Object Recognition

This MLHub package, based on a deep learning kubernetes tutorial by Yan Zhang, Mathew Salvaris, and Fidan Boylu Uz of Microsoft, demonstrates the pre-built ResNet152 model using the open source TensorFlow and available from tfhub to identify the main object of a photo. Sample images are provided within the package and the demonstration applies the pre-built model to each image. This pre-built model has been trained to recognise 1000 different kinds of classes/objects (originally from http://data.dmlc.ml/mxnet/models/imagenet/synset.txt). These include goldfish, great white shark, tiger shark, sports car, etc.

Visit the github repository for further examples and code: https://github.com/mlhubber/objects

Quick Start Command Line Examples

ml demo objects
ml gui objects
ml identify objects https://g3n1u5.com/mlhub/ryleybench.png
ml identify objects https://g3n1u5.com/mlhub/slide.png
ml identify objects https://g3n1u5.com/mlhub/parkedcars.png
ml identify objects https://g3n1u5.com/mlhub/pond.png

Usage

$ pip3 install mlhub
$ ml configure
$ ml install   objects
$ ml configure objects
$ ml readme    objects
$ ml commands  objects
$ ml demo      objects
$ ml identify  objects

Examples

Further Examples

ml ocr azcv https://access.togaware.com/letter_tony_01.png
ml ocr azcv https://access.togaware.com/poem_tony.png
ml landmarks azcv https://access.togaware.com/hb1.png
ml landmarks azcv https://access.togaware.com/hb2.png
ml landmarks azcv https://access.togaware.com/soh1.png
ml landmarks azcv https://access.togaware.com/soh2.png