在win10上配置成功KittiSeg后，随便从网上download了一张图片测试一下效果，结果发现不work
随意数据上的结果：
kitti数据上的结果：
估计是kitti数据集太小了，模型过拟合，所以泛化性能低
打算自己训练一个model,用百度road_seg的数据集。用的是seg_3的数据
对数据进行修改，把label变成2分类问题
import numpy as np
import cv2
#test for one image
#img = cv2.imread('Label/Record057/Camera 6/171206_042426425_Camera_6_bin.png')
#print(img.shape)
#img[np.where((img!=[49,49,49]).all(axis = 2))] = [255,0,0]
#img[np.where((img==[49,49,49]).all(axis = 2))] = [255,0,255]
#cv2.imwrite('a.png',img)
#image = scipy.misc.imresize(img,0.6)
#print(image.shape)
files = [line for line in open('all2.txt')]
file = files[1000:]
num = 0
for path in file:
path = path[:-1] #这里要去掉最后的/n，这也是一个字符，不然返回空
img = cv2.imread(path)
print(img.shape)
img[np.where((img!=[49,49,49]).all(axis = 2))] = [255,0,0]
img[np.where((img==[49,49,49]).all(axis = 2))] = [255,0,255]
cv2.imwrite(path,img)
print(num)
num=num+1
制作并划分train.txt val.txt
a.先制作all.txt
分别读取图片和label，分成两个txt(all1.txt all2.txt),再把两个txt合并。
import os
import glob as gb
#import cv2
all_file = 'all2.txt'
with open (all_file, 'w') as a:
#for root, dirs,files in os.walk('ColorImage'):
for root, dirs,files in os.walk('Label'):
if len(dirs) == 0:
for i in range(len(files)):
if files[i][-3:] =='png':
file_path = root+'/'+files[i]
a.writelines(file_path+'\n')
合并两个txt文件，此时发现图片30331，label30350,两者不一致，所以要对两个txt做比较，去除不匹配的。
#这种是按行来比较，同行之间才比较，所以不符合自己想要的
之前每行后面都加了/n换行，在这里，也算一个字符，所以要去掉
#with open('all.txt','w') as a:
# with open('all1.txt','r') as a1, open('all2.txt') as a2:
# for line1, line2 in zip(a1,a2):
# #print(line1[10:-5],line2[5:-9])
# if line1[10:-5]==line2[5:-9]:
# print('o')
# a.writelines(line1[:-1]+' '+line2[:-1]+'\n')
with open('all.txt','w') as a:
with open('all1.txt','r') as a1, open('all2.txt') as a2:
lines1 = [line for line in a1]
lines2 = [line for line in a2]
for line1 in lines1:
#print(line1+'a')
for line2 in lines2:
if line1[10:-5]==line2[5:-9]:
a.writelines(line1[:-1]+' '+line2[:-1]+'\n')
#print(line1[10:-5],line2[5:-9])
随机划分成训练集验证集 由于数据量太大，自己想要先验证一下算法，所以，就先用1000样本，900训练，100验证。
from random import shuffle
def make_val_split():
"""
Splits the Images in train and test.
Assumes a File all.txt in data_folder.
"""
all_file = "alls.txt"
train_file = "trains.txt"
test_file = "vals.txt"
test_num = 100
files = [line for line in open(all_file)]
shuffle(files)
train = files[:-test_num]
test = files[-test_num:]
#train_file = os.path.join(data_folder, train_file)
#test_file = os.path.join(data_folder, test_file)
with open(train_file, 'w') as file:
for label in train:
file.write(label)
with open(test_file, 'w') as file:
for label in test:
file.write(label)
def main():
make_val_split()
if __name__ == '__main__':
main()
运行train.py遇到的问题：
报错1
image_file, gt_image_file = file.split(" ")
ValueError: too many values to unpack (expected 2)
查看了一下自己的trains.txt 发现 ColorImage\Record008\Camera 5/171206_030617006_Camera_5.jpg Label\Record008\Camera 5/171206_030617006_Camera_5_bin.png 确实每行都有三个空格
所以需要对代码进行修改
对kitti_seg_input.py的114行进行修改，修改后如下
#image_file, gt_image_file = file.split(" ")
image_file1,image_file2,gt_image_file1,gt_image_file2 = file.split(" ")
image_file = image_file1+" "+image_file2
gt_image_file = gt_image_file1+" "+gt_image_file2
报错2：
ResourceExhaustedError (see above for traceback): OOM when allocating tensor with shape[1,64,2701,3367] and type float on /job:localhost/replica:0/task:0/device:GPU:0 by allocator GPU_0_bfc
[[Node: conv1_2/Conv2D = Conv2D[T=DT_FLOAT, data_format="NCHW", dilations=[1, 1, 1, 1], padding="SAME", strides=[1, 1, 1, 1], use_cudnn_on_gpu=true, _device="/job:localhost/replica:0/task:0/device:GPU:0"](conv1_1/Relu, conv1_2/filter/read)]]
Allocator (GPU_0_bfc) ran out of memory trying to allocate 2.19GiB. Current allocation summary follows.
根据https://github.com/tensorflow/models/issues/3393估计可能确实是batchsize的问题，但是，自己的batchsize已经是1了，gg 内存不够的话，要么resize图片，要么换简单一点的网络，
鉴于自己的图片较大，有(2710, 3384），所以先resize一下
根据https://docs.scipy.org/doc/scipy/reference/generated/scipy.misc.imresize.html 使用scipy.misc.imresize(img,0.8) 把图像缩小为原来的0.8，0.8还是跑不起来，所以改为0.6
img = scipy.misc.imread(image_file, mode='RGB')
image = scipy.misc.imresize(img,0.8)
# Please update Scipy, if mode='RGB' is not avaible
gt_img = scp.misc.imread(gt_image_file, mode='RGB')
gy_image = scipy.misc.imresize(gt_img,0.8)
报错3：
train中间evaluate的时候报错
hypes, sess, tv_graph['image_pl'], tv_graph['inf_out'])
File "D:\work\KittiSeg-hotfix-python3.5_support\hypes\../evals/kitti_eval.py", line 71, in evaluate
image_file, gt_file = datum.split(" ")
ValueError: too many values to unpack (expected 2)
对kitti_eval.py进行修改 ，和输入的类似 就ok了
至此，开始训练过程。
对昨天训练好的model在自己的数据上进行测试，结果发现mask全白，也就是说将所有的像素预测为road，排查原因。将验证集的图片输入亦如此，遂将训练集图片输入，还是如此。说明拟合的时候就出了问题，所以，应该是标注出了问题。
在验证集，训练集上的结果：
查看.json文件
自己指定的是
"road_color" : [255,0,255],
"background_color" : [255,0,0],
没有更改，和kitti的一样，但是联想到自己处理出来的数据是蓝色的，kitti的是红色的，肯定有哪里不对，
查看当时自己改数据的代码
是按照kitti的改的啊，分别用取色器查看了kitti和自己的标定，发现蓝色分量和红色分量的值是反的，kitti的是红色分量为255，自己的是蓝色分量255，查了一下，opencv读取图片是BGR，所以BR两个分量反了，将.json文件中background_color改为[0,0,255]
重新开始训练
以后训练前还是要细细检查，这种bug白白浪费了一天时间。
网友评论