Pip install stuck?

Community Help
1

Hey, I am using Roboflow on my PC and it all work ok
i try to move it to my Raspberry pi 4 so firstly i did pip install roboflow and it started to download and install stuff

after a while it reached “opencv-python-headless” and it just stuck there on building wheels for collected packages - the animation still runs but its been like that for like 40 mins

what should i do?

2

It seems like you’re having trouble installing Roboflow on your Raspberry Pi 4. The issue you’re experiencing might be related to the installation of the opencv-python-headless package, which can sometimes take a long time or fail on certain systems due to its complex dependencies.

However, when deploying Roboflow on a Raspberry Pi, the recommended approach is to use the Roboflow Inference Server, which is available as a Docker container. This method bypasses the need to manually install complex dependencies like OpenCV.

Here are the steps to install the Roboflow Inference Server on your Raspberry Pi:

  1. First, ensure your Raspberry Pi is running a compatible system. You’ll need a Raspberry Pi 4 (or Raspberry Pi 400) running the 64bit version of Ubuntu. You can verify this by typing arch into your Raspberry Pi’s command line and checking that it outputs aarch64 (source).

  2. Install Docker on your Raspberry Pi. You can do this with the following commands:

    curl -fsSL https://get.docker.com -o get-docker.sh
sudo sh get-docker.sh

    (source)

  3. Pull the Roboflow Inference Server from Dockerhub. It will automatically detect that you’re running on a Raspberry Pi and install the correct version:

    sudo docker pull roboflow/inference-server:cpu

    (source)

  4. Run the inference server:

    sudo docker run --net=host roboflow/inference-server:cpu

    (source)

After following these steps, your Raspberry Pi should be ready to make predictions using Roboflow. If you’re still having trouble, please let me know!

Hi! I’m Roboflow’s AI powered bot. This is an automated response powered using AI with knowledge from our docs, blog, knowledge base, and previous forum responses. If you find this to be a helpful answer, please mark it as the solution using the checkbox icon below. If this doesn’t solve your issue, please follow up with what you’ve tried/why, and the community will continue to chime in as usual.