RanCh.Wong

首先看看比较简单的 tf.name_scope(‘scope_name’).tf.name_scope 主要结合 tf.Variable() 来使用，方便参数命名管理。也就是说，它的主要目的是为了更加方便地管理参数命名。 # 与 tf.Variable() 结合使用。简化了命名with tf.name_scope('conv1') as scope: weights1 = tf.Va...

这个BUG弄了整整两天，记录一下各种百度，各种换模型，搞得头昏脑胀，最后通过对比实验，监测到killed之前内存暴涨，怀疑是内存泄漏或者内存不够，原来的训练图片尺寸5472×3648,resize一下就可以正常训练了，resize代码如下import osfrom PIL import Image filename = os.listdir("/home/wxy/下载/VOCdevki...

这个BUG解决了整整一天，特此纪念原工程链接https://github.com/chenyilun95/tf-cpn/训练完毕后，执行python mptest.py -d 0-1 -m log/model_dump/snapshot_18.ckpt报错在这里说明一下，执行该命令前，已经完成lib.kernel/lib_nms下的compile.sh编译工作，编译就不多说了，首先手动删...

跑openpose过程中遇到的BUG原因在于get sample images函数下一堆路径不正确，将images文件夹复制到common.py所属的文件夹下即可

安装步骤git clone https://github.com/pdollar/coco.gitcd coco/PythonAPIpython setup.py build_ext --inplacepython setup.py build_ext instal安装之后运行demo里的脚本，报错No module named ‘pycocotools._mask’原因是工程...

训练openpose中途退出，第二次重新训练报错解决方案如下:打开终端依次输入如下内容，其中echo 3 > /proc/sys/vm/drop_caches 为释放内存 wxy@wxy:~$ sudo -s [sudo] wxy 的密码： root@wxy:~# sync root@wxy:~# echo 3 > /proc/sys/vm/drop_c...

with open('outfile.csv', 'r', encoding='gbk') as csvfile: reader = csv.reader(csvfile) j = 0 for i, rows in enumerate(reader): if i == j: row = rows ...

outfile.to_csv('outfile.csv', index=False, encoding='gbk',float_format='%.3f')

import pandas as pddf1 = pd.read_csv('class_and_score.csv', encoding='gbk')df2 = pd.read_csv('hight.csv', encoding='gbk')df3 = pd.read_csv('width.csv', encoding='gbk')#outfile = pd.merge(df1, ...

整合后的代码如下import sysimport argparsefrom yolo import YOLO, detect_videofrom PIL import Imageimport osimport numpy as npimport six.moves.urllib as urllibimport tarfileimport tensorflow as tfimpo...

for image_path in TEST_IMAGE_PATHS: image = Image.open(image_path) # the array based representation of the image will be used later in order to prepare the # result image with boxes and labels o...

按这篇文章测试，https://blog.csdn.net/qq_29075459/article/details/78562581中间下了protoc3.9，报错object_detection/protos/*.proto: No such file or directory这是因为目前的protoc3.5以上版本有Bug,换成3.4就好了https://github.com/google...

测试中遇到的问题，直接上代码 import numpy as np import os import six.moves.urllib as urllib import sys import tarfile import tensorflow as tf import zipfile from collections import def...