-
for index in range(headNum):
reg = output[index * 2 + 0]
cls = output[index * 2 + 1]
for h in range(mapSize[index][0]):
for w in range(mapSize[index][1]):
…
-
ywdqx updated
2 months ago
-
请问我为啥编译失败啊 Why am I couldn't compile it
(base) liable@liable-G3:~/Documents/YoloV8Pose/rk3588-yolo-demo/src/yolov8/build$ cmake -DCMAKE_TOOLCHAIN_FILE=/home/liable/Documents/RKNN/rk3588_dev_rootfs/t…
-
D Using CPPUTILS: True
I Start importing pytorch...
D import clients finished
W Pt model version is 1.6(same as you can check through ), but the installed pytorch is 1.10.0+cpu. This may cause the …
-
### Checklist
- [X] I have searched related issues but cannot get the expected help.
- [ ] 2. I have read the [FAQ documentation](https://github.com/open-mmlab/mmdeploy/tree/main/docs/en/faq.md) but …
-
请问这可能是什么原因造成的？我的librknnrt.so 和 librga.so 和librknn_api.so都是取自rknn model zoo 2.1.0
1. Model: YOLOv5s
2. input size 640 640
3. activation function: relu
4. threadNum=1, FPS=4, threadNum=2, FPS=8
…
-
### Checklist
- [X] I have searched related issues but cannot get the expected help.
- [X] 2. I have read the [FAQ documentation](https://github.com/open-mmlab/mmdeploy/tree/main/docs/en/faq.md) but …
-
### Checklist
- I have searched related issues but cannot get the expected help.
- I have read related documents and don't know what to do.
### Describe the question you meet
I want to use t…
-
在使用FastDeploy推理PPocrV3模型时,我使用paddle模型转换onnx模型再转成rknn模型在rk3588上进行推理,发现推理结果与在windows上结果差异很大,开始我怀疑是模型在转换过程中出现问题,于是我在pc上对转换后的onnx及paddle原始模型进行推理,发现推理结果受到SetStaticShapeInfer()设置的影响,在pc平台使用paddle模型,onnx模型,在…
-
### Checklist
- [X] I have searched related issues but cannot get the expected help.
- [ ] 2. I have read the [FAQ documentation](https://github.com/open-mmlab/mmdeploy/tree/main/docs/en/faq.md) b…