Add files via upload

Author: bubbliiiing

LICENSE

@@ -1,6 +1,6 @@
 MIT License
 
-Copyright (c) 2020 Bubbliiiing
+Copyright (c) 2020 JiaQi Xu
 
 Permission is hereby granted, free of charge, to any person obtaining a copy
 of this software and associated documentation files (the "Software"), to deal

README.md

@@ -1,2 +1,41 @@
-# faster-rcnn-tf2
-这是一个faster-rcnn的tensorflow2实现的库，可以利用voc数据集格式的数据进行训练。
+## Faster-Rcnn：Two-Stage目标检测模型在Keras当中的实现
+---
+
+### 目录
+1. [所需环境 Environment](#所需环境)
+2. [文件下载 Download](#文件下载)
+3. [训练步骤 How2train](#训练步骤)
+4. [参考资料 Reference](#Reference)
+
+### 所需环境
+tensorflow-gpu==1.13.1  
+keras==2.1.5  
+
+### 文件下载
+训练所需的voc_weights.h5可以去百度网盘下载  
+链接: https://pan.baidu.com/s/1xDRhw0U4dWfy_2rceH-YnA 提取码: cm3q  
+
+### 训练步骤
+1、本文使用VOC格式进行训练。  
+2、训练前将标签文件放在VOCdevkit文件夹下的VOC2007文件夹下的Annotation中。  
+3、训练前将图片文件放在VOCdevkit文件夹下的VOC2007文件夹下的JPEGImages中。  
+4、在训练前利用voc2faster-rcnn.py文件生成对应的txt。  
+5、再运行根目录下的voc_annotation.py，运行前需要将classes改成你自己的classes。  
+```python
+classes = ["aeroplane", "bicycle", "bird", "boat", "bottle", "bus", "car", "cat", "chair", "cow", "diningtable", "dog", "horse", "motorbike", "person", "pottedplant", "sheep", "sofa", "train", "tvmonitor"]
+```
+6、就会生成对应的2007_train.txt，每一行对应其图片位置及其真实框的位置。  
+7、在训练前需要修改model_data里面的voc_classes.txt文件，需要将classes改成你自己的classes。  
+8、运行train.py即可开始训练。
+
+### mAP目标检测精度计算更新
+更新了get_gt_txt.py、get_dr_txt.py和get_map.py文件。  
+get_map文件克隆自https://github.com/Cartucho/mAP  
+具体mAP计算过程可参考：https://www.bilibili.com/video/BV1zE411u7Vw
+
+### Reference
+https://github.com/qqwweee/keras-yolo3/  
+https://github.com/pierluigiferrari/ssd_keras  
+https://github.com/kuhung/SSD_keras  
+https://github.com/jinfagang/keras_frcnn  
+https://github.com/Cartucho/mAP  

VOCdevkit/VOC2007/Annotations/README.md

@@ -0,0 +1 @@
+存放标签文件

VOCdevkit/VOC2007/ImageSets/Main/README.md

@@ -0,0 +1 @@
+存放训练索引文件

VOCdevkit/VOC2007/JPEGImages/README.md

@@ -0,0 +1 @@
+存放图片文件

VOCdevkit/VOC2007/voc2faster-rcnn.py

@@ -0,0 +1,44 @@
+import os
+import random 
+ 
+xmlfilepath=r'./VOCdevkit/VOC2007/Annotations'
+saveBasePath=r"./VOCdevkit/VOC2007/ImageSets/Main/"
+ 
+trainval_percent=1
+train_percent=1
+
+temp_xml = os.listdir(xmlfilepath)
+total_xml = []
+for xml in temp_xml:
+    if xml.endswith(".xml"):
+        total_xml.append(xml)
+
+num=len(total_xml)  
+list=range(num)  
+tv=int(num*trainval_percent)  
+tr=int(tv*train_percent)  
+trainval= random.sample(list,tv)  
+train=random.sample(trainval,tr)  
+ 
+print("train and val size",tv)
+print("traub suze",tr)
+ftrainval = open(os.path.join(saveBasePath,'trainval.txt'), 'w')  
+ftest = open(os.path.join(saveBasePath,'test.txt'), 'w')  
+ftrain = open(os.path.join(saveBasePath,'train.txt'), 'w')  
+fval = open(os.path.join(saveBasePath,'val.txt'), 'w')  
+ 
+for i  in list:  
+    name=total_xml[i][:-4]+'\n'  
+    if i in trainval:  
+        ftrainval.write(name)  
+        if i in train:  
+            ftrain.write(name)  
+        else:  
+            fval.write(name)  
+    else:  
+        ftest.write(name)  
+  
+ftrainval.close()  
+ftrain.close()  
+fval.close()  
+ftest .close()

