search

lucastabelini / PolyLaneNet

Code for the paper entitled "PolyLaneNet: Lane Estimation via Deep Polynomial Regression" (ICPR 2020)
https://arxiv.org/abs/2004.10924
MIT License
295 stars 74 forks source link

A problem about modify polynomial degree #41

Closed NARRZ closed 3 years ago

NARRZ commented 3 years ago

Congratulations on your great achievements, I am a beginner and I am very interested in your results. I want to reproduce the data in your paper. If I want to modify the polynomial degree, where should I modify it? Thank you very much.

lucastabelini commented 3 years ago

The key in the config file to be modified is curriculum_steps. I explained how that works here. Also, in the cfgs directory there are three different configs with polynomials of first, second and third order (e.g., tusimple_1order,yaml).

NARRZ commented 3 years ago

Thank you very much.I solved the problem under your suggestion.I want to ask how to draw the training curve and what are the specific commands.Looking forward to your reply.

lucastabelini commented 3 years ago

I will assume that by "training curve" you meant the loss curve. You can use the utils/plot_log.py script for that.

k-nayak commented 2 years ago

@NARRZ and @lucastabelini I was looking for a deep learning model that can compute Lanes and their curvature in real-time and based on the image results I was interested in this implementation, May I know if I can use this for real-time Lane and curvature detection? I plan on using such approaches inside Carla Simulator. I hope to hear from you soon. Thanks.