median frequency balancing的計算
圖片分割經常會遇到class unbalance的情況，如果你的target是要求每個類別的accuracy 都很高那么在訓練的時候做class balancing 很重要，如果你的target要求只要求圖片總體的pixel accuracy好，那么class balancing 此時就不是很重要，因為占比小的class, accuray 雖然小，但是對總體的Pixel accuracy影響也較小。
那么看下本文中的meidan frequency balancing是如何計算的：
對于一個多類別圖片數據庫，每個類別都會有一個class frequency, 該類別像素數目除以數據庫總像素數目, 求出所有class frequency 的median 值，除以該類別對應的frequency 得到weight：

weighti=median(weights)/weightiweighti=median(weights)/weighti

webdemo權重
作者訓練的webdemo和他給出的模型文件的類別數目和label 是對不上號的，因此可以使用webdemo跑測試，但是最好不要在上面finetune, 直接在VGG-16上面finetune 就行

rgb label 轉換為 gray label

#!/usr/bin/env python

import os

import numpy as np

from itertools import izip

from argparse import ArgumentParser

from collections import OrderedDict

from skimage.io import ImageCollection, imsave

from skimage.transform import resize

camvid_colors = OrderedDict([

("Animal", np.array([64, 128, 64], dtype=np.uint8)),

("Archway", np.array([192, 0, 128], dtype=np.uint8)),

("Bicyclist", np.array([0, 128, 192], dtype=np.uint8)),

("Bridge", np.array([0, 128, 64], dtype=np.uint8)),

("Building", np.array([128, 0, 0], dtype=np.uint8)),

("Car", np.array([64, 0, 128], dtype=np.uint8)),

("CartLuggagePram", np.array([64, 0, 192], dtype=np.uint8)),

("Child", np.array([192, 128, 64], dtype=np.uint8)),

("Column_Pole", np.array([192, 192, 128], dtype=np.uint8)),

("Fence", np.array([64, 64, 128], dtype=np.uint8)),

("LaneMkgsDriv", np.array([128, 0, 192], dtype=np.uint8)),

("LaneMkgsNonDriv", np.array([192, 0, 64], dtype=np.uint8)),

("Misc_Text", np.array([128, 128, 64], dtype=np.uint8)),

("MotorcycleScooter", np.array([192, 0, 192], dtype=np.uint8)),

("OtherMoving", np.array([128, 64, 64], dtype=np.uint8)),

("ParkingBlock", np.array([64, 192, 128], dtype=np.uint8)),

("Pedestrian", np.array([64, 64, 0], dtype=np.uint8)),

("Road", np.array([128, 64, 128], dtype=np.uint8)),

("RoadShoulder", np.array([128, 128, 192], dtype=np.uint8)),

("Sidewalk", np.array([0, 0, 192], dtype=np.uint8)),

("SignSymbol", np.array([192, 128, 128], dtype=np.uint8)),

("Sky", np.array([128, 128, 128], dtype=np.uint8)),

("SUVPickupTruck", np.array([64, 128, 192], dtype=np.uint8)),

("TrafficCone", np.array([0, 0, 64], dtype=np.uint8)),

("TrafficLight", np.array([0, 64, 64], dtype=np.uint8)),

("Train", np.array([192, 64, 128], dtype=np.uint8)),

("Tree", np.array([128, 128, 0], dtype=np.uint8)),

("Truck_Bus", np.array([192, 128, 192], dtype=np.uint8)),

("Tunnel", np.array([64, 0, 64], dtype=np.uint8)),

("VegetationMisc", np.array([192, 192, 0], dtype=np.uint8)),

("Wall", np.array([64, 192, 0], dtype=np.uint8)),

("Void", np.array([0, 0, 0], dtype=np.uint8))

])

def convert_label_to_grayscale(im):

out = (np.ones(im.shape[:2]) * 255).astype(np.uint8)

for gray_val, (label, rgb) in enumerate(camvid_colors.items()):

match_pxls = np.where((im == np.asarray(rgb)).sum(-1) == 3)

out[match_pxls] = gray_val

assert (out != 255).all(), "rounding errors or missing classes in camvid_colors"

return out.astype(np.uint8)

def make_parser():

parser = ArgumentParser()

parser.add_argument(

'label_dir',

help="Directory containing all RGB camvid label images as PNGs"

)

parser.add_argument(

'out_dir',

help="""Directory to save grayscale label images.

Output images have same basename as inputs so be careful not to

overwrite original RGB labels""")

return parser

if __name__ == '__main__':

parser = make_parser()

args = parser.parse_args()

labs = ImageCollection(os.path.join(args.label_dir, "*"))

os.makedirs(args.out_dir)

for i, (inpath, im) in enumerate(izip(labs.files, labs)):

print(i + 1, "of", len(labs))

# resize to caffe-segnet input size and preserve label values

resized_im = (resize(im, (360, 480), order=0) * 255).astype(np.uint8)

out = convert_label_to_grayscale(resized_im)

outpath = os.path.join(args.out_dir, os.path.basename(inpath))

imsave(outpath, out)