In this example, we convert DenseNet on PyTorch to SINGA for image classification.
Please
cd
tosinga/examples/imagenet/densenet/
for the following commands
Download one parameter checkpoint file (see below) and the synset word file of ImageNet into this folder, e.g.,
$ wget https://s3-ap-southeast-1.amazonaws.com/dlfile/densenet/densenet-121.tar.gz $ wget https://s3-ap-southeast-1.amazonaws.com/dlfile/resnet/synset_words.txt $ tar xvf densenet-121.tar.gz
$ python serve.py -h
# use cpu $ python serve.py --use_cpu --parameter_file densenet-121.pickle --depth 121 & # use gpu $ python serve.py --parameter_file densenet-121.pickle --depth 121 &
The parameter files for the following model and depth configuration pairs are provided: 121, 169, 201, 161
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.
The parameter files were converted from the pytorch via the convert.py program.
Usage:
$ python convert.py -h