Grove AI vision - Install tensorflow for yolov5-swift error

Products & Technology Grove
1

I’m looking for a way to train a custom model for Grove AI vision to detect vehicles (car/motorbike/bus) and I have followed this guide. But when I install the required packages, it shows errors that cannot find the suitable version.

Cloning into 'yolov5-swift'...
remote: Enumerating objects: 9409, done.
remote: Total 9409 (delta 0), reused 0 (delta 0), pack-reused 9409 (from 1)
Receiving objects: 100% (9409/9409), 22.61 MiB | 7.55 MiB/s, done.
Resolving deltas: 100% (6269/6269), done.
/content/yolov5-swift
ERROR: Could not find a version that satisfies the requirement tensorflow==2.9.0 (from versions: 2.12.0rc0, 2.12.0rc1, 2.12.0, 2.12.1, 2.13.0rc0, 2.13.0rc1, 2.13.0rc2, 2.13.0, 2.13.1, 2.14.0rc0, 2.14.0rc1, 2.14.0, 2.14.1, 2.15.0rc0, 2.15.0rc1, 2.15.0, 2.15.0.post1, 2.15.1, 2.16.0rc0, 2.16.1, 2.16.2, 2.17.0rc0, 2.17.0rc1, 2.17.0, 2.17.1, 2.18.0rc0, 2.18.0rc1, 2.18.0rc2, 2.18.0, 2.18.1, 2.19.0rc0, 2.19.0)
ERROR: No matching distribution found for tensorflow==2.9.0

Does anyone ever train a custom model could help me?
Is the Grove AI module able to detect multiple objects or only one object, since most models on Sensecraft are for one object detection only?

2

Hi, try executing the following snippet at the very beginning of the Colab first:

%%bash
MINICONDA_INSTALLER_SCRIPT=Miniconda3-4.5.4-Linux-x86_64.sh
MINICONDA_PREFIX=/usr/local
wget https://repo.continuum.io/miniconda/$MINICONDA_INSTALLER_SCRIPT
chmod +x $MINICONDA_INSTALLER_SCRIPT
./$MINICONDA_INSTALLER_SCRIPT -b -f -p $MINICONDA_PREFIX

conda install --channel defaults conda python=3.8 --yes
conda update --channel defaults --all --yes
3

thank you, you’ve save my project

1 Like