YOLO-LISA

YOLO-LISA copied to clipboard

I have some questions about how to use the python tool to get the dataset format that we can use. In the lisa.names file we find there were 5 labels that we need:speedLimit, warning, noTurn, stop, pedestrianCrossing, signalAhead. I assume we need to use the extractAnnotations.py to get those annotations for the training and here is what I did
`:~/Desktop/CUelectrical car/DATASET/tools$ python extractAnnotations.py -c [speedLimit, noTurn, stop, pedestrainCrossing, signalAhead]

usage: extractAnnotations.py [-h] [-f acceptedTag] [-c category] [-m 5] {copy,mark,blackout,crop} filename.csv

extractAnnotations.py: error: argument mode: invalid choice: 'noTurn,' (choose from 'copy', 'mark', 'blackout', 'crop') ` Can you help me to find the way that I can convert the dataset into the format that I need? thank you!!

This is what I am using right now to run the "python tool" file how I just got the images but I didn't get the annotations that I want. Any help will be appreciated. thank you!!

python extractAnnotations.py -c warning copy allAnnotations.csv

@zhji2822 I got your problem. The 6 labels (speedLimit, warning, noTurn, stop, pedestrianCrossing, signalAhead) are the superclasses of signs. They are defined in the LISA project papers. You can google their lab's papers. Because of the limited computing power, we did this simplication to detect faster and more accurate. Of course, you can try to deal with the more general one.

yeah, I think you are right. But I still could not find out the way to create the annotated file with Yolo format. You mentioned that we need to edit the python by ourselves. And I am confused how to do that yet.

On Dec 27, 2018 9:42 AM, "Yifan Wang" [email protected] wrote:

@zhji2822 https://github.com/zhji2822 I got your problem. The 6 labels (speedLimit, warning, noTurn, stop, pedestrianCrossing, signalAhead) are the superclasses of signs. They are defined in the LISA http://cvrr.ucsd.edu/vivachallenge/index.php/signs/sign-detection/ project papers. You can google their lab's papers. Because of the limited computing power, we did this simplication to detect faster and more accurate. Of course, you can try to deal with the general one.

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/wyfsh/YOLO-LISA/issues/8#issuecomment-450187644, or mute the thread https://github.com/notifications/unsubscribe-auth/AbmZ5tQqogEdNGjAW6PFxU8rBkVAgQopks5u9PiSgaJpZM4ZiHoR .

I tried crop, copy, Mark, and blackout all last night. And they only output images.

On Thu, Dec 27, 2018, 10:12 AM Zhixian Jin <[email protected] wrote:

yeah, I think you are right. But I still could not find out the way to create the annotated file with Yolo format. You mentioned that we need to edit the python by ourselves. And I am confused how to do that yet.

On Dec 27, 2018 9:42 AM, "Yifan Wang" [email protected] wrote:

@zhji2822 https://github.com/zhji2822 I got your problem. The 6 labels (speedLimit, warning, noTurn, stop, pedestrianCrossing, signalAhead) are the superclasses of signs. They are defined in the LISA http://cvrr.ucsd.edu/vivachallenge/index.php/signs/sign-detection/ project papers. You can google their lab's papers. Because of the limited computing power, we did this simplication to detect faster and more accurate. Of course, you can try to deal with the general one.

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/wyfsh/YOLO-LISA/issues/8#issuecomment-450187644, or mute the thread https://github.com/notifications/unsubscribe-auth/AbmZ5tQqogEdNGjAW6PFxU8rBkVAgQopks5u9PiSgaJpZM4ZiHoR .

@zhji2822 You should carefully read the first 10 lines of evaluateDetections.py and filterAnnotationFile.py. [-c category] -- category should be a txt file.

Thank you!!

On Thu, Dec 27, 2018, 10:31 AM Yifan Wang <[email protected] wrote:

@zhji2822 https://github.com/zhji2822 You should carefully read the first 10 lines of evaluateDetections.py and filterAnnotationFile.py. [-c category] -- category should be a txt file.

— You are receiving this because you were mentioned. Reply to this email directly, view it on GitHub https://github.com/wyfsh/YOLO-LISA/issues/8#issuecomment-450196593, or mute the thread https://github.com/notifications/unsubscribe-auth/AbmZ5tX9CqKtT-rxIPHNQ3kILRTePKQ2ks5u9QPdgaJpZM4ZiHoR .