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.
Please
cd
tosinga/examples/imagenet/inception/
for the following commands
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.
# use cpu $ python serve.py -C & # use gpu $ python serve.py &
$ 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.
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