-
Notifications
You must be signed in to change notification settings - Fork 109
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
Demo code #8
Comments
@bhack you can check the loader.py and set it to load the images from a different folder (folder created by you with new images from internet) or load a single image. The minimal demo code should looks like:
I haven't write an entire script to test a single image but it should not be too complicated if you read the test.py and detector.py |
Thanks, @fastlater. It's true that you can modify the loader and also turn off evaluation. But ideally, it should be easier than that. |
@dvornikita We will be happy to see a clean demo code from you in the future. Just for testing, I created a new loader and used the functions from detector.py. It was a little bit dirty the code but at least, I got the desired output. |
@bhack, @fastlater, @AlonTetro, the demo has arrived. |
Thank you. Is the demo working with BlitzNet512? |
@dvornikita Thank you for letting me know. I will take a look on it. |
@bhack it does. The only difference with testing is that you don't have a dataset linked to the loader. Just specify the right flags for running the demo as you would do for testing. |
@dvornikita I've asked cause with BlitzNet512 I got |
@dvornikita Results seems goods. I've noted generally that MSCOCO And PASCAL GT segmentation masks are not so precise. Have you tried to add also Davis dataset masks 2016 and 2017 to the training mix? |
@bhack No we didn't. The strength of the method is to discover some hidden correlations in bounding boxes and segmentation annotations to reduce class confusion for both and make localization of boxes more precise, while still being realtime. I guess the Davis dataset has only segmentations and if you want them more accurate it would make more sense to use a state-of-the art segmentation method. |
@dvornikita Yes I understand the original scope. But I still think that Blitznet segmentation quality is quite good. I think is not a problem to derive a bounding box from a segmentation Mask like in the Mscoco API official toolkit. |
@bhack I looked closer at the Davis and I agree with you, it's feasible. For sure it can be used at least as a solid pretraining. |
@dvornikita The interesting thing is to evaluate how the quality of the mask influence the segmentation performance of your model. So probably one of the first interesting approach is just to fine-tune on Davis the models that you have already pretrained. |
Seems that all the API requires always the GT cause also the test code works with datasets.
Do you have a minimal demo code to just visually evaluate results on new images from internet?
The text was updated successfully, but these errors were encountered: