
` dcn_v2_stages: [5]`
…
-
安装后测试例子无法通过，报错如下
`
\[work@hostname PaddleDetection\]$ python3 ppdet/modeling/tests/test_architectures.py
ss........EE
======================================================================
ERRO…
-
Geth version: 1.10.2-stable, go1.16
OS & Version: Linux Mint 20 Ulyana
Commit hash : 97d11b0187b4695ccf44e3b71b54155fe405a36f
Date: 20210408
It had been running for a number of days, but now it …
-
I'm trying to reproduce this [tutorial](https://timebutt.github.io/static/how-to-train-yolov2-to-detect-custom-objects/) to make sure I understand how things work before training on my data, so I am u…
-
那位技术同仁帮忙看下，定位下问题，谢谢；我的训练日志如下：
2020-09-18 18:59:45,566-INFO: If regularizer of a Parameter has been set by 'fluid.ParamAttr' or 'fluid.WeightNormParamAttr' already. The Regularization[L2Decay, regular…