使用 Neuron SDK 编译 TensorFlow OpenPose 模型时如何提升机器学习任务的性能

source activate aws_neuron_tensorflow_p36
pip install neuron-cc --upgrade --extra-index-url=https://pip.repos.neuron.amazonaws.com
git clone https://github.com/aws/aws-neuron-sdk.git /tmp/aws-neuron-sdk && cp /tmp/aws-neuron-sdk/src/examples/tensorflow/<name_of_the_new_folder>/* . && rm -rf /tmp/aws-neuron-sdk/
pip install -r requirements-compile.txt

wget -c --tries=2 $( wget -q -O - http://www.mediafire.com/file/qlzzr20mpocnpa3/graph_opt.pb | grep -o 'http*://download[^"]*' | tail -n 1 ) -O graph_opt.pb

python convert_graph_opt.py graph_opt.pb graph_opt_neuron_656x368.pb

2020-07-15 21:44:43.008627: I bazel-out/k8-opt/bin/tensorflow/neuron/convert/segment.cc:460] There are 11 ops of 7 different types in the graph that are not compiled by neuron-cc: Const, NoOp, Placeholder, RealDiv, Sub, Cast, Transpose, (For more information see https://github.com/aws/aws-neuron-sdk/blob/master/release-notes/neuron-cc-ops/neuron-cc-ops-tensorflow.md).
INFO:tensorflow:fusing subgraph neuron_op_ed41d2deb8c54255 with neuron-cc
INFO:tensorflow:Number of operations in TensorFlow session: 474
INFO:tensorflow:Number of operations after tf.neuron optimizations: 474
INFO:tensorflow:Number of operations placed on Neuron runtime: 465

aws s3 mb s3://<MY_BUCKET_NAME>
aws s3 cp graph_opt_neuron_656x368.pb s3://<MY_BUCKET_NAME>/graph_model.pb

conda activate aws_neuron_tensorflow_p36
git clone https://github.com/ildoonet/tf-pose-estimation.git
cd tf-pose-estimation

pip install opencv-python 
pip install -r requirements.txt

import argparse
import logging
import sys
import time

from tf_pose import common
import cv2
import numpy as np
from tf_pose.estimator import TfPoseEstimator
from tf_pose.networks import get_graph_path, model_wh

logger = logging.getLogger('TfPoseEstimatorRun')
logger.handlers.clear()
logger.setLevel(logging.DEBUG)
ch = logging.StreamHandler()
ch.setLevel(logging.DEBUG)
formatter = logging.Formatter('[%(asctime)s] [%(name)s] [%(levelname)s] %(message)s')
ch.setFormatter(formatter)
logger.addHandler(ch)

def main(argString='--image ./images/contortion1.jpg --model cmu', repeats=10):
    parser = argparse.ArgumentParser(description='tf-pose-estimation run')
    parser.add_argument('--image', type=str, default='./images/apink2.jpg')
    parser.add_argument('--model', type=str, default='cmu',
                        help='cmu / mobilenet_thin / mobilenet_v2_large / mobilenet_v2_small')
    parser.add_argument('--resize', type=str, default='0x0',
                        help='if provided, resize images before they are processed. '
                             'default=0x0, Recommends : 432x368 or 656x368 or 1312x736 ')
    parser.add_argument('--resize-out-ratio', type=float, default=2.0,
                        help='if provided, resize heatmaps before they are post-processed. default=1.0')

    args = parser.parse_args(argString.split())

    w, h = model_wh(args.resize)
    if w == 0 or h == 0:
        e = TfPoseEstimator(get_graph_path(args.model), target_size=(432, 368))
    else:
        e = TfPoseEstimator(get_graph_path(args.model), target_size=(w, h))

    # estimate human poses from a single image !
    image = common.read_imgfile(args.image, None, None)
    if image is None:
        logger.error('Image can not be read, path=%s' % args.image)
        sys.exit(-1)

    t = time.time()
    for _ in range(repeats):
        humans = e.inference(image, resize_to_default=(w > 0 and h > 0), upsample_size=args.resize_out_ratio)
    elapsed = time.time() - t

    logger.info('%d times inference on image: %s at %.4f seconds/image.' % (repeats, args.image, elapsed/repeats))

    image = TfPoseEstimator.draw_humans(image, humans, imgcopy=False)
    return image, e

def plotter(image):
    try:
        import matplotlib.pyplot as plt

        fig = plt.figure(figsize=(12,12))
        a = fig.add_subplot(1, 1, 1)
        a.set_title('Result')
        plt.imshow(cv2.cvtColor(image, cv2.COLOR_BGR2RGB))
        
    except Exception as e:
        logger.warning('matplitlib error, %s' % e)
        cv2.imshow('result', image)
        cv2.waitKey()

img, e = main('--model cmu --resize 656x368 --image=./images/ski.jpg --resize-out-ratio 2.0')
plotter(img)

‘[TfPoseEstimatorRun] [INFO] 10 times inference on image: ./images/ski.jpg at 1.5624 seconds/image.’

‘[TfPoseEstimatorRun] [INFO] 10 times inference on image: ./images/ski.jpg at 0.1708 seconds/image’