mrzihan / hnr-vln Goto Github PK

When i want to build an environment in the server i meet a problem below. this problem occurs while installing the python packages(tinycudann,torch_kdtree,pyliblzfse). i have worked on this problem about 1 week and tired al the methods proposed online . But they do not work. Did you meet the problem? thanks

Hi, thanks for this fantastic work. I'm very interested in the source code and its release date. l wonder when it will be available?
Thanks!

Hi,
When I try to run this code, I find some problem, "from habitat_extensions.discrete_planner import DiscretePathPlanner
ModuleNotFoundError: No module named 'habitat_extensions.discrete_planner". Could you provide this file?

When I try to download the Habitat-Matterport 3D Research Dataset (HM3D) from habitat-matterport-3dresearch, It goes to Matterport's account. I found that the link in the dataset is invalid, where should I download the dataset?

This is really a nice work! But there are some questions I want to ask.
I found that when I set NUM_ENVIRONMENTS>1, this code will run fail. Is that because in this method NUM_ENVIRONMENTSonly can be 1? And by the way, how much time does the training procedure take?

Dear author:
Thanks for your great work. When I was creating a conda environment following the requirements.txt. I found there are some packages followed with @filepath/ instead of version. Could you help me and provide a file without file path?Thanks so much.

Dear author:
When I try to run "run_nerf.py", It shows the following problems:
" File "/home/user/dxf/HNR-VLN-main1/habitat-lab/habitat/core/embodied_task.py", line 275, in _init_entities
task=self,
File "/home/user/dxf/HNR-VLN-main1/habitat-lab/habitat/tasks/vln/vln.py", line 60, in init
self.observation_space = spaces.Discrete(0)
File "/home/user/anaconda3/envs/hvln37/lib/python3.7/site-packages/gym/spaces/discrete.py", line 36, in init
assert n > 0, "n (counts) have to be positive"
AssertionError: n (counts) have to be positive"

and

" buf = self.recv_bytes()
File "/home/user/anaconda3/envs/hvln37/lib/python3.7/multiprocessing/connection.py", line 216, in recv_bytes
buf = self._recv_bytes(maxlength)
File "/home/user/anaconda3/envs/hvln37/lib/python3.7/multiprocessing/connection.py", line 407, in _recv_bytes
buf = self._recv(4)
File "/home/user/anaconda3/envs/hvln37/lib/python3.7/multiprocessing/connection.py", line 379, in _recv
chunk = read(handle, remaining)
ConnectionResetError: [Errno 104] Connection reset by peer
Exception ignored in: <function VectorEnv.del at 0x7f11486e6200>
Traceback (most recent call last):
File "/home/user/dxf/HNR-VLN-main1/habitat-lab/habitat/core/vector_env.py", line 588, in del
self.close()",

    Do you have any suggestions? 

Hi! I wonder whether the finetuning stage of MLP for volumn rendering is before the task execution, or is it finetuned online while navigating? In other words, is it simultaneously mapping and navigating or is it finetuned in a specific scene before language navigation task in that scene?