-
我在使用自己的onnx模型时候报错如下:
onnxruntime.capi.onnxruntime_pybind11_state.InvalidArgument: [ONNXRuntimeError] : 2 : INVALID_ARGUMENT : Unexpected input data type. Actual: (tensor(float16)) , expected: (tens…
-
### Search before asking
- [X] I have searched the [issues](https://github.com///issues) and found no similar feature requests.
### Description
User need selection guide.
### Use case
# Object D…
-
### Search before asking
- [X] I have searched the Ultralytics YOLO [issues](https://github.com/ultralytics/ultralytics/issues) and [discussions](https://github.com/ultralytics/ultralytics/discussi…
-
## 复现步骤
使用了来自Ultralytics的[yolov8n.pt](https://github.com/ultralytics/assets/releases/download/v0.0.0/yolov8n.pt)模型导出的yolov8n.onnx(导出命令为`yolo export model=yolov8n.pt format=onnx opset=13`),通过如下脚本进行i…
-
### Describe the issue
Trying out the yolov8 pose models for iOS using ONNX. I have exported the model to ONNX using the following code.
```
from ultralytics import YOLO
# Load a model
for ve…
-
Hello,
I'm trying to convert TorchScript to pnnx, but pnnx inference results are different from TorchScript inference results.
1. QAT model from TensorRT:
[model:]( https://pan.baidu.com/…
-
跑BDD100K数据集用于Traffic Object Detection任务,只需要检测图像中的汽车,跑完我mAP50为77.97,但Recall很低,只有不到60,但别人论文中YOLOv8n、YOLOv5s这些网络recall能有80左右,这差的太多了,mAP50我跟他们差不多。何解?
-
# Performance Metrics
| Model | Test Size | #Params | FLOPs | APval | HorizonJ5 Latency | HorizonJ5 Latency |
|:---------------|:----:|:---:|:--:|:--:|:--:|:--:|
| [YOLOv5-S](https://github.com/u…
-
### Search before asking
- [X] I have searched the Inference [issues](https://github.com/roboflow/inference/issues) and found no similar feature requests.
### Question
im trying to run code that p…
-
[file.txt](https://github.com/FeiGeChuanShu/ncnn-android-yolov8/files/10915729/file.txt)
Hello,
I converted my yolov8n.pt to onnx to param & bin successfully using all the stipulated procedures. How…