Keras pretrained models (currently only VGG16) + Transfer Learning for predicting classes in the Oxford 102 flower dataset
This bootstraps the training of deep convolutional neural networks with Keras to classify images in the Oxford 102 category flower dataset.
Train process is fully automated and best weights for model are saving
Overview
bootstrap.py
: to download the Oxford 102 dataset and prepare image filestrain.py
: starts training process end-to-endserver.py
: a small python server based on sockets and designed to keep a model in memory for fast recognition requestsclient.py
: a client that sends requests to server.py
Usage
Step 1: Bootstrap
python bootstrap.py
Step 2: Train
python train.py
predict.py
or server.py
+ client.py
Step 3: Get predictions using Using predict.py
:
python predict.py -p "/path/to/image"
Using server.py
+ client.py
:
- run server and wait till model is loaded. Do not break server, it should be run and listen for incoming connections
python server.py
- send requests using client
python client.py -p "/path/to/image"