FSCT
FSCT copied to clipboard
SKrisanski
I forked your wonderful program and updated the requirements.txt and a few other files to now work with python 3.10 and Pytorch 2.2.1. I also fixed some of the warnings...
I ran in Windows 10 Anaconda. try to ues las data from Test data TypeError: 'numpy.float64' object cannot be interpreted as an integer Do you have any suggestion ? FSCT-main)...
Updated the required packages so it runs on python 3.11.7 still using a conda environment and verified FSCT working on Mac OS 14 with CPU only (M2 Ultra) using TLS...
Look like stuck at this step [33 lines of output] Traceback (most recent call last): File "/home/student.unimelb.edu.au/haninhn/miniconda3/envs/pdal/lib/python3.12/site-packages/pip/_vendor/pyproject_hooks/_in_process/_in_process.py", line 353, in main() File "/home/student.unimelb.edu.au/haninhn/miniconda3/envs/pdal/lib/python3.12/site-packages/pip/_vendor/pyproject_hooks/_in_process/_in_process.py", line 335, in main json_out['return_val'] = hook(**hook_input['kwargs'])...
I cloned the repo, added a training las file, ran python train.py and got the following: ``` (fsct) [jollyb@styx scripts]$ python train.py Using default number of CPU cores (all of...
It seems to be a problem with cuda, but I tried to reduce the batch size to 1, the training still fails, I use sample.las data. My computer has 40...
Running both train.py and Training Monitor.py at the same time, train.py worked fine, while Training Monitor.py did not display a live view.
What is causing the error as shown in the attached image? 
Hi! Great tool! After segmenting the tree stems, is it possible to cluster the trees one-by-one? So like add an ID or a unique color to the trees, creating identical...
Main changes: - Main file added to invoke code from project root path. Python arguments refactored. - Unused imports removed - FSCT main configuration moved to specific configuration files (config.ini)...
