-
I really want to display the result locally using a local camera. I notice that inference_utils.py use pims.PyAVVideoReader to get the imformation about the video. So I really want to know how to call…
-
This should follow the example of #1412 and #1401, including
- Docstring updates
- Colab demonstrating that weight loading works (if pre-trained weights exist) and numerics are identical
-
### 问题描述 Please describe your issue
比如MobileNetV3_large_x1_0的地址是https://paddleseg.bj.bcebos.com/dygraph/backbone/mobilenetv3_large_x1_0_ssld.tar.gz
MobileNetV3_large_x0_5的如果写https://paddleseg.bj.bce…
-
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：windows10, python3.7
- 版本号/Version：2.6 Paddle： PaddleOCR： 问题相关组件/Related compone…
-
版本信息：
python 3.8.8
paddle 2.2.1
cuda 11.6
cudnn 8.2.1
release 2.5
配置：
batch_size_per_card: 1
num_workers: 1
问题：loss不下降了
 and weight type (torch.cuda.FloatTensor…
-
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：ubuntu 20.0.4
版本号/Version：PaddleOCR-release-2.6
config配置如下：`
```yaml
Global:
us…
-
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：ubuntu 20.0.4
- 版本号/Version：PaddleOCR-release-2.6
config配置如下：`
Global:
us…
-
**Describe the bug**
I am working on quantization of few timm models using Torch FX Graph Mode Quantization. Specifically, I am looking into post training static quantization. For static models like …