ia-flash / matchvec

Reconnaître la marque/modèle des véhicules dans une image

MatchVec

Retourne le marque/modèle d'un véhicule à partir d'un cliché, parmi 100 classes fréquentes dans le parc automobile francais.

Obtains the make and model of a vehicle image from the most frequent cars in France.

Installation

Build docker images

make build

Launch dockers

make up

Launch celery worker

make celery

Documentation

Documentation is automatically generated using Github actions and deployed using Github pages.

Utilisation

See iaflash.fr/testapi/matchvec

Test

make test

Sam support

License

Source code has been published using Apache 2.0 license.

© 2019 Agence Nationale de Traitement Automatisé des Infractions (ANTAI), Victor Journé, Cristian Brokate

matchvec's Issues

Add api version and timestamp to response

il faut prévoir dans dans le JSON sortant de vos API de mettre la version de l'API et un timestamp de la génération du JSON

Add steps to simplify lambda layers

Remove double numpy dependencies in opencv and onnx and pandas

Add a license

I suggest using the Apache 2.0 license. Let me know if you want me to make a PR.

faster_rcnn onnx warning

Initializer rpn_head.rpn_reg.bias appears in graph inputs and will not be treated as constant value/weight. This may prevent some of the graph optimizations, like const folding. Move it out of graph inputs if there is no need to override it, by either re-generating the model with latest exporter/converter or with the tool onnxruntime/tools/python/remove_initializer_from_input.py.