-
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/System Environment:macos
- 版本号/Version:Paddle:2.4.2 PaddleOCR:release/2.6 问题相关组件/Related component…
-
你好,我有一些疑问想请教一下,期待回复。 我在复现DB++算法的时候,骨干网络是ResNet50,不使用预训练模型 pretrained_model = None,模型训练过程评估指标都为0。我以为不使用预训练模型,随着模型的训练,ResNet50网络中的参数会慢慢的学习,不太明白为什么会为0,是还需要其他的配置吗?
当我把骨干网络换成MobileNetv3,且同样pretrained_mod…
-
作者您好,之前有提过“onnx 无法导出 F.threshold 函数,所以需要把 mobilenet SE 模块中的 HardSigmoid() 替换掉”,能否详细解释一下如何将更换主干的网络进行导出
-
Hello author,
I trained my own data using the method in your paper, and I output all the noise data. I analyzed these noise data, but some of them were not very accurate. Although I achieved high acc…
-
I have my own datasets-it is an image i need to detect all the text in an image it contain both Arabic and English text.
What per-trained model we can use for training?
what type of dict we need t…
-
### Bug description
- implementation is still troublesome on CPU (grouped convolutions)
- is not ONNX exportable (some strange error messages)
- cannot be pushed to the huggingface hub (raise wit…
-
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/System Environment:Ubuntu18.04
- 版本号/Version:Paddle: PaddleOCR: 问题相关组件/Related components:
- 运行指令/…
-
Hi, I have quite a problem to use keras_core together with tflite converter..
minimal reproducible example is here:
```
import os
import keras_core as keras
def get_model():
# Create…
-
是这样的,我的服务器上有四张T4卡,但是使用paddleocr推理时只用了0号卡,其余几张卡都是空闲状态,环境变量设置了`export CUDA_VISIBLE_DEVICES=0,1,2,3`,请问要怎样才能利用所用GPU?麻烦大佬解答一下。
-
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/System Environment:
- 版本号/Version:Paddle: PaddleOCR: 问题相关组件/Related components:
- 运行指令/Command Cod…