Win10调试ssd_tensorflow的目标检测

1、环境：win10+tensorflow-gpu==1.14.0

2、下载代码：到https://github.com/balancap/SSD-Tensorflow到本地

3、解压代码，并将checkpoints下的ssd_300_vgg.ckpt.zip进行解压在checkpoints目录下。否则后果不堪设想

4、如果你的电脑装有jupyter notebook.则将此SSD-Tensorflow文件复制在jupyter文件目录下，然后启动jupyter notebook。

打开notebooks下的ssd_notebook.ipynb文件，运行每个cell。

也可以将此ipynb下的所有代码复制在SSD_Tensorflow目录新建的ssd_python.py中，运行

也可以直接搜网上教程，新建py文件，复制代码，然后运行。

这个附上我复制的代码：（切记修改路径ckpt_file）

# coding: utf-8
# In[1]:import os
import math
import randomimport numpy as np
import tensorflow as tf
import cv2slim = tf.contrib.slim# In[2]:
import matplotlib.pyplot as plt
import matplotlib.image as mpimg# In[3]:import syssys.path.append('./')# In[4]:from nets import ssd_vgg_300, ssd_common, np_methods
from preprocessing import ssd_vgg_preprocessing
from notebooks import visualization# In[5]:# TensorFlow session: grow memory when needed. TF, DO NOT USE ALL MY GPU MEMORY!!!
gpu_options = tf.GPUOptions(allow_growth=True)
config = tf.ConfigProto(log_device_placement=False, gpu_options=gpu_options)
isess = tf.InteractiveSession(config=config)# ## SSD 300 Model
#
# The SSD 300 network takes 300x300 image inputs. In order to feed any image, the latter is resize to this input shape (i.e.`Resize.WARP_RESIZE`). Note that even though it may change the ratio width / height, the SSD model performs well on resized images (and it is the default behaviour in the original Caffe implementation).
#
# SSD anchors correspond to the default bounding boxes encoded in the network. The SSD net output provides offset on the coordinates and dimensions of these anchors.# In[6]:# Input placeholder.
net_shape = (300, 300)
data_format = 'NHWC'
img_input = tf.placeholder(tf.uint8, shape=(None, None, 3))
# Evaluation pre-processing: resize to SSD net shape.
image_pre, labels_pre, bboxes_pre, bbox_img = ssd_vgg_preprocessing.preprocess_for_eval(img_input, None, None, net_shape, data_format, resize=ssd_vgg_preprocessing.Resize.WARP_RESIZE)
image_4d = tf.expand_dims(image_pre, 0)# Define the SSD model.
reuse = True if 'ssd_net' in locals() else None
ssd_net = ssd_vgg_300.SSDNet()
with slim.arg_scope(ssd_net.arg_scope(data_format=data_format)):predictions, localisations, _, _ = ssd_net.net(image_4d, is_training=False, reuse=reuse)# Restore SSD model.
ckpt_filename = 'E:\gitcode\ssd\chde222-SSD-Tensorflow-master\SSD-Tensorflow\checkpoints/ssd_300_vgg.ckpt'
# ckpt_filename = '../checkpoints/VGG_VOC0712_SSD_300x300_ft_iter_120000.ckpt'
isess.run(tf.global_variables_initializer())
saver = tf.train.Saver()
saver.restore(isess, ckpt_filename)# SSD default anchor boxes.
ssd_anchors = ssd_net.anchors(net_shape)# ## Post-processing pipeline
#
# The SSD outputs need to be post-processed to provide proper detections. Namely, we follow these common steps:
#
# * Select boxes above a classification threshold;
# * Clip boxes to the image shape;
# * Apply the Non-Maximum-Selection algorithm: fuse together boxes whose Jaccard score > threshold;
# * If necessary, resize bounding boxes to original image shape.# In[7]:# Main image processing routine.
def process_image(img, select_threshold=0.5, nms_threshold=.45, net_shape=(300, 300)):# Run SSD network.rimg, rpredictions, rlocalisations, rbbox_img = isess.run([image_4d, predictions, localisations, bbox_img],feed_dict={img_input: img})# Get classes and bboxes from the net outputs.rclasses, rscores, rbboxes = np_methods.ssd_bboxes_select(rpredictions, rlocalisations, ssd_anchors,select_threshold=select_threshold, img_shape=net_shape, num_classes=21, decode=True)rbboxes = np_methods.bboxes_clip(rbbox_img, rbboxes)rclasses, rscores, rbboxes = np_methods.bboxes_sort(rclasses, rscores, rbboxes, top_k=400)rclasses, rscores, rbboxes = np_methods.bboxes_nms(rclasses, rscores, rbboxes, nms_threshold=nms_threshold)# Resize bboxes to original image shape. Note: useless for Resize.WARP!rbboxes = np_methods.bboxes_resize(rbbox_img, rbboxes)return rclasses, rscores, rbboxes# In[21]:# Test on some demo image and visualize output.
path = 'E:/gitcode/ssd/chde222-SSD-Tensorflow-master/SSD-Tensorflow/demo/'
image_names = sorted(os.listdir(path))img = mpimg.imread(path + image_names[-1])
rclasses, rscores, rbboxes = process_image(img)# visualization.bboxes_draw_on_img(img, rclasses, rscores, rbboxes, visualization.colors_plasma)
visualization.plt_bboxes(img, rclasses, rscores, rbboxes)

