Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Can we adapt the server to Yolo v3? How to get proper .pb file? #2

Open
locoda opened this issue Apr 19, 2019 · 4 comments
Open

Can we adapt the server to Yolo v3? How to get proper .pb file? #2

locoda opened this issue Apr 19, 2019 · 4 comments
Assignees
Labels
new feature New feature has been requested.

Comments

@locoda
Copy link

locoda commented Apr 19, 2019

Since I noticed that your project used .pb file for graph, how you get that? We tried several projects, and got errors like
Op type not registered 'LeakyRelu' in binary running on xxx. Make sure the Op and Kernel are registered in the binary running in this process.
How you get a proper .pb file?

@szaza
Copy link
Owner

szaza commented Apr 20, 2019

Hi,
Unfortunately, the current version does not support the YoloV3 model. The current version uses the following classifier to parse the output tensor and to display it on the output stream: https://github.com/szaza/tensorflow-java-examples-spring/blob/master/src/main/java/edu/ml/tensorflow/service/classifier/YOLOClassifier.java; A similar classifier should be written for the YoloV3. The current classifier has been implemented based on the Yolo9000 article: https://arxiv.org/pdf/1612.08242.pdf;
To implement the YoloV3 classifier please have a look at the following article: https://pjreddie.com/media/files/papers/YOLOv3.pdf;

@szaza szaza self-assigned this Apr 20, 2019
@szaza
Copy link
Owner

szaza commented Apr 20, 2019

Unfortunately, in the current days I do not have too much time to add yolov3 support for this project, however I would be very happy if I could review a pull request with this new feature. I would also provide you some instructions to develop this feature. For this reason I created a new branch: https://github.com/szaza/tensorflow-java-examples-spring/tree/feature/add-yolov3-support; I would be happy if I could add you as a contributor to the project. @spaul13 already started to implement it and I believe we could develop it together.
If anybody else is interested in this feature, please let me know and I'll add them as a contributor.

@szaza szaza added the new feature New feature has been requested. label Apr 20, 2019
@swzaaaaaaa
Copy link

Could you support GPU computing under windows10 system?

@NeighborhoodCoding
Copy link

NeighborhoodCoding commented Sep 10, 2020

Hi, I have question personally... I have my yolo model and I know python but not JAVA. I want to connect my TF by JAVA laguage... What should I study? your code is good reference for me, I should change "https://github.com/szaza/tensorflow-java-examples-spring/blob/master/src/main/java/edu/ml/tensorflow/service/classifier/YOLOClassifier.java" to custom as my yolo model? (TF input, output connecting by JAVA) (Also, actually my code is pytorch...;;)

Sign up for free to join this conversation on GitHub. Already have an account? Sign in to comment
Labels
new feature New feature has been requested.
Projects
None yet
Development

No branches or pull requests

4 participants