物体检测--Mask_RCNN系列:(三)训练自己的数据集与代码详解
写下前面：前面我们对mask rcnn进行了解释，其中很多参考和引用了其他朋友的经验和资源，并对开源代码进行了实例测试，这里再给出mask rcnn项目开源地址：https://github.com/matterport/Mask_RCNN.后面我会就如何训练自己的数据集进行简要的总结，并将自己对训练和测试部分的代码注释和理解分享给大家，包括训练数据。
训练自己的数据集要用到数据标注工具：这里建议基于开源项目图片标记工具：https://github.com/wkentaro/labelme ，
这里有关数据标记工具labelme的使用可以参考这篇博客：https://blog.csdn.net/shwan_ma/article/details/77823281
利用标注工具准备好数据集：
将标注好的数据分别放在四个文件夹下：
《一》：cv2_mask:
《二》：json:
《三》：labelme_json\1_json
《四》：pic:
====》ok --- 训练数据准备完成：
下面新建train_selfdata.py脚本：添加如下代码：
# -*- coding: utf-8 -*-
import os
import sys
import random
import math
import re
import time
import numpy as np
import cv2
import matplotlib
import matplotlib.pyplot as plt
import tensorflow as tf
from mrcnn.config import Config
# import utils
from mrcnn import model as modellib, utils
from mrcnn import visualize
import yaml
from mrcnn.model import log
from PIL import Image
# os.environ["CUDA_VISIBLE_DEVICES"] = "0"
# Root directory of the project
ROOT_DIR = os.getcwd()
# ROOT_DIR = os.path.abspath("../")
# Directory to save logs and trained model
MODEL_DIR = os.path.join(ROOT_DIR, "logs")
iter_num = 0
# Local path to trained weights file
COCO_MODEL_PATH = os.path.join(ROOT_DIR, "mask_rcnn_coco.h5")
# Download COCO trained weights from Releases if needed
if not os.path.exists(COCO_MODEL_PATH):
utils.download_trained_weights(COCO_MODEL_PATH)
class ShapesConfig(Config):
"""Configuration for training on the toy shapes dataset.
Derives from the base Config class and overrides values specific
to the toy shapes dataset.
"""
# Give the configuration a recognizable name
NAME = "shapes"
# Train on 1 GPU and 8 images per GPU. We can put multiple images on each
# GPU because the images are small. Batch size is 8 (GPUs * images/GPU).
GPU_COUNT = 1
IMAGES_PER_GPU = 1
# Number of classes (including background)
NUM_CLASSES = 1 + 1 # background + 1 shapes 这里根据训练情况修改
# Use small images for faster training. Set the limits of the small side
# the large side, and that determines the image shape.
IMAGE_MIN_DIM = 320
IMAGE_MAX_DIM = 384
# Use smaller anchors because our image and objects are small
RPN_ANCHOR_SCALES = (8 * 6, 16 * 6, 32 * 6, 64 * 6, 128 * 6) # anchor side in pixels
# Reduce training ROIs per image because the images are small and have
# few objects. Aim to allow ROI sampling to pick 33% positive ROIs.
TRAIN_ROIS_PER_IMAGE = 100
# Use a small epoch since the data is simple
STEPS_PER_EPOCH = 100
# use small validation steps since the epoch is small
VALIDATION_STEPS = 50
config = ShapesConfig()
config.display()
class DrugDataset(utils.Dataset):
# 得到该图中有多少个实例（物体）
def get_obj_index(self, image):
n = np.max(image)
return n
# 解析labelme中得到的yaml文件，从而得到mask每一层对应的实例标签
def from_yaml_get_class(self, image_id):
info = self.image_info[image_id]
with open(info['yaml_path']) as f:
temp = yaml.load(f.read())
labels = temp['label_names']
del labels[0]
return labels
# 重新写draw_mask
def draw_mask(self, num_obj, mask, image, image_id):
# print("draw_mask-->",image_id)
# print("self.image_info",self.image_info)
info = self.image_info[image_id]
# print("info-->",info)
# print("info[width]----->",info['width'],"-info[height]--->",info['height'])
for index in range(num_obj):
for i in range(info['width']):
for j in range(info['height']):
# print("image_id-->",image_id,"-i--->",i,"-j--->",j)
# print("info[width]----->",info['width'],"-info[height]--->",info['height'])
at_pixel = image.getpixel((i, j))
if at_pixel == index + 1:
mask[j, i, index] = 1
return mask
# 重新写load_shapes，里面包含自己的自己的类别
# 并在self.image_info信息中添加了path、mask_path 、yaml_path
# yaml_pathdataset_root_path = "/tongue_dateset/"
# img_floder = dataset_root_path + "rgb"
# mask_floder = dataset_root_path + "mask"
# dataset_root_path = "/tongue_dateset/"
def load_shapes(self, count, img_floder, mask_floder, imglist, dataset_root_path):
"""Generate the requested number of synthetic images.
count: number of images to generate.
height, width: the size of the generated images.
