Comments (5)
I just submitted a pull request for yolov8 example #5506 I hope it can be helpful to you.
Hi, I tested the yolov8.cpp example in your PR, but the results are unreasonable. Specifically, I got yolov8n.bin and yolov8n.param following your guide in yolov8.cpp, and your yolov8n example returns many detections with same confidence of 0.5. The result:
我知道这个问题,这个原因不是因为我这边的原因,而是您导出的yolov8.ncnn.* 模型是仅固定支持[1,3,640,640]的模型,并不支持动态shape输入造成的。
这个错误的模型会导致输入进去的数据为了保持图像原比例缩放,并不符合模型要求的[1,3,640,640],实际上有可能是[1,3,640,540],所以模型内部会错位读取图像,对结果造成严重偏差。
只是要尝试效果的话,您可以直接把输入的图片用画图工具或者cv::resize() 修改成640x640的尺寸。
pnnx本身是支持动态shape输入的,您可以去参考 https://github.com/pnnx/pnnx?tab=readme-ov-file#------detailed-options
导出正确的支持动态shape输入的模型,期待您的好消息~🤣
Well, I find out that the problem originates from a bug in your yolov8.cpp
the following lines:
int wpad = (w + MAX_STRIDE - 1) / MAX_STRIDE * MAX_STRIDE - w;
int hpad = (h + MAX_STRIDE - 1) / MAX_STRIDE * MAX_STRIDE - h;
should be modified as:
int wpad = (target_size + MAX_STRIDE - 1) / MAX_STRIDE * MAX_STRIDE - w;
int hpad = (target_size + MAX_STRIDE - 1) / MAX_STRIDE * MAX_STRIDE - h;
from ncnn.
wait for
from ncnn.
I just submitted a pull request for yolov8 example #5506
I hope it can be helpful to you.
from ncnn.
I just submitted a pull request for yolov8 example #5506 I hope it can be helpful to you.
Hi, I tested the yolov8.cpp example in your PR, but the results are unreasonable. Specifically, I got yolov8n.bin and yolov8n.param following your guide in yolov8.cpp, and your yolov8n example returns many detections with same confidence of 0.5. The result:
from ncnn.
I just submitted a pull request for yolov8 example #5506 I hope it can be helpful to you.
Hi, I tested the yolov8.cpp example in your PR, but the results are unreasonable. Specifically, I got yolov8n.bin and yolov8n.param following your guide in yolov8.cpp, and your yolov8n example returns many detections with same confidence of 0.5. The result:
我知道这个问题,这个原因不是因为我这边的原因,而是您导出的yolov8.ncnn.* 模型是仅固定支持[1,3,640,640]的模型,并不支持动态shape输入造成的。
这个错误的模型会导致输入进去的数据为了保持图像原比例缩放,并不符合模型要求的[1,3,640,640],实际上有可能是[1,3,640,540],所以模型内部会错位读取图像,对结果造成严重偏差。
只是要尝试效果的话,您可以直接把输入的图片用画图工具或者cv::resize() 修改成640x640的尺寸。
pnnx本身是支持动态shape输入的,您可以去参考 https://github.com/pnnx/pnnx?tab=readme-ov-file#------detailed-options
导出正确的支持动态shape输入的模型,期待您的好消息~🤣
from ncnn.
Related Issues (20)
- onnx转ncnn后的depthwise层无法加载,显示出现nan
- git submodule update --init failed
- CMake Error at toolchains/ios.toolchain.cmake:649 (get_filename_component):
- 在mac build for android faild
- Use opencv-python-headless for python package? HOT 2
- Segmentation Fault when extracting output ncnn
- Why is my 1D convolution not working?
- memory usage diffrent in CPU and in GPU mode
- layer `torch.roll` not exists or registered, with pnnx to ncnn
- 开启多线程后运行变慢 HOT 3
- 人脸检测点位的模型无法在60pro上推理正确,在之前安卓上是正常的 HOT 2
- windows ncnn::create_gpu_instance”: dll 链接不一致 HOT 1
- Harmony OS Next Build shared lib failed when enable vulkan HOT 1
- Inference Issues with YOLOv8 Model Converted to NCNN HOT 1
- How do you set Vulkan allocators for an extractor in python?
- CPU推理没问题GPU 推理报错 HOT 3
- efficientvit onnx转换为ncnn后出现无参数的LayerNorm,推理时ex.extract()返回-100
- ios非调试中ruapu_init异常 HOT 2
- Upgrade cmake_minimum_required version for ndk r27? HOT 1
- 安卓上ncnn开启Vulkan compute推理后,GPU没有被调用? HOT 2
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from ncnn.