目标检测SSD+Tensorflow 训练自己的数据集

1.代码地址：https://github.com/balancap/SSD-Tensorflow，下载该代码到本地

2.解压ssd_300_vgg.ckpt.zip 到checkpoint文件夹下

3.测试一下看看，在notebooks中创建demo_test.py,其实就是复制ssd_notebook.ipynb中的代码，该py文件是完成对于单张图片的测试，对Jupyter不熟，就自己改了，感觉这样要方便一些。

 

 

import os
import math
import random
 
import numpy as np
import tensorflow as tf
import cv2
 
slim = tf.contrib.slim
import matplotlib.pyplot as plt
import matplotlib.image as mpimg
import sys
sys.path.append('../')
from nets import ssd_vgg_300, ssd_common, np_methods
from preprocessing import ssd_vgg_preprocessing
from notebooks import visualization
# 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)
# 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 = '../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)
 
 
# 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
# Test on some demo image and visualize output.
#测试的文件夹
path = '../demo/'
image_names = sorted(os.listdir(path))
#文件夹中的第几张图，-1代表最后一张
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)

 

 

4.将自己的数据集做成VOC2007格式放在该工程下面

5. 修改datasets文件夹中pascalvoc_common.py文件，将训练类修改别成自己的

 

#原始的
# VOC_LABELS = {
#     'none': (0, 'Background'),
#     'aeroplane': (1, 'Vehicle'),
#     'bicycle': (2, 'Vehicle'),
#     'bird': (3, 'Animal'),
#     'boat': (4, 'Vehicle'),
#     'bottle': (5, 'Indoor'),
#     'bus': (6, 'Vehicle'),
#     'car': (7, 'Vehicle'),
#     'cat': (8, 'Animal'),
#     'chair': (9, 'Indoor'),
#     'cow': (10, 'Animal'),
#     'diningtable': (11, 'Indoor'),
#     'dog': (12, 'Animal'),
#     'horse': (13, 'Animal'),
#     'motorbike': (14, 'Vehicle'),
#     'person': (15, 'Person'),
#     'pottedplant': (16, 'Indoor'),
#     'sheep': (17, 'Animal'),
#     'sofa': (18, 'Indoor'),
#     'train': (19, 'Vehicle'),
#     'tvmonitor': (20, 'Indoor'),
# }
#修改后的
VOC_LABELS = {
    'none': (0, 'Background'),
    'pantograph':(1,'Vehicle'),
}

6.  将图像数据转换为tfrecods格式，修改datasets文件夹中的pascalvoc_to_tfrecords.py文件，然后更改文件的83行读取方式为’rb‘，如果你的文件不是.jpg格式，也可以修改图片的类型。

此外， 修改67行，可以修改几张图片转为一个tfrecords

7.运行tf_convert_data.py文件，但是需要传给它一些参数：

linux	在SSD-Tensorflow-master文件夹下创建tf_conver_data.sh,文件写入内容如下： DATASET_DIR=./VOC2007/     #VOC数据保存的文件夹（VOC的目录格式未改变）   OUTPUT_DIR=./tfrecords_  #自己建立的保存tfrecords数据的文件夹        python ./tf_convert_data.py \        --dataset_name=pascalvoc \            --dataset_dir=${DATASET_DIR} \      --output_name=voc_2007_train \    --output_dir=${OUTPUT_DIR}
windows     +pychram	配置pycharm-->run-->Edit Configuration Script parameters中写入：--dataset_name=pascalvoc --dataset_dir=./VOC2007/ --output_name=voc_2007_train --output_dir=./tfrecords_ 运行tf_convert_data.py文件

生成tfrecords文件过程中你会看到	生成tfrecords文件完毕后你会看到

8.训练模型train_ssd_network.py文件中修改

 

train_ssd_network.py文件中网络参数配置，若需要改，在此文件中进行修改，如：

其他需要修改的地方

a.   nets/ssd_vgg_300.py  (因为使用此网络结构) ，修改87 和88行的类别
b. train_ssd_network.py,修改类别120行，GPU占用量，学习率，batch_size等
c eval_ssd_network.py 修改类别，66行
d. datasets/pascalvoc_2007.py 根据自己的训练数据修改整个文件	# (Images, Objects) statistics on every class. # TRAIN_STATISTICS = { # 'none': (0, 0), # 'aeroplane': (238, 306), # 'bicycle': (243, 353), # 'bird': (330, 486), # 'boat': (181, 290), # 'bottle': (244, 505), # 'bus': (186, 229), # 'car': (713, 1250), # 'cat': (337, 376), # 'chair': (445, 798), # 'cow': (141, 259), # 'diningtable': (200, 215), # 'dog': (421, 510), # 'horse': (287, 362), # 'motorbike': (245, 339), # 'person': (2008, 4690), # 'pottedplant': (245, 514), # 'sheep': (96, 257), # 'sofa': (229, 248), # 'train': (261, 297), # 'tvmonitor': (256, 324), # 'total': (5011, 12608), # } # TEST_STATISTICS = { # 'none': (0, 0), # 'aeroplane': (1, 1), # 'bicycle': (1, 1), # 'bird': (1, 1), # 'boat': (1, 1), # 'bottle': (1, 1), # 'bus': (1, 1), # 'car': (1, 1), # 'cat': (1, 1), # 'chair': (1, 1), # 'cow': (1, 1), # 'diningtable': (1, 1), # 'dog': (1, 1), # 'horse': (1, 1), # 'motorbike': (1, 1), # 'person': (1, 1), # 'pottedplant': (1, 1), # 'sheep': (1, 1), # 'sofa': (1, 1), # 'train': (1, 1), # 'tvmonitor': (1, 1), # 'total': (20, 20), # } # SPLITS_TO_SIZES = { # 'train': 5011, # 'test': 4952, # } # (Images, Objects) statistics on every class.   TRAIN_STATISTICS = { 'none': (0, 0), 'pantograph': (1000, 1000), } TEST_STATISTICS = { 'none': (0, 0), 'pantograph': (1000, 1000), } SPLITS_TO_SIZES = { 'train': 500, 'test': 500, }