"""
# Add classes
self.add_class("shapes", 1, "person") # 修改！！！！！！！
for i in range(count):
# 获取图片宽和高
print(i)
filestr = imglist[i].split(".")[0]
# print(imglist[i],"-->",cv_img.shape[1],"--->",cv_img.shape[0])
# print("id-->", i, " imglist[", i, "]-->", imglist[i],"filestr-->",filestr)
# filestr = filestr.split("_")[1]
mask_path = mask_floder + "/" + filestr + ".png"
yaml_path = dataset_root_path + "labelme_json/" + filestr + "_json/info.yaml"
print(dataset_root_path + "labelme_json/" + filestr + "_json/img.png")
cv_img = cv2.imread(dataset_root_path + "labelme_json/" + filestr + "_json/img.png")
self.add_image("shapes", image_id=i, path=img_floder + "/" + imglist[i],
width=cv_img.shape[1], height=cv_img.shape[0], mask_path=mask_path, yaml_path=yaml_path)
# 重写load_mask
def load_mask(self, image_id):
"""Generate instance masks for shapes of the given image ID.
"""
global iter_num
print("image_id", image_id)
info = self.image_info[image_id]
count = 1 # number of object
img = Image.open(info['mask_path'])
num_obj = self.get_obj_index(img)
mask = np.zeros([info['height'], info['width'], num_obj], dtype=np.uint8)
mask = self.draw_mask(num_obj, mask, img, image_id)
occlusion = np.logical_not(mask[:, :, -1]).astype(np.uint8)
for i in range(count - 2, -1, -1):
mask[:, :, i] = mask[:, :, i] * occlusion
occlusion = np.logical_and(occlusion, np.logical_not(mask[:, :, i]))
labels = []
labels = self.from_yaml_get_class(image_id)
labels_form = []
for i in range(len(labels)):
if labels[i].find("person") != -1:
# print "car"
labels_form.append("person")
elif labels[i].find("leg") != -1:
# print "leg"
labels_form.append("leg")
elif labels[i].find("well") != -1:
# print "well"
labels_form.append("well")
class_ids = np.array([self.class_names.index(s) for s in labels_form])
return mask, class_ids.astype(np.int32)
def get_ax(rows=1, cols=1, size=8):
"""Return a Matplotlib Axes array to be used in
all visualizations in the notebook. Provide a
central point to control graph sizes.
Change the default size attribute to control the size
of rendered images
"""
_, ax = plt.subplots(rows, cols, figsize=(size * cols, size * rows))
return ax
# 基础设置
dataset_root_path = "samples/trinmy/myinfo/" # 指定数据路径--此文件夹下放四个训练数据文件夹
img_floder = dataset_root_path + "pic"
mask_floder = dataset_root_path + "cv2_mask"
# yaml_floder = dataset_root_path
imglist = os.listdir(img_floder)
count = len(imglist)
# train与val数据集准备
dataset_train = DrugDataset()
dataset_train.load_shapes(count, img_floder, mask_floder, imglist, dataset_root_path)
dataset_train.prepare()
# print("dataset_train-->",dataset_train._image_ids)
dataset_val = DrugDataset()
dataset_val.load_shapes(count, img_floder, mask_floder, imglist, dataset_root_path)
dataset_val.prepare()
# print("dataset_val-->",dataset_val._image_ids)
# Load and display random samples
# image_ids = np.random.choice(dataset_train.image_ids, 4)
# for image_id in image_ids:
# image = dataset_train.load_image(image_id)
# mask, class_ids = dataset_train.load_mask(image_id)
# visualize.display_top_masks(image, mask, class_ids, dataset_train.class_names)
# Create model in training mode
model = modellib.MaskRCNN(mode="training", config=config,
model_dir=MODEL_DIR)
# Which weights to start with?
init_with = "coco" # imagenet, coco, or last
if init_with == "imagenet":
model.load_weights(model.get_imagenet_weights(), by_name=True)
elif init_with == "coco":
# Load weights trained on MS COCO, but skip layers that
# are different due to the different number of classes
# See README for instructions to download the COCO weights
# print(COCO_MODEL_PATH)
model.load_weights(COCO_MODEL_PATH, by_name=True,
exclude=["mrcnn_class_logits", "mrcnn_bbox_fc",
"mrcnn_bbox", "mrcnn_mask"])
elif init_with == "last":
# Load the last model you trained and continue training
model.load_weights(model.find_last()[1], by_name=True)
