训练自己的数据集 about objectdetection-onestagedet HOT 5 CLOSED

I think you should modify the following:
1, labels, data_root_dir and other hyper parameters in yolov3.yml
2, if you need, you may modify anchors, thresh in loss

You don't need modify the num_classes which can be deduced from labels in yolov3.yml

I think you don't need weights of other models , you can just train from scratch, it's easy to converge.

from objectdetection-onestagedet.

Thank your for your reply. I have trained the model on my own dataset.

from objectdetection-onestagedet.

Thank your for your reply. I have trained the model on my own dataset.

我也在训练自己的数据集，有些问题想向你请教，请问你的数据集怎么制作放置的为什么我按照VOC2007的数据放置且按照readme的设置后，在执行python examples/train.py Yolov2时出现了FileNotFoundError: [Errno 2] No such file or directory: '/VOCdevkit/train/JPEGImages/0112.jpg'的问题，train文件目录是怎么来的？我并没有在VOCdevkit中创建过train文件夹。

from objectdetection-onestagedet.

@qhykwsw Could you tell me about your own datasets are VOC format (XML) or YOLO format (txt)?

Thank you.

from objectdetection-onestagedet.

Thank your for your reply. I have trained the model on my own dataset.

我也在训练自己的数据集，有些问题想向你请教，请问你的数据集怎么制作放置的为什么我按照VOC2007的数据放置且按照readme的设置后，在执行python examples/train.py Yolov2时出现了FileNotFoundError: [Errno 2] No such file or directory: '/VOCdevkit/train/JPEGImages/0112.jpg'的问题，train文件目录是怎么来的？我并没有在VOCdevkit中创建过train文件夹。

请问您解决了吗

from objectdetection-onestagedet.