Anymake
Anymake
> > 匹配 > > 你跑了多少个epoch 原代码设的500 我没跑完发现准确率就到了那个值 你的是多少个epoch到达论文指标的？
> > > > 匹配 > > > > > > > > > 你跑了多少个epoch 原代码设的500 我没跑完发现准确率就到了那个值 > > > > > > 你的是多少个epoch到达论文指标的？ > > 尴尬 窗口关了没记录 训练默认的有log记录下来的，在保存模型的文件夹有个log.log文件
Hi, how about the work on a proper SVG/PDF export ?
> Hi @YELKHATTABI > > After modifying `builtin.py`, you could set a breakpoint at https://github.com/mlzxy/devit/blob/main/detectron2/data/datasets/builtin.py#L327 and use detectron2 dataset interface (https://detectron2.readthedocs.io/en/stable/tutorials/datasets.html#metadata-for-datasets) to inspect the meta data of your dataset, e.g.,...
> Note that when I use certain versions of xformers on some GPU, e.g., 2080 Ti I remember, it sometimes produces inaccurate inference results. Don't know why but I would...
在cuda11.3上这么安装就可以了，很简单 conda create -n YoloWord python=3.8 conda activate YoloWord pip install torch==1.11.0+cu113 torchvision==0.12.0+cu113 --extra-index-url https://download.pytorch.org/whl/cu113 pip install -e .