Comments (5)
Hi @johnwlambert; L5Kit is still an early release so hopefully a lot of what you suggest will be there soon :)
(1) Would it be possible to add the rendered notebooks with output in Github, rather than just the code?
Having the output in GitHub is a little bit tricky, especially if you want to keep them updated (even now jupyter makes some slight changes like the python version or other metadata). Maybe once the examples will get enough mature adding it won't be that cumbersome.
(2) Would you all be able to make a map notebook, to better understand the format, e.g. road vs. lane geometry, like this notebook?
We don't have that granularity yet, but given that those operations are performed in the code we'll do that if enough interest arises.
(3) To what precision is the aerial imagery aligned with the published map? It looks like Page Mill Road's road geometry doesn't align with the aerial map here:
I can't give you an exact number, but we're working to improve that. We're aware semantic and satellite don't match exactly.
(4) I ran into the following bug when installing requirements on Mac when I follow the setup instructions at
pip install -r requirements.txt
numcodecs
is a zarr
dependency and contains, among other, the blosc
compressor. As far as I know it's implemented in C++ so it may have some system dependencies. You can maybe try to update pip as the latest version may have a pre-compiled wheel for that
from l5kit.
Thanks for the quick reply Luca. I found I was able to push rendered IPython notebooks to Git without much trouble by just saving and committing the file after running all cells.
I found updating my pip
installation didn't resolve those installation errors.
from l5kit.
I found I was able to push rendered IPython notebooks to Git without much trouble by just saving and committing the file after running all cells
yeah but the issue is not pushing them, is keeping them updated. The output cells are build artefacts, and as such it's not a good idea to upload them unless the notebook is very very stable. When things will get stable, we'll consider it.
I found updating my
pip
installation didn't resolve those installation errors.
you can try to install only zarr
in a new env (pip install zarr
). If that doesn't work, you might want to head to the zarr/numcodecs GitHub and ask there for support. zarr can run on mac, so I suspect it might be a system dependencies issue...
from l5kit.
Hi @johnwlambert, regarding the alignment in the figure:
The figure in the paper was aligned manually in adobe illustrator so there is some alignment gap we will fix in the next update. Thanks for pointing this out! This affects only the paper if you actually run the code rasterizes the two maps - aerial and semantic should be aligned very closely (< 1m error).
from l5kit.
That's good to know, thanks @pondruska.
from l5kit.
Related Issues (20)
- How to visualize ego prediction of agents track?
- How to use trained model with live data and own map?
- Highway scenes
- In windows anaconda An error occurs when the sim_outs = sim_loop.unroll(scenes_to_unroll) statement is executed in SimNet ReferenceError: weakly-referenced object no longer exists HOT 2
- Consulting the meanings of several data fields.
- ReferenceError: weakly-referenced object no longer exists HOT 2
- Question on Traffic light face
- Error in the examples/visualisation/visualise_data.ipynb HOT 1
- SafetyNet source code HOT 1
- cannot find .zarr files HOT 2
- FileNotFoundError: [Errno 2] No such file or directory: './agent_motion_config.yaml' HOT 1
- l5kit on mac m1 chip HOT 1
- ReferenceError: weakly-referenced object no longer exists HOT 1
- prediction model
- Example perception solution
- How can I transform the vehicle centroid coord to google map coord? prediction dataset HOT 1
- AgentDataset(cfg, zarr_dataset, rast) Low number of returns
- About the raw data of this dataset HOT 1
- Conner of the download of dataset HOT 1
- THIS PROJECT WAS DISCONTINUED AND IT IS NOT ACTIVELY MAINTAINED
Recommend Projects
-
React
A declarative, efficient, and flexible JavaScript library for building user interfaces.
-
Vue.js
🖖 Vue.js is a progressive, incrementally-adoptable JavaScript framework for building UI on the web.
-
Typescript
TypeScript is a superset of JavaScript that compiles to clean JavaScript output.
-
TensorFlow
An Open Source Machine Learning Framework for Everyone
-
Django
The Web framework for perfectionists with deadlines.
-
Laravel
A PHP framework for web artisans
-
D3
Bring data to life with SVG, Canvas and HTML. 📊📈🎉
-
Recommend Topics
-
javascript
JavaScript (JS) is a lightweight interpreted programming language with first-class functions.
-
web
Some thing interesting about web. New door for the world.
-
server
A server is a program made to process requests and deliver data to clients.
-
Machine learning
Machine learning is a way of modeling and interpreting data that allows a piece of software to respond intelligently.
-
Visualization
Some thing interesting about visualization, use data art
-
Game
Some thing interesting about game, make everyone happy.
Recommend Org
-
Facebook
We are working to build community through open source technology. NB: members must have two-factor auth.
-
Microsoft
Open source projects and samples from Microsoft.
-
Google
Google ❤️ Open Source for everyone.
-
Alibaba
Alibaba Open Source for everyone
-
D3
Data-Driven Documents codes.
-
Tencent
China tencent open source team.
from l5kit.