-
Here is a summary of common training and inference issues.
-
As per https://huggingface.co/hr16/ControlNet-HandRefiner-pruned/discussions/3, you don't actually need to make an openpose stick figure to get the depthmap. All you need is some reliable way of detec…
-
大佬 您好！请问下您有尝试转换yolov8m或者yolov8l转ncnn后做测试吗？我把yolov8l转ncnn后，用您这个项目跑会闪退。是不是我转的步骤有问题？请请教一下您是怎么转的呢。我使用官网的export转的：
from ultralytics import YOLO
model = YOLO("yolov8n-pose.pt")
model.export(format='ncnn…
-
### Search before asking
- [X] I have searched the Ultralytics YOLO [issues](https://github.com/ultralytics/ultralytics/issues) and found no similar bug report.
### Ultralytics YOLO Component
Pred…
-
大佬你好，我的教师网络是改进了的YOLOv8s网络，学生模型是原版YOLOv8n网络，两者的网络结构层数不一致了，这种情况下可以用蒸馏吗？因为我调试代码时报了RuntimeError: running_mean should contain 256 elements not 128错误
-
## Benchmark
| **Model** | **Params (M)** | **FLops@640 (G)** | **Input Size** | **Latency RK3588 (ms)** | **mAP@640** |
| --------------------------…
-
Hi Thanks a lot for releasing the code. I am quite new to using onnx for yolov8 segmentation. I was wondering if you could please provide the onnx file as an example. For example `yolov8s-seg.onnx`. T…
-
Hello，i convert the official pretrained model to the onnx model by
`yolo export model=jameslahm/yolov10{n/s/m/b/l/x} format=onnx opset=13 simplify`
Then, i convert the onnx to the tensorRT-fp16 i…
-
我在3090上面测试了yolov8s.trt，图片是从视频上面解析后保存的，为什么推理图片的耗时（batch_size=1）比推理视频（batch_size=4）的耗时要高。前者是3.2ms; 后者是2.8ms
-
版本：paddleslim2.5 paddledet2.6 paddleYOLO2.5训练出来的 yolov8s模型，根据示例进行自动压缩出错。
我模型导出来，模型输入 为image，这里报错，说data没有image这个属性；该如何修改？？
![image](https://github.com/PaddlePaddle/PaddleSlim/assets/54930060/7725…