RelationalGraphLearning
RelationalGraphLearning copied to clipboard
[IROS20] Relational graph learning for crowd navigation
I'm sorry to bother you, I noticed that your code also implements policies such as sarl, I'd like to know how to train those policies
Traceback (most recent call last): File "train.py", line 256, in main(sys_args) File "train.py", line 81, in main logging.info('Current git head hash code: {}'.format(repo.head.object.hexsha)) File "/home/nine_beita/anaconda3/envs/torch/lib/python3.6/site-packages/git/refs/symbolic.py", line 193, in _get_object return...
FAILED tests/scenarios_pedpedspace.py::test_separator - TypeError: 'str' object is not callable FAILED tests/scenarios_pedpedspace.py::test_gate - TypeError: 'str' object is not callable FAILED tests/scenarios_pedpedspace.py::test_walkway[30] - TypeError: 'str' object is not callable FAILED tests/scenarios_pedpedspace.py::test_walkway[60] -...
When I enter the command "python train.py --policy rgl ", it appears" Traceback (most recent call last): File "/home/hurong/RelationalGraphLearning-master/crowd_nav/train.py", line 6, in import importlib.util ImportError: no module named util" I...
Hi, Chen! I'm interested in your work. However,when I run train.py, the problem occured: ` File "train.py", line 255, in main(sys_args) File "train.py", line 79, in main repo = git.Repo(search_parent_directories=True)...
Hello! Thanks for your wonderful work. You predicted the next states of humans with the relational graph containing the robot. However, you also assumed that the robot is invisible to...
Hi, I'd like to listen your opinion on the following issues related to human trajectory prediction on training real datasets. 1. What if the number of people changes at each...
I am reading your excellent code. I found a small bug that failing to load the imitation model. I suggest replacing model.load_state_dict_rl(torch.load(il_weight_file)) with policy.load_state_dict_rl(torch.load(il_weight_file)) in line 138 in train.py. Thanks!
Hi Changan, thanks for the great work! I finished training, but I cannot print the log figure with command `python utils/plot.py data/output/output.log` I looked into the output.log file, and found...
`Output directory already exists! Overwrite the folder? (y/n)y 2023-08-09 19:38:00, INFO: Current git head hash code: 8e87aa5ed8221efd688f8e6857ba4c38637bf6e1 2023-08-09 19:38:00, INFO: Current config content is : 2023-08-09 19:38:00, INFO: Using device:...