-
Notifications
You must be signed in to change notification settings - Fork 105
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
How to train FasterSeg with customized labels? #46
Comments
Hi @KHeap25 ! Thank you very much for your interests in our work! First, I have to admit that I have never run this repo for a brand new dataset from scratch. What I can do is try to help you with any bug or problem. Some comments to your steps:
Hope that helps. |
Thanks @chenwydj for your reply! In relation to your recommendation above, I implement a new version of the After passing the step pretrain the supernet, I got the following error during the step search the architecture. It looks like something with the "TensorRT" latency test went wrong. If I remove "TensorRT" from the system, I am able to run all the training and evaluation steps. Are there any important differences between TensorRT and PyTorch for the latency test? I look forward to hearnig from you. Kind regards |
I would guess the tensorrt meets some problem, although you have installed it. Here is the place where the function using tensorrt is imported, you may want to comment out this part: |
Hi @chenwydj, firstly let me summarize the points which I adjusted for using own customized labels.
After doing the steps, I was able to run a training process with customized labels (with PyTorch for latency test). Based on that, I have some questions about the logger for TensorBoard monitoring.
It would be great if you can give me some advice, which would help me to understand the results of the training steps better. Kind regards |
Hi @KHeap25, The "objective" indicates Eq. 5 in our Appendix B. It is a combined target of accuracy and latency, adopted from Tan et al., 2019. The other parts is FPS, and the code is here. Arch0 indicates teacher net, arch1 the student. FPS0 indicates the architecture that aggregates outputs from [1/8, 1/32] branches, and FPS1 the aggregation from [1/16, 1/32]. Hope that helps! |
@KHeap25 can you share your code to see how your modifications got afterall? |
Hey @EmersonJr, @KHeap25 was in the project with me. You can find our code here: https://github.com/Gaussianer/FasterSeg |
Hello,
it's very interesting to train and use FasterSeg with own custom data.
To get information about that, I read the comments of this issue description.
Based on the description linked above, I did the following steps:
2.1 make sure that hight and width are divisible by 32
Are there any other points in the FasterSeg repository which I need to adjust for using customized labels?
For example:
In cityscapes.py, camvid.py and bdd.py are some methodes like get_class_colors() and get_class_names() which return color or class names of the cityscapes data.
Is it neccessary to add the customized labels to this methods?
For which purpose are this methods?
It would be great if you can give me some hints to answer this questions, so I can run the training process with customized labels.
Best regards
The text was updated successfully, but these errors were encountered: