Faster-RCNN_TF代码解读4：config.py

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

"""Fast R-CNN config system.

This file specifies default config options for Fast R-CNN. You should not
change values in this file. Instead, you should write a config file (in yaml)
and use cfg_from_file(yaml_file) to load it and override the default options.

Most tools in $ROOT/tools take a --cfg option to specify an override file.
    - See tools/{train,test}_net.py for example code that uses cfg_from_file()
    - See experiments/cfgs/*.yml for example YAML config override files
"""

import os
import os.path as osp
import numpy as np
from distutils import spawn
# `pip install easydict` if you don't have it
from easydict import EasyDict as edict
#easydict的应用：https://pypi.python.org/pypi/easydict/
#就是一个dict的子类，但是功能变的更加简洁，如添加元素不需要setdefault()，只需要'.'操作即可
__C = edict()
# Consumers can get config by:
#   from fast_rcnn_config import cfg
cfg = __C

#
# Training options
#

__C.TRAIN = edict()
#__C.NET_NAME = 'VGGnet'
# learning rate
__C.TRAIN.LEARNING_RATE = 0.001
__C.TRAIN.MOMENTUM = 0.9
__C.TRAIN.GAMMA = 0.1
__C.TRAIN.STEPSIZE = 50000
__C.TRAIN.DISPLAY = 10
__C.IS_MULTISCALE = False

# Scales to compute real features
#__C.TRAIN.SCALES_BASE = (0.25, 0.5, 1.0, 2.0, 3.0)
#__C.TRAIN.SCALES_BASE = (1.0,)

# parameters for ROI generating
#__C.TRAIN.SPATIAL_SCALE = 0.0625
#__C.TRAIN.KERNEL_SIZE = 5

# Aspect ratio to use during training
#__C.TRAIN.ASPECTS = (1, 0.75, 0.5, 0.25)
#__C.TRAIN.ASPECTS= (1,)


# Scales to use during training (can list multiple scales)
# Each scale is the pixel size of an image's shortest side
__C.TRAIN.SCALES = (600,)

# Max pixel size of the longest side of a scaled input image
__C.TRAIN.MAX_SIZE = 1000

# Images to use per minibatch
__C.TRAIN.IMS_PER_BATCH = 2

# Minibatch size (number of regions of interest [ROIs])
__C.TRAIN.BATCH_SIZE = 128

# Fraction of minibatch that is labeled foreground (i.e. class > 0)
__C.TRAIN.FG_FRACTION = 0.25

# Overlap threshold for a ROI to be considered foreground (if >= FG_THRESH)
__C.TRAIN.FG_THRESH = 0.5

# Overlap threshold for a ROI to be considered background (class = 0 if
# overlap in [LO, HI))
__C.TRAIN.BG_THRESH_HI = 0.5
__C.TRAIN.BG_THRESH_LO = 0.1

# Use horizontally-flipped images during training?
__C.TRAIN.USE_FLIPPED = True

# Train bounding-box regressors
__C.TRAIN.BBOX_REG = True

# Overlap required between a ROI and ground-truth box in order for that ROI to
# be used as a bounding-box regression training example
__C.TRAIN.BBOX_THRESH = 0.5

# Iterations between snapshots
__C.TRAIN.SNAPSHOT_ITERS = 5000

# solver.prototxt specifies the snapshot path prefix, this adds an optional
# infix to yield the path: <prefix>[_<infix>]_iters_XYZ.caffemodel
__C.TRAIN.SNAPSHOT_PREFIX = 'VGGnet_fast_rcnn'
__C.TRAIN.SNAPSHOT_INFIX = ''

# Use a prefetch thread in roi_data_layer.layer
# So far I haven't found this useful; likely more engineering work is required
__C.TRAIN.USE_PREFETCH = False

# Normalize the targets (subtract empirical mean, divide by empirical stddev)
__C.TRAIN.BBOX_NORMALIZE_TARGETS = True
# Deprecated (inside weights)
__C.TRAIN.BBOX_INSIDE_WEIGHTS = (1.0, 1.0, 1.0, 1.0)
# Normalize the targets using "precomputed" (or made up) means and stdevs
# (BBOX_NORMALIZE_TARGETS must also be True)
__C.TRAIN.BBOX_NORMALIZE_TARGETS_PRECOMPUTED = False
__C.TRAIN.BBOX_NORMALIZE_MEANS = (0.0, 0.0, 0.0, 0.0)
__C.TRAIN.BBOX_NORMALIZE_STDS = (0.1, 0.1, 0.2, 0.2)

# Train using these proposals
__C.TRAIN.PROPOSAL_METHOD = 'selective_search'

# Make minibatches from images that have similar aspect ratios (i.e. both
# tall and thin or both short and wide) in order to avoid wasting computation
# on zero-padding.
__C.TRAIN.ASPECT_GROUPING = True

# Use RPN to detect objects
__C.TRAIN.HAS_RPN = False
# IOU >= thresh: positive example
__C.TRAIN.RPN_POSITIVE_OVERLAP = 0.7
# IOU < thresh: negative example
__C.TRAIN.RPN_NEGATIVE_OVERLAP = 0.3
# If an anchor statisfied by positive and negative conditions set to negative
__C.TRAIN.RPN_CLOBBER_POSITIVES = False
# Max number of foreground examples
__C.TRAIN.RPN_FG_FRACTION = 0.5
# Total number of examples
__C.TRAIN.RPN_BATCHSIZE = 256
# NMS threshold used on RPN proposals
__C.TRAIN.RPN_NMS_THRESH = 0.7
# Number of top scoring boxes to keep before apply NMS to RPN proposals
__C.TRAIN.RPN_PRE_NMS_TOP_N = 12000
# Number of top scoring boxes to keep after applying NMS to RPN proposals
__C.TRAIN.RPN_POST_NMS_TOP_N = 2000
# Proposal height and width both need to be greater than RPN_MIN_SIZE (at orig image scale)
__C.TRAIN.RPN_MIN_SIZE = 16
# Deprecated (outside weights)
__C.TRAIN.RPN_BBOX_INSIDE_WEIGHTS = (1.0, 1.0, 1.0, 1.0)
# Give the positive RPN examples weight of p * 1 / {num positives}
# and give negatives a weight of (1 - p)
# Set to -1.0 to use uniform example weighting
__C.TRAIN.RPN_POSITIVE_WEIGHT = -1.0

# Enable timeline generation
__C.TRAIN.DEBUG_TIMELINE = False

#
# Testing options
#

__C.TEST = edict()

# Scales to use during testing (can list multiple scales)
# Each scale is the pixel size of an image's shortest side
__C.TEST.SCALES = (600,)

# Max pixel size of the longest side of a scaled input image
__C.TEST.MAX_SIZE = 1000

# Overlap threshold used for non-maximum suppression (suppress boxes with
# IoU >= this threshold)
__C.TEST.NMS = 0.3

# Experimental: treat the (K+1) units in the cls_score layer as linear
# predictors (trained, eg, with one-vs-rest SVMs).
__C.TEST.SVM = False

# Test using bounding-box regressors
__C.TEST.BBOX_REG = True

# Propose boxes
__C.TEST.HAS_RPN = True

# Test using these proposals
__C.TEST.PROPOSAL_METHOD = 'selective_search'

## NMS threshold used on RPN proposals
__C.TEST.RPN_NMS_THRESH = 0.7
## Number of top scoring boxes to keep before apply NMS to RPN proposals
__C.TEST.RPN_PRE_NMS_TOP_N = 6000
#__C.TEST.RPN_PRE_NMS_TOP_N = 12000
## Number of top scoring boxes to keep after applying NMS to RPN proposals
__C.TEST.RPN_POST_NMS_TOP_N = 300
#__C.TEST.RPN_POST_NMS_TOP_N = 2000
# Proposal height and width both need to be greater than RPN_MIN_SIZE (at orig image scale)
__C.TEST.RPN_MIN_SIZE = 16

# Enable timeline generation
__C.TEST.DEBUG_TIMELINE = False

#
# MISC
#

# The mapping from image coordinates to feature map coordinates might cause
# some boxes that are distinct in image space to become identical in feature
# coordinates. If DEDUP_BOXES > 0, then DEDUP_BOXES is used as the scale factor
# for identifying duplicate boxes.
# 1/16 is correct for {Alex,Caffe}Net, VGG_CNN_M_1024, and VGG16
__C.DEDUP_BOXES = 1./16.

# Pixel mean values (BGR order) as a (1, 1, 3) array
# We use the same pixel mean for all networks even though it's not exactly what
# they were trained with
__C.PIXEL_MEANS = np.array([[[102.9801, 115.9465, 122.7717]]])

# For reproducibility
__C.RNG_SEED = 3

# A small number that's used many times
__C.EPS = 1e-14

# Root directory of project
#该root_dir 操作方式：__file__为该config.py文件的路径，所有总路径为abs（__file__/../..）此时即为Fsater-ECNN_TF目录
__C.ROOT_DIR = osp.abspath(osp.join(osp.dirname(__file__), '..', '..'))

