This model makes use of Google's Machine learning api named Keras to assemble and train the model. Keras uses a Google's ML frameworks called Tensorflow as the backend for this model.
The model is trained on the Image-Net dataset,
and is served through a Flask server.
The model can be tested by sending an HTTP POST request to "localhost:5000/predict" to make predictions.
$ pip install flask gevent requests pillow
python Sense.py
curl -X POST -F [email protected] 'http://localhost:5000/predict'
Response
{"predictions":[{"label":"beagle","probability":0.9901767373085022},{"label":"Walker_hound","probability":0.0022487046662718058},{"label":"Brittany_spaniel","probability":0.0011901347897946835},{"label":"pot","probability":0.0011802910594269633},{"label":"Cardigan","probability":0.0006831124192103744}],"success":true}
http://localhost:5000/predict
Post a form file named "image" to localhost:5000/predict
