Inference of YOLOv8 models exported as onnx models with Embarcadero C++ Builder
Бюджет €200-600 EUR
Job Description:
The Embarcadero C++ Builder version 11.2 should be used for inference models developed with YOLOv8 which are exported as onnx models.
1) Open [login to view URL] (based on the [login to view URL] from YOLOv8) in Colab and run
2) After running through [login to view URL] there are
a) 3 sample models:
- model_det Detection model model_det started with YOLO('[login to view URL]') # load a pretrained YOLOv8n detection model
- model_seg Segmentation model model_seg started with YOLO('[login to view URL]') # load a pretrained YOLOv8n segmentation model
- model_cls Classification model model_cls started with YOLO('[login to view URL]') # load a pretrained YOLOv8n classification model
b) sample results for usage of the models with the sample images (included in the outputs)
3) Each model should be exported as onnx and downloaded for inference calculation on a Windows 10 system using the CPU (no GPU!). Colab notebook (*.ipynb) with export code of models should be given.
4) The exported onnx models have to be used in a C++ Builder project. The basic framework is given in InferenceModels01.zip. Calculation of the sample [login to view URL] (see [login to view URL]) must have same results as in sample01.ipynb.
For the C++ Builder project the following requirements have to be fulfilled:
a) Only direct use of *.c, *.cpp, *.h and *.hpp files, no installation of components. DLLs can be used under certain circumstances, but only after consultation.
b) All used files have to have MIT or similar licence so that they can be used for commercial usage without showing source code.
c) Project works with (and any combination of them)
- configuration debug/release
- platform windows 32 bit/64 bit
- option C++ linker -> link with dynamic RTL true/false
- option packages -> linking with run time packages true/false
Prerequisites:
- access to Embarcadero C++ Builder (current version 11.2; maybe a free test version is available)
- experience with Embarcadero C++ Builder and Delphi
- knowledge and access to Colab
Remarks
- If possible, you are welcome to use [login to view URL]
- documented code has to be delivered
- once more: results must be the same as with original (not exported) models
- It is not possible to get access to my pc
- Payment will only be done if all parts are done sucessfully.
Attached files
- [login to view URL] basic framework C++ Builder project
- [login to view URL] sample for Colab usage
TASKS
Above 3) and 4) have to be done. Of course, I need the source and have to be able to build and run it on my PC (Windows 10).
16 фрилансеров(-а) готовы выполнить эту работу в среднем за €490
Hi there, I have recently done a YOLO project you can see in my profile. I am a full stack developer with 4+ years of experience in both front-end and back-end development. I have read your Run the yolov8 onnx model in Больше
Hi there, My name is Umair. I have good experience with Delphi, C++ Programming, Artificial Intelligence and Python. I am a practicing Developer/Designer Since 2015. I can perfectly work on this project regarding Del Больше
Hello sir I am a Senior Developer specialized in desktop application development having an experience of more than 8+ years. I am very excited to see your job posting as I am confident that I am a perfect fit for what Больше
Hello, I am very familiar with OpenAI/GPT, PyTorch, TensorFlow, Keras, Pandas, sklearn, numpy, GAN, CNN, RNN, LSTM and SVM. I have completed several machine learning projects such as chat bot, trading prediction, senti Больше
Hi, Dear I am a Senior Software developer and I've strong experienced in Software development over 6 years. I am a passionate developer so I can do anything you want. No problem. It seems like me is a great fit for th Больше
Sir, I am well versed in these kind of jobs and can do your project as per requirement. I have over 12 years of experience. I am very much able to work on this. ***I am ready to start Waiting to hear from you. Больше
