Kk875
Kk875
> 非常感谢作者提供这么好的项目，我准备好数据以后，训练突然变为nan是什么原因啊 > > 2022-03-31 23:34:18,384 - mmdet - INFO - Epoch [1][250/3977] lr: 9.970e-03, eta: 12:19:21, time: 0.923, data_time: 0.010, memory: 4583, loss_rpn_cls: 0.0869, loss_rpn_bbox: 0.0403, s0.loss_cls: 0.2751, s0.acc:...
> 我也遇到这个问题了 兄弟，可以交流一下吗？刚才看到你在map杯上提问了，我的邮箱[email protected]，没法联系到你。。。
> 我的经验是调小学习率，希望能帮到你。 > […](#) > ------------------ 原始邮件 ------------------ 发件人: ***@***.***>; 发送时间: 2023年7月5日(星期三) 下午4:57 收件人: ***@***.***>; 抄送: ***@***.***>; ***@***.***>; 主题: Re: [zhaozhen2333/iFLYTEK2021] loss变为nan (Issue #3) 非常感谢作者提供这么好的项目，我准备好数据以后，训练突然变为nan是什么原因啊 2022-03-31 23:34:18,384 - mmdet - INFO -...
> > > > The final test set is confidential 您好，请问模型推理输出各个地区的shp，为什么在Arc GIS pro 中无法显示？
> 修改了transforms.py的代码，还是会报这个错。 请问解决了吗
> thanks for your great work! but i cant use GPU in anylabeling-gpu error： [ WARN:[email protected]] global net_impl.cpp:178 cv::dnn::dnn4_v20230620::Net::Impl::setUpNet DNN module was not built with CUDA backend; switching to CPU...
> @monkeycc Maybe your internet connection is not good to download the model. You can try the following: download from a browser, extract, and load it as a custom model:...
> i wrote this dedicated for this problem if anyone is interested: https://github.com/enekuie/COCO-json-annotations-to-YOLO-txt-format-converter.git hi，Is it possible to convert successfully? The output of this repo is not in coco format, so...
> I followed the instructions and loaded my model successfully,it works very well,Thanks！ But we can go further，We can design an interface to guide users to load their own models...