littlemountainman / modeld Goto Github PK

My docker file:

FROM ubuntu:20.04

RUN apt-get -y update
RUN apt-get -y install git vim curl python3-pip

RUN git clone https://github.com/littlemountainman/modeld.git
WORKDIR /modeld

COPY sample.hevc /modeld/
RUN pip3 install -r requirements.txt

CMD ["python3", "main.py sample.hevc"]

gives me error:

#9 8.378   Downloading botocore-1.15.26-py2.py3-none-any.whl (6.0 MB)
#9 8.821 Collecting bs4==0.0.1
#9 8.840   Downloading bs4-0.0.1.tar.gz (1.1 kB)
#9 9.030 Collecting cachetools==4.0.0
#9 9.047   Downloading cachetools-4.0.0-py3-none-any.whl (10 kB)
#9 9.089 ERROR: Could not find a version that satisfies the requirement carla==0.9.7 (from -r requirements.txt (line 17)) (from versions: 0.9.5)
#9 9.247 ERROR: No matching distribution found for carla==0.9.7 (from -r requirements.txt (line 17))
------

same error when I try locally on my MacBook Pro in a virtual environment. Appreciate help!

I have a question that why supercombo.keras output points in space? I think the lane line label is in image coordinate, is it?

Hi this is a great implementation. I tried it, really cool. But compared to the current model (new torch model) outputs, the keras model has a relatively large variance, especially for the speed and acceleration.

I'm wondering do you have plans to implement the new torch model?

I have watched your youtube and will try it out on my PC.
what is your discord channel?
My interest is to explore whether this can be ported to rk3399pro which has NPU accelerator and run in realtime.

Thanks,

I converted an mp4 video to hevc format using

ffmpeg -i Driving.mp4 -c:v libx265 -vtag hvc1 output.hevc

as well as

ffmpeg -i Driving.mp4 -c:v libx265 -vtag hvc1 output.mp4

But for both the files I get Data Unreadable error when running the minimal.py file. Also the sample data file mentioned in the readme is not available for download. Help please.

Thank you.

hi, Author.
carla==0.9.7 how to get?

When I carry out orders( pip3 install -r requirements.txt )

ERROR: Could not find a version that satisfies the requirement carla==0.9.7 (from -r requirements.txt (line 17)) (from versions: 0.9.3, 0.9.4, 0.9.5)
ERROR: No matching distribution found for carla==0.9.7 (from -r requirements.txt (line 17))

https://pypi.org/search/?q=carla is carla 0.9.5

I get this error whe running main.py,

I am on windows with python 3.7

Traceback (most recent call last):
File "main.py", line 24, in
fr = FrameReader(camerafile)
File "C:\Users\asus\Desktop\Self Driving\comma supercombo\modeld-master\tools\lib\framereader.py", line 679, in FrameReader
index_data = get_video_index(fn, frame_type, cache_prefix)
File "C:\Users\asus\Desktop\Self Driving\comma supercombo\modeld-master\tools\lib\framereader.py", line 215, in get_video_index
return pickle.load(cache_file)
_pickle.UnpicklingError: invalid load key, '\x00'.

@littlemountainman

Will it be possible to overlay lane/driving prediction to the original video instead of displaying on a separate window?

There is a repository, superdrive below which is similar to your code and I believe it has better memory management. You may want to check it out
https://github.com/NamoDev/SuperDrive

Thanks,