在使用Mask R-CNN訓練自己的資料時，需要提前瞭解Mask R-CNN的標註工具以及跑通Mask R-CNN的Demo。下面的兩篇部落格分別介紹了Mask R-CNN標註工具以及如何跑通Mask R-CNN的Demo。

Mask RCNN標註工具

使用Keras與Tensorflow安裝Mask RCNN並跑通Demo

在瞭解了Mask RCNN標註工具以及跑通了Demo後，我們要根據實際的問題來進行訓練自己的Mask RCNN模型。由於資料集不方便公開，下面簡單介紹訓練的整個流程。

1   準備資料集

    訓練Mask RCNN模型只需要4個資料夾的資料，分別是原圖，json檔案，生成的json資料夾以及label.png。

    注意：在使用labelme標註後生成的json資料夾中的label.png圖片是16位的，但是Opencv讀取16位的時候會出現錯誤，因此我們需要通過指令碼將16位的label.png轉為8位的，指令碼大家可以在這裡下載。labelme16位轉8位下載

資料夾資料：

4個資料夾中的內容分別是

cv2_mask                                                       json

labelme_json                                                 pic

2  訓練模型

準備好資料集後，我們就需要去訓練我的模型。

訓練資料的原始碼：

# -*- 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()#得到該.py的絕對路徑

#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 = 2

    # 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 = 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):
    # 得到該圖中有多少個例項（物體）
    def get_obj_index(self, image):
        n = np.max(image)
        return n

    # 解析labelme中得到的yaml檔案，從而得到mask每一層對應的例項標籤
    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

    # 重新寫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

    # 重新寫load_shapes，裡面包含自己的類別,可以任意新增
    # 並在self.image_info資訊中添加了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,可通過這種方式擴充套件多個物體
        self.add_class("shapes", 1, "package") # 包裹
        for i in range(count):
            # 獲取圖片寬和高

            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)

    # 重寫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("tank") != -1:
                # print "box"
                labels_form.append("tank")
            elif labels[i].find("triangle")!=-1:
                #print "column"
                labels_form.append("triangle")
            elif labels[i].find("white")!=-1:
                #print "package"
                labels_form.append("white")
        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

#基礎設定
dataset_root_path="train_data/"#含有4個資料夾的主目錄
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與val資料集準備
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=20,
            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=40,
            layers="all")
 

訓練的結果圖：

3  在經過訓練後，通過測試可以觀察我們模型的效果，訓練的次數比較少，效果一般。

測試程式碼如下圖所示：

# -*- 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', 'package']
# 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'])

參考部落格：

https://blog.csdn.net/qq_29462849/article/details/81037343

https://blog.csdn.net/l297969586/article/details/79140840/