-
I am testing the semantic segmentation using my custom data set, and the dataset has two classes(particle and crack). I modified the config file in the file **_quick_start/bisenet_optic_disc_512x512_1…
-
### 问题确认 Search before asking
- [X] 我已经查询[历史issue](https://github.com/PaddlePaddle/PaddleSeg/issues)(包括open与closed),没有发现相似的bug。I have searched the [open and closed issues](https://github.com/PaddlePa…
-
Hello,
I'm currently training this model on my own dataset, I have created a separate dataloader python file, the file and folder structure of the dataset is the same as ISIC. No other code other t…
-
RuntimeError: (NotFound) Operator nearest_interp_v2 does not have kernel for data_type[int]:data_layout[ANY_LAYOUT]:place[CPUPlace]:library_type[PLAIN].
[Hint: Expected kernel_iter != kernels.end()…
-
1)PaddlePaddle版本:2.0.1
2)CPU:预测若用CPU,请提供CPU型号,MKL/OpenBlas/MKLDNN/等数学库使用情况
3)GPU:GTX 3070,CUDA 10.1、CUDNN 7.6
4)系统环境:Windows 10,Python 3.6
训练信息
1)单机,单卡
2)显存信息:8G
3)Operator…
-
yaml:
!export CUDA_VISIBLE_DEVICES=0 # 设置1张可用的卡
# windows下请执行以下命令
!set CUDA_VISIBLE_DEVICES=0
!cd work/PaddleSeg && python pdseg/train.py \
--cfg configs/deeplabv3p_resnet50_vd_cityscapes.…
-
*********************************************
温馨提示:根据社区不完全统计,按照模板提问,可以加快回复和解决问题的速度
*********************************************
## 环境
- 【FastDeploy版本】: 说明具体的版本,如FastDeploy-release-1.0.0 Windo…
-
While working on #3125 I came across a quirk: Actions' runners are more bare bones than Travis, and as a result `actions/checkout@v2`, the standard script that downloads our repo to test it, will *get…
-
1. PaddleSeg版本:PaddleSeg 2.6
2. PaddlePaddle版本:PaddlePaddle 2.1.0
3. 操作系统信息:Linux
4. Python版本号:Python3.6
5. CUDA/cuDNN版本:CUDA10.2
6. 其他内容:
!使用paddlaseg里quick_start的bisenet_optic_disc_512x5…
-
不好意思,有一些疑惑想要请教,就是在我们训练模型之前我们会在yml file (例子:bisenet_optic_disc_512x512_1k.yml) 设置一些transforms的设定 (比如:Resize,RandomDistort 等等)再开始训练。我的疑惑是譬如RandomDistort 这样,会随机给我们一些设定数值基于我们的 contrast_range, contrast_pro…