-
训练DB检测模型,训练完成后转换为Inference模式预测。
第一次未使用use_dilation,预测的框很小(可能是训练样本的原因),但是预测到了。
python3 tools/infer/predict_det.py --det_algorithm="DB" --det_model_dir="./output/db_mv3_inference/" --image_dir="./test…
-
Hi guys,
I had problem when execute the command
pip install -r requirements.txt
With the following output
_**(env) jetbot@nano-4gb-jp45:~ /WaSR-T$ pip install -r requirements.txt
Collecting …
-
训练PPYOLO时,GPU使用长时间为0,经常GPU沉寂十几秒,活跃一两秒,修改work_num也没明显改善,请大佬们帮忙看看是什么问题。
# 配置文件如下:
```
architecture: YOLOv3
use_gpu: true
max_iters: 50000
log_smooth_window: 100
log_iter: 100
save_dir: outpu…
-
First of of thank you for this wonderful work.
I want to trained Paddle-OCR for Greek+English language. Can anyone guide me the flow of this problem.plz
-
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
- 系统环境/Win11:
- 版本号/Version:Paddle-->paddlepaddle-gpu 2.4.0.post116: PaddleOCR 2.6.1.0: 问题相关组件/无:
- 运行指令/…
-
是否有建议的配置选项
python main.py -a mobilenet_v3_small --epochs 6 --lr 1e-5 --batch-size 64 --pretrained --train_data datasets/ --val_data datasets/ --gpu 0
-
Please make sure that this is a feature request. As per our [GitHub Policy](https://github.com/tensorflow/tensorflow/blob/master/ISSUES.md), we only address code/doc bugs, performance issues, feature …
-
When I try to train the detection model, I get the error message: /home/PaddleOCR/ppocr/ext_op/roi_align_rotated/roi_align_rotated.cc: In function ‘std::vector RoIAlignRotatedBackward(const Tensor&, c…
-
使用了自定义的dict,发现fc层的维度与词典不对应。请问怎么设置FC层的维度?
-
1.
# 评估预训练模型
python tools/eval.py -c configs/det/ch_PP-OCRv3/ch_PP-OCRv3_det_cml.yml -o Global.pretrained_model="./pretrained_models/ch_PP-OCRv3_det_distill_train/best_accuracy"
结果如下:
方案 hmeans
…