Skip to main content

MLCVZoo MMDetection Package

Project description

MLCVZoo MMDetection

The MLCVZoo is an SDK for simplifying the usage of various (machine learning driven) computer vision algorithms. The package mlcvzoo_mmdetection is the wrapper module for the mmdetection framework.

Install

NOTE: For some panoptic segmentation models of mmdetection you need to have the panopticapi installed. How this is handled in mlcvzoo-mmdetection is listed below. Otherwise you will get an ImportError.

Install for developer

Clone repository

cd YOUR_PATH
git clone git@git.openlogisticsfoundation.org:silicon-economy/base/ml-toolbox/mlcvzoo-models/mlcvzoo-mmdetection.git
cd mlcvzoo-mmdetection

Create and install python environment

virtualenv .venv
source .venv/bin/activate

# Install dependencies with all extras (including panopticapi)
source build.sh

For VSCode IDE add the relevant environment variables in .venv/bin/activate.

export PYTHONPATH=PARENT_OF_YOUR_REPOSITORY
# The MMDETECTION_DIR is needed in our unit tests for defining the
# path to the configuration files of mmdetection. Since mmdet v2.15.0
# the configuration are stored in the mmdet/.mim/ folder of the installed
# mmdet package in your python environment. For older versions a specific checkout
# is needed.
export MMDETECTION_DIR="$VIRTUAL_ENV/lib/python3.10/site-packages/mmdet/.mim/"

If you want to use the complete functionality of this module including model deployment, you must additionally clone the mmdeploy framework. After cloning the repository, add the environment variable MMDEPLOY_DIR to .venv/bin/activate and set it to the path of the mmdeploy repository.

Install for package users

The following command installs the mlcvzoo-mmdetection package, however we recommend to have a look at the build.sh script. It is gathering all fixes that are needed to setup a running python environment.

pip install mlcvzoo-mmdetection

NOTE: In order to use panoptic segmentations you have to install the following, as specified by mmdetection:

pip install panopticapi @ git+https://github.com/cocodataset/panopticapi.git@7bb4655548f98f3fedc07bf37e9040a992b054b0

Further documentation

Technology stack

  • Python

Project details


Download files

Download the file for your platform. If you're not sure which to choose, learn more about installing packages.

Source Distribution

mlcvzoo_mmdetection-6.9.0.tar.gz (28.8 kB view details)

Uploaded Source

Built Distribution

If you're not sure about the file name format, learn more about wheel file names.

mlcvzoo_mmdetection-6.9.0-py3-none-any.whl (33.0 kB view details)

Uploaded Python 3

File details

Details for the file mlcvzoo_mmdetection-6.9.0.tar.gz.

File metadata

  • Download URL: mlcvzoo_mmdetection-6.9.0.tar.gz
  • Upload date:
  • Size: 28.8 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.2.0 CPython/3.10.12

File hashes

Hashes for mlcvzoo_mmdetection-6.9.0.tar.gz
Algorithm Hash digest
SHA256 c4f125384ad982de94dfbe7f87e9ae835a984273f7c71e69e42edbc3447ab560
MD5 39c4ed6732bc83ca2c792c4143acc8d4
BLAKE2b-256 a70c78cb6b9def589a64b03f21a6a016c8d13ecf2d2eee84ccdd95253af78806

See more details on using hashes here.

File details

Details for the file mlcvzoo_mmdetection-6.9.0-py3-none-any.whl.

File metadata

File hashes

Hashes for mlcvzoo_mmdetection-6.9.0-py3-none-any.whl
Algorithm Hash digest
SHA256 689f184b91a3dab30f7b0d415236075ff40fd451437cc2f09d6d795a3f22dfd8
MD5 72c615713d95ea0344b4c7205e81e58b
BLAKE2b-256 266f2079cf6690a6b7e7d5d6fba2f6d58162a3fba429dc67d3c18055e18f0b08

See more details on using hashes here.

Supported by

AWS Cloud computing and Security Sponsor Datadog Monitoring Depot Continuous Integration Fastly CDN Google Download Analytics Pingdom Monitoring Sentry Error logging StatusPage Status page