本文中训练代码参考：https://blog.csdn.net/l297969586/article/details/79140840
我使用mask rcnn训练了自己的数据集用来识别舌头，测试结果如下：
1 写在前面
- 基于Mask RCNN开源项目：https://github.com/matterport/Mask_RCNN
- 图片标记工具基于开源项目：https://github.com/wkentaro/labelme
- 训练图片大小不一致，训练图片数据集1498张
- 训练工具GPU GTX 1080ti，训练用时约5h
有关labelme的安装与使用可参考我的另一篇博文：https://blog.csdn.net/disiwei1012/article/details/79508954
有关Mask RCNN、Faster RCNN的原理解读可参考我的另两篇博文：
https://blog.csdn.net/disiwei1012/article/details/79508839
https://blog.csdn.net/disiwei1012/article/details/79466088
2 准备训练数据集
1、使用labelme标注图片保存后，会产生与原图像同名后缀为json的文件，如下：
2、然后需要将后缀名为json的文件转化为5个文件，如下：
转化方法：首先找到labelme的安装路径，进入Scripts文件夹，然后执行
python labelme_json_to_dataset [文件名]完整如下：
但是这样转化有一个很大的问题，就是每次只能转化一个.json文件，我修改了…labelme\Scripts\文件夹下的labelme_json_to_dataset文件，可以一下把整个文件夹下的.json文件全部转化，如下：
修改后的labelme_json_to_dataset文件如下：
#!D:\conda\envs\labelme\python.exe
import argparse
import json
import os
import os.path as osp
import warnings
import numpy as np
import PIL.Image
import yaml
from labelme import utils
def main():
parser = argparse.ArgumentParser()
parser.add_argument('json_file')
parser.add_argument('-o', '--out', default=None)
args = parser.parse_args()
json_file = args.json_file
list = os.listdir(json_file)
for i in range(0, len(list)):
path = os.path.join(json_file, list[i])
if os.path.isfile(path):
data = json.load(open(path))
img = utils.img_b64_to_array(data['imageData'])
lbl, lbl_names = utils.labelme_shapes_to_label(img.shape, data['shapes'])
captions = ['%d: %s' % (l, name) for l, name in enumerate(lbl_names)]
lbl_viz = utils.draw_label(lbl, img, captions)
out_dir = osp.basename(list[i]).replace('.', '_')
out_dir = osp.join(osp.dirname(list[i]), out_dir)
if not osp.exists(out_dir):
os.mkdir(out_dir)
PIL.Image.fromarray(img).save(osp.join(out_dir, 'img.png'))
PIL.Image.fromarray(lbl).save(osp.join(out_dir, 'label.png'))
PIL.Image.fromarray(lbl_viz).save(osp.join(out_dir, 'label_viz.png'))
with open(osp.join(out_dir, 'label_names.txt'), 'w') as f:
for lbl_name in lbl_names:
f.write(lbl_name + '\n')
warnings.warn('info.yaml is being replaced by label_names.txt')
info = dict(label_names=lbl_names)
with open(osp.join(out_dir, 'info.yaml'), 'w') as f:
yaml.safe_dump(info, f, default_flow_style=False)
print('Saved to: %s' % out_dir)
if __name__ == '__main__':
main()3、生成Mask文件，由于labelme生成的掩码标签 label.png为16位存储，opencv默认读取8位，需要将16位转8位
可通过C++程序转化，代码请参考这篇博文：http://blog.csdn.net/l297969586/article/details/79154150
也可通过Java程序转化，转化代码如下：
/**
* 说明 : 16位 转化为 8位
*/
public void transform(String originPath, String transformPath) {
if(!new File(originPath).exists()) {
System.out.println("文件不存在！");
return;
}
//原图片
Mat src = Imgcodecs.imread(originPath, Imgcodecs.CV_LOAD_IMAGE_UNCHANGED);
//生成的图片
Mat mat = Mat.zeros(src.rows(), src.cols(), CvType.CV_8SC1);
for (int r = 0; r < src.rows(); r++) {
for(int c = 0; c < src.cols(); c++){
mat.put(r, c, src.get(r, c));
}
}
Imgcodecs.imwrite(transformPath, mat);
}4、最后的数据集的样子，如下：
cv2_mask : 保存8位的Mask文件
json : labelme标记保存产生的文件
labelme_json : 通过python labelme_json_to_dataset转化生成的文件
pic : 原始图片
注意：这4个文件夹中的文件保持一致
pic文件夹内容如下：
cv2_mask文件夹内容如下：
labelme_json文件夹内容如下：
json 文件夹内容如下：
3 训练完整代码
在项目目录下，新建train_data文件夹，并将准备好的数据集放入train_data文件夹
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
from config import Config
import utils
import model as modellib
import visualize
import yaml
from model import log
from PIL import Image
# Root directory of the project
ROOT_DIR = os.getcwd()
# 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 + 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 = 800
IMAGE_MAX_DIM = 1600
# 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 = 32
# Use a small epoch since the data is simple
STEPS_PER_EPOCH = 100
# use small validation steps since the epoch is small
VALIDATION_STEPS = 5
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, "tongue") # 黑色素瘤
for i in range(count):
# 获取图片宽和高
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("tongue") != -1:
# print "box"
labels_form.append("tongue")
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="train_data/"
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(7, 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
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=30,
layers="all")
4 完整测试代码
import os
import sys
import random
import math
import numpy as np
import skimage.io
import matplotlib
import matplotlib.pyplot as plt
import coco
import utils
import model as modellib
import visualize
from config import Config
%matplotlib inline
# Root directory of the project
ROOT_DIR = os.getcwd()
# 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(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)
# 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 + 1 # 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 = 800
IMAGE_MAX_DIM = 1600
# 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 = 32
# Use a small epoch since the data is simple
STEPS_PER_EPOCH = 100
# use small validation steps since the epoch is small
VALIDATION_STEPS = 5
#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)
# Load weights trained on MS-COCO
# model.load_weights(COCO_MODEL_PATH, by_name=True)
model_path = model.find_last()[1]
# Load trained weights (fill in path to trained weights here)
assert model_path != "", "Provide path to trained weights"
print("Loading weights from ", model_path)
model.load_weights(model_path, by_name=True)
class_names = ['BG', 'tongue']
# 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)))
# Run detection
results = model.detect([image], verbose=1)
# Visualize results
r = results[0]
visualize.display_instances(image, r['rois'], r['masks'], r['class_ids'],
class_names, r['scores'])有疑问欢迎留言哈~