search

PaddlePaddle / models

Officially maintained, supported by PaddlePaddle, including CV, NLP, Speech, Rec, TS, big models and so on.
Apache License 2.0
6.89k stars 2.91k forks source link

deeplabv3 #1607

Open geng007 opened 5 years ago

geng007 commented 5 years ago

default default

read.py中 if six.PY2: import commands label_files = commands.getoutput( "find %s -type f | grep labelTrainIds | sort" % label_dirname).splitlines() print(label_files) else: import subprocess label_files = subprocess.getstatusoutput( "find %s -type f | grep labelTrainIds | sort" % label_dirname)[-1].splitlines() print(label_files)

label_files读取到的是空列表[],dataset是cityscape

busyboxs commented 5 years ago

你对数据做处理了么？gt文件夹下面是否有带有labelTrainIds的文件，比如

CityScape/gtFine/train/aachen/aachen_000000_000019_gtFine_labelTrainIds.png