View Code? Open in Web Editor
NEW
Dockerized Repo for "3D-PV-Locator: Large-scale detection of rooftop-mounted photovoltaic systems in 3D" based on Applied Energy publication.
License: MIT License
Python 99.23%
Dockerfile 0.77%
3d-pv-locator's Introduction
๐ญ Iโm currently a PhD Student at Stanford University with Martin Fischer. You can find out more on my webpage .
๐ฑ Iโm currently learning about geometric and generative deep learning.
โก I'm combining computer vision and remote sensing to decarbonize the building sector.
3d-pv-locator's People
Contributors
3d-pv-locator's Issues
I am having problems installing the environment with conda, do I need to add any additional channels other than the default ones?
The output i am getting is:
conda create --name PV4GER --file requirements.txt
Collecting package metadata (current_repodata.json): done
Solving environment: failed with repodata from current_repodata.json, will retry with next repodata source.
Collecting package metadata (repodata.json): done
Solving environment: failed
PackagesNotFoundError: The following packages are not available from current channels:
typing-extensions==3.7.4.3=pypi_0
pytorch==1.5.1=py3.8_0
torchaudio==0.5.1=py38
torchvision==0.6.1=py38_cpu
Current channels:
My environment is this (MacOS):
conda --version
conda 4.9.2
python --version
Python 3.8.5
Great work on this. But the dependencies are all outdated and it's not possible to install them anymore. By chance do you have a docker image for it?
I can't access the bucket when trying to download the model from AWS.
This is the error message when i simply paste in the command from the instructions.
aws s3 cp --request-payer requester s3://pv4ger/NRW_models/inceptionv3_weights.tar models/classification/
fatal error: An error occurred (400) when calling the HeadObject operation: Bad Request
Did something change in the syntax for AWS or is the bucket not available anymore?
i got my Access tokens correct and the region set as eu-central-1.
Greetings,
Simon