# Train the head branches
# Passing layers="heads" freezes all layers except the head
# layers. You can also pass a regular expression to select
# which layers to train by name pattern.
model.train(dataset_train, dataset_val,
learning_rate=config.LEARNING_RATE,
epochs=10,
layers='heads')
# Fine tune all layers
# Passing layers="all" trains all layers. You can also
# pass a regular expression to select which layers to
# train by name pattern.
model.train(dataset_train, dataset_val,
learning_rate=config.LEARNING_RATE / 10,
epochs=10,
layers="all")
其中，注意修改自己训练文件的路径，其他超参数参数可在工程的config.py文件中修改，一般不需要修改：
### 上述开始正常训练后，训练的模型会保存在logs文件夹中；同时可以通过tensorboard对训练过程进行可视化查看。
下面就用训练的模型进行测试：在自己的工程中新建test_self.py脚本，写入如下代码即可进行测试及可视化显示：
# -*- coding: utf-8 -*-
import os
import sys
import random
import math
import numpy as np
import skimage.io
import matplotlib
import matplotlib.pyplot as plt
import cv2
import time
from mrcnn.config import Config
from datetime import datetime
# Root directory of the project
ROOT_DIR = os.getcwd()
# Import Mask RCNN
sys.path.append(ROOT_DIR) # To find local version of the library
from mrcnn import utils
import mrcnn.model as modellib
from mrcnn import visualize
# Import COCO config
sys.path.append(os.path.join(ROOT_DIR, "samples/coco/")) # To find local version
from samples.coco import coco
# Directory to save logs and trained model
MODEL_DIR = os.path.join(ROOT_DIR, "logs")
# Local path to trained weights file
COCO_MODEL_PATH = os.path.join(MODEL_DIR ,"mask_rcnn_coco.h5")
# Download COCO trained weights from Releases if needed
if not os.path.exists(COCO_MODEL_PATH):
utils.download_trained_weights(COCO_MODEL_PATH)
print("cuiwei***********************")
# Directory of images to run detection on
IMAGE_DIR = os.path.join(ROOT_DIR, "images")
class ShapesConfig(Config):
"""Configuration for training on the toy shapes dataset.
Derives from the base Config class and overrides values specific
to the toy shapes dataset.
"""
# Give the configuration a recognizable name
NAME = "shapes"
# Train on 1 GPU and 8 images per GPU. We can put multiple images on each
# GPU because the images are small. Batch size is 8 (GPUs * images/GPU).
GPU_COUNT = 1
IMAGES_PER_GPU = 1
# Number of classes (including background)
NUM_CLASSES = 1 + 3 # background + 3 shapes
# Use small images for faster training. Set the limits of the small side
# the large side, and that determines the image shape.
IMAGE_MIN_DIM = 320
IMAGE_MAX_DIM = 384
# Use smaller anchors because our image and objects are small
RPN_ANCHOR_SCALES = (8 * 6, 16 * 6, 32 * 6, 64 * 6, 128 * 6) # anchor side in pixels
# Reduce training ROIs per image because the images are small and have
# few objects. Aim to allow ROI sampling to pick 33% positive ROIs.
TRAIN_ROIS_PER_IMAGE =100
# Use a small epoch since the data is simple
STEPS_PER_EPOCH = 100
# use small validation steps since the epoch is small
VALIDATION_STEPS = 50
#import train_tongue
#class InferenceConfig(coco.CocoConfig):
class InferenceConfig(ShapesConfig):
# Set batch size to 1 since we'll be running inference on
# one image at a time. Batch size = GPU_COUNT * IMAGES_PER_GPU
GPU_COUNT = 1
IMAGES_PER_GPU = 1
config = InferenceConfig()
model = modellib.MaskRCNN(mode="inference", model_dir=MODEL_DIR, config=config)
# Create model object in inference mode.
model = modellib.MaskRCNN(mode="inference", model_dir=MODEL_DIR, config=config)
# Load weights trained on MS-COCO
model.load_weights(COCO_MODEL_PATH, by_name=True)
# COCO Class names
# Index of the class in the list is its ID. For example, to get ID of
# the teddy bear class, use: class_names.index('teddy bear')
class_names = ['BG', 'tank','triangle','white']
# Load a random image from the images folder
file_names = next(os.walk(IMAGE_DIR))[2]
image = skimage.io.imread(os.path.join(IMAGE_DIR, random.choice(file_names)))
a=datetime.now()
# Run detection
results = model.detect([image], verbose=1)
b=datetime.now()
# Visualize results
print("shijian",(b-a).seconds)
r = results[0]
visualize.display_instances(image, r['rois'], r['masks'], r['class_ids'],
class_names, r['scores'])
(说明：这里数据集是借用他人的训练集)
最后；将自己的项目及其训练集图片，以及详细注释了的训练代码上传github：https://github.com/Danbinabo