# Data directory
#osp.join为os.path.join，osp.join(‘home‘，’ubuntu‘，’lijing‘)返回’home/ubuntu/lijing‘
#osp.abspath（path）为将该路径转化为绝对路径
#os.path.split（path）将path分割成目录和文件名二元组返回
#os.path.dirname(path)返回文件之前的路径，即os.path.split(path)的第一个元素
#os.path.basename(path)返回path最后的文件名。如何path以／或\结尾，那么就会返回空值。即os.path.split(path)的第二个元素。
#os.path.commonprefix（path1,path2,path3..）给定的这几个路径找到重合部分路径并返回
#os.path.exists（path）查看该路径是否存在，返回bool值
#os.path.isabs(path)判断是否是绝对路径，返回bool
#os.path.isfile(path)如果path是一个存在的文件，返回True。否则返回False
#os.path.isdir(path) 如果path是一个存在的路径，返回True。否则返回False


#由__C.ROOT_DIR可知 Fsater-ECNN_TF/data
__C.DATA_DIR = osp.abspath(osp.join(__C.ROOT_DIR, 'data'))

# Model directory
#Fsater-ECNN_TF/models/pascal_voc
__C.MODELS_DIR = osp.abspath(osp.join(__C.ROOT_DIR, 'models', 'pascal_voc'))

# Name (or path to) the matlab executable
__C.MATLAB = 'matlab'

# Place outputs under an experiments directory
__C.EXP_DIR = 'default'


if spawn.find_executable("nvcc"):
    # Use GPU implementation of non-maximum suppression
    __C.USE_GPU_NMS = True

    # Default GPU device id
    __C.GPU_ID = 0
else:
    __C.USE_GPU_NMS = False


def get_output_dir(imdb, weights_filename):
    """Return the directory where experimental artifacts are placed.
    If the directory does not exist, it is created.

    A canonical path is built using the name from an imdb and a network
    (if not None).
    """
    #e.g. Fsater-RCNN_TF/output/default/voc_2007_train
    outdir = osp.abspath(osp.join(__C.ROOT_DIR, 'output', __C.EXP_DIR, imdb.name))
    #weights_filename给的是None
    if weights_filename is not None:
        outdir = osp.join(outdir, weights_filename)
    #如果该路径不存在，就创建这样的一个路径
    if not os.path.exists(outdir):
        os.makedirs(outdir)
    return outdir

def _merge_a_into_b(a, b):
    """Merge config dictionary a into config dictionary b, clobbering the
    options in b whenever they are also specified in a.
    """
    if type(a) is not edict:
        return

    for k, v in a.iteritems():
        # a must specify keys that are in b
        if not b.has_key(k):
            raise KeyError('{} is not a valid config key'.format(k))

        # the types must match, too
        old_type = type(b[k])
        if old_type is not type(v):
            if isinstance(b[k], np.ndarray):
                v = np.array(v, dtype=b[k].dtype)
            else:
                raise ValueError(('Type mismatch ({} vs. {}) '
                                'for config key: {}').format(type(b[k]),
                                                            type(v), k))

        # recursively merge dicts
        if type(v) is edict:
            try:
                _merge_a_into_b(a[k], b[k])
            except:
                print('Error under config key: {}'.format(k))
                raise
        else:
            b[k] = v

def cfg_from_file(filename):
    """Load a config file and merge it into the default options."""
    #加载一个文件就是先open再用yaml或pickle去打开
    #edict为easydict，为dict的一个实例，就是为了简便创建一个字典
    import yaml
    with open(filename, 'r') as f:
        yaml_cfg = edict(yaml.load(f))

    _merge_a_into_b(yaml_cfg, __C)

def cfg_from_list(cfg_list):
    """Set config keys via list (e.g., from command line)."""
    from ast import literal_eval
    assert len(cfg_list) % 2 == 0
    for k, v in zip(cfg_list[0::2], cfg_list[1::2]):
        key_list = k.split('.')
        d = __C
        for subkey in key_list[:-1]:
            assert d.has_key(subkey)
            d = d[subkey]
        subkey = key_list[-1]
        assert d.has_key(subkey)
        try:
            value = literal_eval(v)
        except:
            # handle the case when v is a string literal
            value = v
        assert type(value) == type(d[subkey]), \
            'type {} does not match original type {}'.format(
            type(value), type(d[subkey]))
        d[subkey] = value