Object Detection with YOLOX (PyTorch) - training with python in Colab, inference with C++
€30-250 EUR
已完成
已发布超过 1 年前
€30-250 EUR
货到付款
SAMPLE DATA
===========
Sample images are in the attached zip [login to view URL] under
CreatedImages
The annotations are given in the text files
[login to view URL]
[login to view URL]
Suppose data is in Google Drive under
'/content/gdrive/MyDrive/SampleObjectDetection02/od01/'
So start with an Colab notebook like:
from [login to view URL] import drive
[login to view URL]("/content/gdrive", force_remount=True)
dir = '/content/gdrive/MyDrive/SampleObjectDetection02/od01/'
%cd {dir}
TASKS
=====
I) Training in Colab
--------------------
Remark: This all has to be done in Colab. (For development you nust ahve a Colab environment on your own!)
1) Prepare data for use in training using a pretrained YOLOX model
2) Train model and show how to set the following training features:
- selection of pretrained model (YOLOX-s, YOLOX-x,...)
- settings for data augmentation, at least :
* rotation with limits for angle
* flipping vertical and horizontal
* brightness and/or contrast with limits for brightness/contrat
* zoom with limits for zoom factor
- how to freeze layers
- use of tensorboard
3) Evaluate model, calculate measures for goodness of model abritray test data
4) Inference: Use model with a specific image, show results (rectangles around objects found), save results as tab-delimited text file
-> Send notebook which I can run in Colab
II) Inference with C++
----------------------
Remark: It is fine to use OpenCV (C++) via vcpkg for this part.
1) Setup a concole C++ Visual Studio 2021 project (or Embarcadero C++ Builder 11 project)
2) Use trained model from above
3) Calculate specific image, show results (rectangles around objects found), save results as tab-delimited text file
-> Send source code for C++ project
Both tasks have to be done sucessfully on my machine before payment is released. Of course, I have tp be able to perform the training in my Colab and build and run the C++ project for inference.
Hi there,
We have been working on Machine Learning and Object Detection for the last three years. We have recently developed:
Size-Invariant Ship Detection YOLOv3 Model from Satellite Images :
[login to view URL]
We have also written a Conference Paper on the same:
[login to view URL]
We have rich experience in the field of Google Colab and Object detection models like YOLO, Faster-RCNN, SSDs etc. We can develop the required project for you using the best suitable algorithms based on your requirements. We can discuss more details in the chat.
Looking forward to hear from you soon.
Regards
Hello Dear,
I hope you are doing fine.
I have almost 5 years of experience in machine learning algorithms. I can implement various types of artificial intelligence algorithms including yours with Matlab, Python and etc. I am doing PhD from Tampere University, Finland and have several journal publications on the subjects. You can see my profile and reviews for related projects.
I read about your project and am interested in working with you. Please send me a message so that we can discuss more.
Warm regards
Uzair
Hi there,
I am an ML engineer. I can start right away and deliver within the deadline. So, Let’s have a quick conversation. I can be more specific once we get all the requirements and information required to execute the project.
Thank you!!
Hello!
The expert you are looking for must be the senior software engineer who is experienced, veryfied and I think I am able to complete that project with resonable price as soon as possible.
I have finished several projects similar to yours and perfectly satisfied clients so I got good reflections from them.
I am sure our relationship will bring us mutual benifits and desirable results.
Thank you!
I am an long-experienced C++ developer who mastered C++, MFC, QT and C#. I have ever developed many professional C++ product with QT and C#. For example, I have ever developed Ladder IDE app for one device company. Its performace was great and get attention from many customers.
I can work in your timezone 8+hours a day.
Once I start the project, I don't stop working.
Please contact me and start right now.
Hello. I read your project description very carefully. I have a deep understanding and experience in the areas of python, Pytorch, C++ that you mentioned. I've previously worked on so many projects for other employers. So, I would like to go through more specific discussions with you to provide successful results. Thank you.
Hello I am good at computer vision.
I am currently working on an object detection competition using yolox and have achieved top results.
We also have sample code so you can quickly produce simple results.
Please contact me!
I am Akashkumar Jain. I am an Automation & Robotics Engineer. I will provide you with best quality of work.
Projects:
- Pedestrian detection and their distance from the camera.
- Gaze-based cursor movement.
- Fire detection from video
- Plant health classification, etc
Skills:
- Python
- ML
- Computer Vision
- MATLAB
- Deep Learning
I am attaching a few of my works for your reference.
Thank you for giving me your precious time.
Thanks,
Akash
I am 10+ years experienced python developer. Well versed with Google colab and pytorch.
I can make your yolox model and help getting it run on your machine.
Thanks,