运行结果：

参考自https://blog.csdn.net/hezuo1181/article/details/91380182

Win10调试ssd_tensorflow的目标检测相关推荐

win10,vs2015深度学习目标检测YOLOV5+deepsort C++多目标跟踪代码实现，源码注释，拿来即用。
打死不用CSDN,整改的太恶心了,发什么都审核不过,各种图片和链接不让发.人如果没有立场那还是人吗?不用CSDN并且博客园就很好! DeepSort纯C++ Yolov5[s,l,m系列],详细讲解- ...
Win10下 Swin Transformer目标检测环境配置流程
Win10下 Swin-Transformer目标检测环境:对于第一次配置mmdetection的同学可能有所帮助. 1.版本环境介绍 Window 10 Visual Studio 2017 pyt ...
tensorflow 目标检测API及jupyter notebook 虚拟环境配置
环境 tensorflow == 2.8.0 win10 or linux 概要目标检测项目的主要步骤如下: 搭建虚拟环境采集图像并打标训练预测模型的保存和转换调优项目部署 1. 搭建虚 ...
跑yolo3模型出的效果图_【目标检测实战】Darknet入门—yolov3模型训练(Win10下的安装、编译、实现)...
效果图简介 Yolo,是实时物体检测的算法系统,基于Darknet-一个用C和CUDA编写的开源神经网络框架.它快速,易于安装,并支持CPU和GPU计算,也是yolo的底层.本文主要介绍在win10 ...
python实现yolo目标检测_Yolov5—实现目标检测（win10）
Yolov5-实现目标检测(win10) 该方法可以在win10上实现Yolov5的目标检测,配置前需要安装Anaconda3 一.环境配置源码下载地址:https://github.com/ult ...
【目标检测实验系列】使用yolov3 spp训练西工大遥感数据集NWPU VHR-10（包括如何将NWPU VHR-10转为VOC格式和yolov3 spp实验调试的详细步骤，且附上训练完的权重文件）
目录 1. 文章主要内容 2. 西工大数据集转换为VOC格式数据集 2.1 VOC数据集结构 2.2 西工大数据集 2.3 转换格式 2.3.1 构建与VOC类似的数据集文件结构(文件夹名可以自定义) ...
Yolov5—实现目标检测（win10）
Yolov5-实现目标检测(win10) 该方法可以在win10上实现Yolov5的目标检测,配置前需要安装Anaconda3 一.环境配置源码下载地址:https://github.com/ult ...
SSD目标检测:tensorflow 版本调试以及出现错误的解决方法
这里分享一下我在进行复现目标检测算法 SSD-Tensorflow 版本的调试经验. 首先贴上论文链接:SSD: Single Shot MultiBoxDetector Tensorflow 版本的 ...
WIN10+YOLOv4 环境搭建并进行YOLOv4目标检测
我的当前软件环境:WIN10,CUDA10.2,cuDNN7.6.5,python3.7,VS2019,OpenCV3.4.0 硬件环境:Rtx2060,12G显存: 1.1 下载安装NVIDIA显 ...

Win10调试ssd_tensorflow的目标检测

Win10调试ssd_tensorflow的目标检测相关推荐

最新文章

热门文章