faster-rcnn 之训练脚本解析：./tools/train_faster_rcnn_alt_opt.py

【说明】：欢迎加入：faster-rcnn 交流群 238138700，本文分析faster-rcnn 训练的python脚本；

【debug】：我是把__main__修改了下，放在一个自己定义的函数里面，然后调用debug一步步看执行效果的，读者不妨也这样做，可以清晰看到程序是如何运行的；

#!/usr/bin/env python

# --------------------------------------------------------
# Faster R-CNN
# Copyright (c) 2015 Microsoft
# Licensed under The MIT License [see LICENSE for details]
# Written by Ross Girshick
# --------------------------------------------------------

"""Train a Faster R-CNN network using alternating optimization.
This tool implements the alternating optimization algorithm described in our
NIPS 2015 paper ("Faster R-CNN: Towards Real-time Object Detection with Region
Proposal Networks." Shaoqing Ren, Kaiming He, Ross Girshick, Jian Sun.)
"""

import _init_paths
from fast_rcnn.train import get_training_roidb, train_net
from fast_rcnn.config import cfg, cfg_from_file, cfg_from_list, get_output_dir
from datasets.factory import get_imdb
from rpn.generate import imdb_proposals
import argparse
import pprint
import numpy as np
import sys, os
import multiprocessing as mp
import cPickle
import shutil

def parse_args():
    """
    Parse input arguments
    """
    parser = argparse.ArgumentParser(description='Train a Faster R-CNN network')
    parser.add_argument('--gpu', dest='gpu_id',
                        help='GPU device id to use [0]',
                        default=0, type=int)
    parser.add_argument('--net_name', dest='net_name',
                        help='network name (e.g., "ZF")',
                        default='ZF', type=str) #qyy
    parser.add_argument('--weights', dest='pretrained_model',
                        help='initialize with pretrained model weights',
                        default='./data/imagenet_models/ZF.v2.caffemodel', type=str) #qyy
    parser.add_argument('--cfg', dest='cfg_file',
                        help='optional config file',
                        default='./experiments/cfgs/faster_rcnn_alt_opt.yml', type=str)# qyy
    parser.add_argument('--imdb', dest='imdb_name',
                        help='dataset to train on',
                        default='voc_2007_trainval', type=str)
    parser.add_argument('--set', dest='set_cfgs',
                        help='set config keys', default=None,
                        nargs=argparse.REMAINDER)

    if len(sys.argv) == 1:
        parser.print_help()
        sys.exit(1)

    args = parser.parse_args()
    return args

def get_roidb(imdb_name, rpn_file=None):
    imdb = get_imdb(imdb_name)
    print 'Loaded dataset `{:s}` for training'.format(imdb.name)
    imdb.set_proposal_method(cfg.TRAIN.PROPOSAL_METHOD)
    print 'Set proposal method: {:s}'.format(cfg.TRAIN.PROPOSAL_METHOD)
    if rpn_file is not None:
        imdb.config['rpn_file'] = rpn_file
    roidb = get_training_roidb(imdb)
    return roidb, imdb

def get_solvers(net_name):
    # Faster R-CNN Alternating Optimization
    n = 'faster_rcnn_alt_opt'
    # Solver for each training stage
    solvers = [[net_name, n, 'stage1_rpn_solver60k80k.pt'],
               [net_name, n, 'stage1_fast_rcnn_solver30k40k.pt'],
               [net_name, n, 'stage2_rpn_solver60k80k.pt'],
               [net_name, n, 'stage2_fast_rcnn_solver30k40k.pt']]
    solvers = [os.path.join(cfg.MODELS_DIR, *s) for s in solvers]
    # Iterations for each training stage
    max_iters = [80000, 40000, 80000, 40000]
    # max_iters = [100, 100, 100, 100]
    # Test prototxt for the RPN
    rpn_test_prototxt = os.path.join(
        cfg.MODELS_DIR, net_name, n, 'rpn_test.pt')
    return solvers, max_iters, rpn_test_prototxt

# ------------------------------------------------------------------------------
# Pycaffe doesn't reliably free GPU memory when instantiated nets are discarded
# (e.g. "del net" in Python code). To work around this issue, each training
# stage is executed in a separate process using multiprocessing.Process.
# ------------------------------------------------------------------------------

def _init_caffe(cfg):
    """Initialize pycaffe in a training process.
    """

    import caffe
    # fix the random seeds (numpy and caff