-
**问题描述**
根据PaddleDetection提供的[模型压缩文档](https://github.com/PaddlePaddle/PaddleDetection/blob/8377e846439a709f5ab3ac6948d768221b5cf1e6/configs/slim/README.md),我将训练好的ppyoloe plus s模型进行量化训练。量化后的模型,以及导出为…
-
## 描述问题
跑默认的object_detection pipeline高性能模式下的picodet可以正常运行
`paddlex --pipeline object_detection --input https://paddle-model-ecology.bj.bcebos.com/paddlex/imgs/demo_image/general_image_classification…
-
使用paddle2onnx转换mot_ppyoloe_l_36e_pipeline模型到onnx格式,使用onnxruntime加载转换后的onnx模型文件报错。
环境:
ubuntu-22.04
paddle2onnx-1.2.8
PaddlePaddle 2.6.1
onnxruntime-1.19.2
模型文件地址:
https://bj.bcebos.com/…
-
你好,我是基于ppyoloe_plus_crn_s_80e_coco自己训练的模型,导出后在PaddleDetection-2.4版本中的Android_demo中替换了预测库版本为:[v2.14-rc](https://github.com/PaddlePaddle/Paddle-Lite/releases/tag/v2.14-rc)中的inference_lite_lib.android.ar…
-
-
Hi Marcos,
Can you please explain the motivation for changing the models output format in [this commit](https://github.com/marcoslucianops/DeepStream-Yolo/commit/b451b036b2fa9f8b92cb13bb5f4585f8883…
-
Hi, i convert the model from `paddle2torch.py`, using the commond below:
```shell
python paddle2torch.py -f 0 -i ../ppyoloe_plus_crn_s_80e_coco.pdparams -o ppyoloe_s.pth
```
The `ppyoloe_plus_crn_…
-
![image](https://github.com/user-attachments/assets/c479c3ad-b53c-4d22-aa41-fd1f9ab7481e)
![image](https://github.com/user-attachments/assets/d96dcd61-2937-42ca-96a4-acf3a15aa0f2)
安装模式用的FD文档中的Conda指…
-
运行如下代码报错了:[Paddle2ONNX] Oops, there are some operators not supported yet,including fake_channel_wise_quantize_dequantize_abs_max,fake_quantize_dequantize_moving_average_abs_max,
```python
import f…
-
模型转换nb指令 sh opt_linux.sh --valid_targets=huawei_ascend_npu,arm --optimize_out=ppyoloe --model_dir=/share/disk1/bzp/PaddleDetection/ppyoloe_osd_0630/ppyoloe_plus_crn_s_30e_voc_osd_0630/
![error](htt…