-
i am newer in openvino and i am trying to implement in on colab for action recognition , i fellow the demo but got the following problem
![image](https://user-images.githubusercontent.com/922308…
-
### OpenVINO Version
2023.3
### Operating System
Other (Please specify in description)
### Device used for inference
NPU
### Framework
None
### Model used
yolov8
### Issu…
-
**Describe the bug**
When I try to build `onnxruntime` with OpenVINO support, as instructed in the [official instructions](https://onnxruntime.ai/docs/build/eps.html#openvino), `1 - onnxruntime_test_…
-
Actually, I have already got the IR models about MTCNN( including all the nets .xml and .bin). I was wondering if anyone could tell me how to make an inference in OpenVINO or how to write the scripts …
-
[ 81%] Building CXX object CMakeFiles/monitor.dir/src/main.cpp.o
/home/jeetendra/object-size-detector-cpp/src/main.cpp: In function ‘void frameRunner()’:
/home/jeetendra/object-size-detector-cpp/src…
-
I wanted to implement custom_model according to your instructions, but the following error occurred when converting to openvino
How did you solve it, could you help me?
```
[ ERROR ] Cannot in…
-
(clip4str) root@Lab-PC:/workspace/Project/OCR/CLIP4STR# bash scripts/vl4str_base.sh
abs_root: /home/shuai
model:
_convert_: all
img_size:
- 224
- 224
max_label_length: 25
charset_t…
-
I adjusted the input resolution of the model, from 416*416 to 736*256. how to convert it to openVINO? just need to modify this?
![image](https://user-images.githubusercontent.com/45247320/112420120…
-
The project is so cool. Using TensorRT or OpenVINO to optimize the model to a lower precision could increase the performance of the edge inference. BTW is the project accepting any pull requests?
-
可以提供onnx的模型版本,或者如何输出onnx,或者openvino的方式吗?
如果是pytorch的模型,可以提供一个可以直接部署使用的安装包吗?
因为当前的提供的包含了训练/评估/测试等功能的,在部署模型的时候,这些可能都是不需要的,
只需要部署一个最简单的,包含预处理/推理/返回结果即可。