Image Classification using Inception V4

In this example, we convert Inception V4 trained on Tensorflow to SINGA for image classification. Tested on SINGA version 1.1.1 with parameters pretrained by tensorflow.

Instructions

Please cd to singa/examples/imagenet/inception/ for the following commands

Download

Download the parameter checkpoint file

$ wget https://s3-ap-southeast-1.amazonaws.com/dlfile/inception_v4.tar.gz
$ tar xvf inception_v4.tar.gz

Download synset_word.txt file.

Run the program

# use cpu
$ python serve.py -C &
# use gpu
$ python serve.py &

Submit images for classification

$ curl -i -F image=@image1.jpg http://localhost:9999/api
$ curl -i -F image=@image2.jpg http://localhost:9999/api
$ curl -i -F image=@image3.jpg http://localhost:9999/api

image1.jpg, image2.jpg and image3.jpg should be downloaded before executing the above commands.

Details

We first extract the parameter values from Tensorflow's checkpoint file into a pickle version. After downloading and decompressing the checkpoint file, run the following script

$ python convert.py --file_name=inception_v4.ckpt