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-6.8.0.tar.gz (28.4 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-6.8.0-py3-none-any.whl (32.4 kB view details)

Uploaded Python 3

File details

Details for the file mlcvzoo_mmdetection-6.8.0.tar.gz.

File metadata

  • Download URL: mlcvzoo_mmdetection-6.8.0.tar.gz
  • Upload date:
  • Size: 28.4 kB
  • Tags: Source
  • Uploaded using Trusted Publishing? No
  • Uploaded via: twine/6.1.0 CPython/3.10.12

File hashes

Hashes for mlcvzoo_mmdetection-6.8.0.tar.gz
Algorithm Hash digest
SHA256 3f4acdac991d8ffa65a5590de1e197f3ecc013fac8b46af48a9958d4a90807e2
MD5 b17bc218601aabd30dda8de2bf9cd177
BLAKE2b-256 612df894327d525abc5a4ecaa73bb73f0e21e1d40bc7b8301b04199f3bf91996

See more details on using hashes here.

File details

Details for the file mlcvzoo_mmdetection-6.8.0-py3-none-any.whl.

File metadata

File hashes

Hashes for mlcvzoo_mmdetection-6.8.0-py3-none-any.whl
Algorithm Hash digest
SHA256 d7698ef1118d7b65a39138576e86802dd090132ccc6694ce428de9ee3fc7d059
MD5 5416091661548ed05dca155c4df6e62f
BLAKE2b-256 ff3b34979bbf579a505b3e2d308c0c2542a50e3b45d23c674dc7ad9143965da8

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