redis-camera-ai's Introduction

Redis plugins for Grafana

Introduction

The Redis plugins for Grafana let you connect Grafana to Redis to visualize more types of data in more ways than otherwise would be possible.

All the increased functionality comes with a more streamlined workflow.

Redis Data Source can connect to any Redis database On-Premises and in the Cloud.

Requirements

Grafana 8.0+ is required for Redis plugins 2.X.
Grafana 7.1+ is required for Redis plugins 1.X.

Quick Links

Documentation

License

Redis plugins for Grafana are licensed under the Apache License Version 2.0.

redis-camera-ai's People

Contributors

Stargazers

Watchers

redis-camera-ai's Issues

redis.exceptions.ResponseError: GPU requested but TF couldn't find CUDA

Thanks for your awesome job!
I can run this demo when I use cpu, but I met problems when I try to use gpu.
Below is my dockerfile: I just change the first line of the dockerfile, and switch cpu into gpu, then I can't load the TF-model for redisAI.

FROM redislabs/redisai:edge-gpu-bionic as redisai
FROM redislabs/redistimeseries:edge as redistimeseries
FROM redislabs/redisgears:edge

ENV LD_LIBRARY_PATH=/usr/lib/redis/modules

ARG MODULES=/var/opt/redislabs/lib/modules
ARG RG=${MODULES}/redisgears.so
ARG REDIS="redis-server --loadmodule ${RG} Plugin /var/opt/redislabs/modules/rg/plugin/gears_python.so"

ARG REQ="numpy \
    Pillow \
    opencv-python-headless"
# opencv-python-headless是没有GUI功能的opencv

# Set up a build environment
WORKDIR /data
RUN set -ex;\
    apt-get update;

# Copy RedisTimeSeries
COPY --from=redistimeseries ${LD_LIBRARY_PATH}/*.so ${LD_LIBRARY_PATH}/

# Copy RedisAI
COPY --from=redisai ${LD_LIBRARY_PATH}/redisai.so ${LD_LIBRARY_PATH}/
COPY --from=redisai ${LD_LIBRARY_PATH}/backends ${LD_LIBRARY_PATH}/backends

# Start Redis and install Deps
RUN nohup bash -c "${REDIS}&" && sleep 4 && redis-cli RG.PYEXECUTE "import cv2; GearsBuilder().run()" REQUIREMENTS $REQ \
    && redis-cli save

ENTRYPOINT ["redis-server"]
CMD ["--loadmodule", "/usr/lib/redis/modules/redistimeseries.so", \
    "--loadmodule", "/usr/lib/redis/modules/redisai.so", \
    "--loadmodule", "/var/opt/redislabs/lib/modules/redisgears.so", \
    "Plugin", "/var/opt/redislabs/modules/rg/plugin/gears_python.so"]

Here is the traceback msg:

redisedge-init-1       | Loading model - Traceback (most recent call last):
redisedge-init-1       |   File "init.py", line 35, in <module>
redisedge-init-1       |     res = conn.execute_command('AI.MODELSET', 'yolo:model', 'TF', args.device, 'INPUTS', 'input', 'OUTPUTS', 'output', 'BLOB', model)
redisedge-init-1       |   File "/usr/local/lib/python3.7/site-packages/redis/client.py", line 775, in execute_command
redisedge-init-1       |     return self.parse_response(connection, command_name, **options)
redisedge-init-1       |   File "/usr/local/lib/python3.7/site-packages/redis/client.py", line 789, in parse_response
redisedge-init-1       |     response = connection.read_response()
redisedge-init-1       |   File "/usr/local/lib/python3.7/site-packages/redis/connection.py", line 642, in read_response
redisedge-init-1       |     raise response
redisedge-init-1       | redis.exceptions.ResponseError: GPU requested but TF couldn't find CUDA

THANKS!

Recommend Projects