9.通过加载预训练好的vgg16模型,训练网络

下载预训练好的vgg16模型，解压放入checkpoint文件中，如果找不到vgg_16.ckpt文件，可以在下面的链接中点击下载。

链接：https://pan.baidu.com/s/1diWbdJdjVbB3AWN99406nA 密码：ge3x

按照之前的方式，同样，如果你是linux用户，你可以新建一个.sh文件，文件里写入

 

DATASET_DIR=./tfrecords_/
TRAIN_DIR=./train_model/
CHECKPOINT_PATH=./checkpoints/vgg_16.ckpt
  
python3 ./train_ssd_network.py \  
    --train_dir=./train_model/ \      #训练生成模型的存放路径  
    --dataset_dir=./tfrecords_/ \  #数据存放路径  
    --dataset_name=pascalvoc_2007 \ #数据名的前缀  
    --dataset_split_name=train \  
    --model_name=ssd_300_vgg \      #加载的模型的名字  
    --checkpoint_path=./checkpoints/vgg_16.ckpt \  #所加载模型的路径  
    --checkpoint_model_scope=vgg_16 \   #所加载模型里面的作用域名  
    --checkpoint_exclude_scopes=ssd_300_vgg/conv6,ssd_300_vgg/conv7,ssd_300_vgg/block8,ssd_300_vgg/block9,ssd_300_vgg/block10,ssd_300_vgg/block11,ssd_300_vgg/block4_box,ssd_300_vgg/block7_box,ssd_300_vgg/block8_box,ssd_300_vgg/block9_box,ssd_300_vgg/block10_box,ssd_300_vgg/block11_box \  
    --trainable_scopes=ssd_300_vgg/conv6,ssd_300_vgg/conv7,ssd_300_vgg/block8,ssd_300_vgg/block9,ssd_300_vgg/block10,ssd_300_vgg/block11,ssd_300_vgg/block4_box,ssd_300_vgg/block7_box,ssd_300_vgg/block8_box,ssd_300_vgg/block9_box,ssd_300_vgg/block10_box,ssd_300_vgg/block11_box \  
    --save_summaries_secs=60 \  #每60s保存一下日志  
    --save_interval_secs=600 \  #每600s保存一下模型  
    --weight_decay=0.0005 \     #正则化的权值衰减的系数  
    --optimizer=adam \          #选取的最优化函数  
    --learning_rate=0.001 \     #学习率  
    --learning_rate_decay_factor=0.94 \ #学习率的衰减因子  
    --batch_size=24 \     
    --gpu_memory_fraction=0.9   #指定占用gpu内存的百分比 

 如果你是windows+pycharm中运行，除了在上述的run中Edit Configuration配置，你还可以打开Terminal，在这里运行代码，输入即可

python ./train_ssd_network.py  --train_dir=./train_model/  --dataset_dir=./tfrecords_/  --dataset_name=pascalvoc_2007 --dataset_split_name=train --model_name=ssd_300_vgg   --checkpoint_path=./checkpoints/   --checkpoint_model_scope=vgg_16 --checkpoint_exclude_scopes=ssd_300_vgg/conv6,ssd_300_vgg/conv7,ssd_300_vgg/block8,ssd_300_vgg/block9,ssd_300_vgg/block10,ssd_300_vgg/block11,ssd_300_vgg/block4_box,ssd_300_vgg/block7_box,ssd_300_vgg/block8_box,ssd_300_vgg/block9_box,ssd_300_vgg/block10_box,ssd_300_vgg/block11_box   --trainable_scopes=ssd_300_vgg/conv6,ssd_300_vgg/conv7,ssd_300_vgg/block8,ssd_300_vgg/block9,ssd_300_vgg/block10,ssd_300_vgg/block11,ssd_300_vgg/block4_box,ssd_300_vgg/block7_box,ssd_300_vgg/block8_box,ssd_300_vgg/block9_box,ssd_300_vgg/block10_box,ssd_300_vgg/block11_box --save_summaries_secs=60   --save_interval_secs=600 --weight_decay=0.0005   --optimizer=adam   --learning_rate=0.001 --learning_rate_decay_factor=0.94   --batch_size=24      --gpu_memory_fraction=0.9