Replies: 8 comments
-
想问下为什么要fine-tune呢,是我们提供的预训练模型效果较差吗?fine-tune训练的超参数是用的默认配置吗? |
Beta Was this translation helpful? Give feedback.
-
测试了效果不太好,我的排版没有顺序,有些会漏识别或者错识别。训练的超参是默认的configs/picodet/legacy_model/application/layout_analysis/picodet_lcnet_x1_0_layout.yml文件,使用labelme标注的多边形数据,使用x2coco.py转换成训练集和测试集,yml文件配置如下: pretrain_weights: https://paddledet.bj.bcebos.com/models/pretrained/LCNet_x1_0_pretrained.pdparams PicoDet: LCNet: metric: COCO TrainDataset: EvalDataset: TestDataset: worker_num: 8 TrainReader:
EvalReader:
TestReader:
|
Beta Was this translation helpful? Give feedback.
-
Beta Was this translation helpful? Give feedback.
-
Beta Was this translation helpful? Give feedback.
-
想问下导出的inference模型文件直接推理测试会报错吗?以及,可以将该文件提供给我们用于排查问题吗? |
Beta Was this translation helpful? Give feedback.
-
|
Beta Was this translation helpful? Give feedback.
-
请问有最终答复吗?自己数据再fine-tune效果不太好 |
Beta Was this translation helpful? Give feedback.
-
同问 |
Beta Was this translation helpful? Give feedback.
Uh oh!
There was an error while loading. Please reload this page.
-
请提供下述完整信息以便快速定位问题/Please provide the following information to quickly locate the problem
ubuntu 22.04
cuda 11.8
PaddleDetection-2.6.0
使用picodet_lcnet_x1_0_fgd_layout_cdla训练模型上训练自己的数据集
export CUDA_VISIBLE_DEVICES=0,1
python -m paddle.distributed.launch --gpus '0,1' tools/train.py
-c configs/picodet/legacy_model/application/layout_analysis/picodet_lcnet_x1_0_layout.yml
--eval
Beta Was this translation helpful? Give feedback.
All reactions