-
Notifications
You must be signed in to change notification settings - Fork 169
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
[question] any instruction on train multi custom classes? #13
Comments
Hi, yes, you do. In addition you have to modify the loss. Currently it does this:
This is implementation is actually quite ugly and only works for two classes. Make sure that you generate a vector representing class labels as one-hot vector or as numerical class vector. You can then use this vector in combination with: Btw. I am also going to try to reduce the annonlib dependency. So you might want to keep an eye on the next one or two commits. |
@MarvinTeichmann great! I'll give it a try |
This commit can be interesting for #13.
This commit removes a large chunk of Annolib dependency. The data is now loaded directly from the kitti dataset .txt. In addition the loss was improved to utilize a mask for `don't care` areas. The modifications in this commit can be very useful for #13.
As mentioned in the commit messages, keep a close look at the modifications of |
@MarvinTeichmann wow, thank you so much |
@MarvinTeichmann after spending few hours reading the code, i just got some basic understanding of it, and there is an error initializing tf computation graph:
since YOLO v2 is working OK for my project, so i guess i'll try to fine-tune YOLO model first and keeping an eye on KittiBox, definitely gonna test out KittiBox later |
Did you run |
oops! that's my mistake, issue fixed |
@eisneim may I asked which Yolo implementation you are using? I would like to add another baseline to the paper. |
@MarvinTeichmann darknet for training (using YOLOv2 network) use tensorflow implementation darkflow for other stuff, use darknet binary I can get about 30-40fps performance, but accuracy varies across different class due to training datasets(which is hand annotated using my chrome extension) my ultimate goal is to not only detect the object, but also estimate object's surface homography(4 points) so i can replace and render some other image on top of detected surface |
Hi, I want to know that did you change the code to multi class? If you did,can you give me a instruction? I have no idea on the change of code. Thanks a lot if you can answer me. It's better if you can help me. |
Hi, suppose i wanna use kittiBox to detect road-sign, billboard, monitor screen and totally 7 types of object, i seem like i have to modify AnnotationLib.py to make it parse annotation rect with class number.
thanks!
The text was updated successfully, but these errors were encountered: