classify.py

#-*- coding: utf-8 -*-
"""
All modification made by Cambricon Corporation: © 2018 Cambricon Corporation
All rights reserved.
All other contributions:
Copyright (c) 2014--2018, the respective contributors
All rights reserved.
For the list of contributors go to https://github.com/BVLC/caffe/blob/master/CONTRIBUTORS.md
Redistribution and use in source and binary forms, with or without
modification, are permitted provided that the following conditions are met:
    * Redistributions of source code must retain the above copyright notice,
      this list of conditions and the following disclaimer.
    * Redistributions in binary form must reproduce the above copyright
      notice, this list of conditions and the following disclaimer in the
      documentation and/or other materials provided with the distribution.
    * Neither the name of Intel Corporation nor the names of its contributors
      may be used to endorse or promote products derived from this software
      without specific prior written permission.
THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS"
AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE LIABLE
FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR
SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER
CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY,
OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE
OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
"""

#!/usr/bin/env python
"""
classify.py is an out-of-the-box image classifer callable from the command line.

By default it configures and runs the Caffe reference ImageNet model.
"""
import numpy as np
import os
import sys
import argparse
import glob
import time

import caffe
MLUInited = 0

def main(argv):
    pycaffe_dir = os.path.dirname(__file__)

    parser = argparse.ArgumentParser()
    # Required arguments: input and output files.
    parser.add_argument(
        "input_file",
        help="Input image, directory, or npy."
    )
    parser.add_argument(
        "output_file",
        help="Output npy filename."
    )
    # Optional arguments.
    parser.add_argument(
        "--model_def",
        default=os.path.join(pycaffe_dir,
                "../models/bvlc_reference_caffenet/deploy.prototxt"),
        help="Model definition file."
    )
    parser.add_argument(
        "--pretrained_model",
        default=os.path.join(pycaffe_dir,
                "../models/bvlc_reference_caffenet/bvlc_reference_caffenet.caffemodel"),
        help="Trained model weights file."
    )
    parser.add_argument(
        "--gpu",
        action='store_true',
        help="Switch for gpu computation."
    )
    parser.add_argument(
        "--mlu",
        action='store_true',
        help="Switch for MLU computation."
    )
    parser.add_argument(
        "--mfus",
        action='store_true',
        help="Switch for MFUS (MLU Fusion) computation."
    )
    parser.add_argument(
        "--center_only",
        action='store_true',
        help="Switch for prediction from center crop alone instead of " +
             "averaging predictions across crops (default)."
    )
    parser.add_argument(
        "--images_dim",
        default='256,256',
        help="Canonical 'height,width' dimensions of input images."
    )
    parser.add_argument(
        "--mean_file",
        default=os.path.join(pycaffe_dir,
                             'caffe/imagenet/ilsvrc_2012_mean.npy'),
        help="Data set image mean of [Channels x Height x Width] dimensions " +
             "(numpy array). Set to '' for no mean subtraction."
    )
    parser.add_argument(
        "--input_scale",
        type=float,
        help="Multiply input features by this scale to finish preprocessing."
    )
    parser.add_argument(
        "--raw_scale",
        type=float,
        default=255.0,
        help="Multiply raw input by this scale before preprocessing."
    )
    parser.add_argument(
        "--channel_swap",
        default='2,1,0',
        help="Order to permute input channels. The default converts " +
             "RGB -> BGR since BGR is the Caffe default by way of OpenCV."
    )
    parser.add_argument(
        "--ext",
        default='jpg',
        help="Image file extension to take as input when a directory " +
             "is given as the input file."
    )
    args = parser.parse_args()

    image_dims = [int(s) for s in args.images_dim.split(',')]

    mean, channel_swap = None, None
    if args.mean_file:
        mean = np.load(args.mean_file)
    if args.channel_swap:
        channel_swap = [int(s) for s in args.channel_swap.split(',')]

    if args.gpu:
        caffe.set_mode_gpu()
        print("GPU mode")
    elif args.mlu:
        caffe.set_mode_mlu()
        MLUInited = 1
        print("MLU mode")
    elif args.mfus:
        caffe.set_mode_mfus()
        MLUInited = 1
        print("MFUS mode")
    else:
        caffe.set_mode_cpu()
        print("CPU mode")

    caffe.set_rt_core("MLU100");  # FIXME change to your core version

    # Make classifier.
    classifier = caffe.Classifier(args.model_def, args.pretrained_model,
            image_dims=image_dims, mean=mean,
            input_scale=args.input_scale, raw_scale=args.raw_scale,
            channel_swap=channel_swap)

    # Load numpy array (.npy), directory glob (*.jpg), or image file.
    args.input_file = os.path.expanduser(args.input_file)
    if args.input_file.endswith('npy'):
        print("Loading file: %s" % args.input_file)
        inputs = np.load(args.input_file)
    elif os.path.isdir(args.input_file):
        print("Loading folder: %s" % args.input_file)
        inputs =[caffe.io.load_image(im_f)
                 for im_f in glob.glob(args.input_file + '/*.' + args.ext)]
    else:
        print("Loading file: %s" % args.input_file)
        inputs = [caffe.io.load_image(args.input_file)]

    print("Classifying %d inputs." % len(inputs))

    # Classify.
    start = time.time()
    predictions = classifier.predict(inputs, not args.center_only)
    print("Done in %.2f s." % (time.time() - start))

    # Save
    print("Saving results into %s" % args.output_file)
    np.save(args.output_file, predictions)


if __name__ == '__main__':
        main(sys.argv)
        # The call to exit mlu lib should happen after all Caffe objects have been
        # destructed. In this case, they are in the main function.
        if MLUInited == 1 :
            caffe.exit_mlu_lib()