Vision_for_anchor.py

@@ -0,0 +1,89 @@
+import numpy as np
+import matplotlib.pyplot as plt
+from tensorflow import keras
+from utils.config import Config
+
+config = Config()
+
+def generate_anchors(sizes=None, ratios=None):
+    if sizes is None:
+        sizes = config.anchor_box_scales
+
+    if ratios is None:
+        ratios = config.anchor_box_ratios
+
+    num_anchors = len(sizes) * len(ratios)
+
+    anchors = np.zeros((num_anchors, 4))
+    # print(anchors)
+    anchors[:, 2:] = np.tile(sizes, (2, len(ratios))).T
+    
+    for i in range(len(ratios)):
+        anchors[3*i:3*i+3, 2] = anchors[3*i:3*i+3, 2]*ratios[i][0]
+        anchors[3*i:3*i+3, 3] = anchors[3*i:3*i+3, 3]*ratios[i][1]
+    
+
+    anchors[:, 0::2] -= np.tile(anchors[:, 2] * 0.5, (2, 1)).T
+    anchors[:, 1::2] -= np.tile(anchors[:, 3] * 0.5, (2, 1)).T
+    # print(anchors)
+    return anchors
+
+def shift(shape, anchors, stride=config.rpn_stride):
+    # [0,1,2,3,4,5……37]
+    # [0.5,1.5,2.5……37.5]
+    # [8,24,……]
+    shift_x = (np.arange(0, shape[0], dtype=keras.backend.floatx()) + 0.5) * stride
+    shift_y = (np.arange(0, shape[1], dtype=keras.backend.floatx()) + 0.5) * stride
+
+    shift_x, shift_y = np.meshgrid(shift_x, shift_y)
+
+    shift_x = np.reshape(shift_x, [-1])
+    shift_y = np.reshape(shift_y, [-1])
+    # print(shift_x,shift_y)
+    shifts = np.stack([
+        shift_x,
+        shift_y,
+        shift_x,
+        shift_y
+    ], axis=0)
+
+    shifts            = np.transpose(shifts)
+    number_of_anchors = np.shape(anchors)[0]
+
+    k = np.shape(shifts)[0]
+
+    shifted_anchors = np.reshape(anchors, [1, number_of_anchors, 4]) + np.array(np.reshape(shifts, [k, 1, 4]), keras.backend.floatx())
+    shifted_anchors = np.reshape(shifted_anchors, [k * number_of_anchors, 4])
+
+    
+    fig = plt.figure()
+    ax = fig.add_subplot(111)
+    plt.ylim(-300,900)
+    plt.xlim(-300,900)
+    # plt.ylim(0,600)
+    # plt.xlim(0,600)
+    plt.scatter(shift_x,shift_y)
+    box_widths = shifted_anchors[:,2]-shifted_anchors[:,0]
+    box_heights = shifted_anchors[:,3]-shifted_anchors[:,1]
+    
+    initial = 0
+    for i in [initial+0,initial+1,initial+2,initial+3,initial+4,initial+5,initial+6,initial+7,initial+8]:
+        rect = plt.Rectangle([shifted_anchors[i, 0],shifted_anchors[i, 1]],box_widths[i],box_heights[i],color="r",fill=False)
+        ax.add_patch(rect)
+    plt.show()
+
+    return shifted_anchors
+
+def get_anchors(shape,width,height):
+    anchors = generate_anchors()
+    network_anchors = shift(shape,anchors)
+    network_anchors[:,0] = network_anchors[:,0]/width
+    network_anchors[:,1] = network_anchors[:,1]/height
+    network_anchors[:,2] = network_anchors[:,2]/width
+    network_anchors[:,3] = network_anchors[:,3]/height
+    network_anchors = np.clip(network_anchors,0,1)
+    print(network_anchors)
+    return network_anchors
+
+if __name__ == "__main__":
+    get_anchors([38,38],600,600)