Mask R-CNN实验测试

源码下载地址：https://github.com/matterport/Mask_RCNN

一、安装

Mask R-CNN是基于Python 3, Keras, and TensorFlow的

1.复制上面连接中的代码到本地

git clone https://github.com/matterport/Mask_RCNN.git

2.进入到Mask R-CNN的目录下安装依赖库

pip3 install -r requirements.txt

3.运行安装程序

python3 setup.py install

4.下载预训练的COCO权重（mask_rcnn_coco.h5）文件：https://github.com/matterport/Mask_RCNN/releases

完成上面的步骤就可以测试Mask R-CNN的测试代码了。

二、测试

最简单的测试程序

import os
import sys
import random
import math
import numpy as np
import skimage.io
import matplotlib
import matplotlib.pyplot as plt

# Root directory of the project
ROOT_DIR = os.path.abspath("../")

# 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
import coco

%matplotlib inline 

# 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 InferenceConfig(coco.CocoConfig):
    # 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()
config.display()

# 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', 'person', 'bicycle', 'car', 'motorcycle', 'airplane',
               'bus', 'train', 'truck', 'boat', 'traffic light',
               'fire hydrant', 'stop sign', 'parking meter', 'bench', 'bird',
               'cat', 'dog', 'horse', 'sheep', 'cow', 'elephant', 'bear',
               'zebra', 'giraffe', 'backpack', 'umbrella', 'handbag', 'tie',
               'suitcase', 'frisbee', 'skis', 'snowboard', 'sports ball',
               'kite', 'baseball bat', 'baseball glove', 'skateboard',
               'surfboard', 'tennis racket', 'bottle', 'wine glass', 'cup',
               'fork', 'knife', 'spoon', 'bowl', 'banana', 'apple',
               'sandwich', 'orange', 'broccoli', 'carrot', 'hot dog', 'pizza',
               'donut', 'cake', 'chair', 'couch', 'potted plant', 'bed',
               'dining table', 'toilet', 'tv', 'laptop', 'mouse', 'remote',
               'keyboard', 'cell phone', 'microwave', 'oven', 'toaster',
               'sink', 'refrigerator', 'book', 'clock', 'vase', 'scissors',
               'teddy bear', 'hair drier', 'toothbrush']


# 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'])

测试结果展示

三、训练自己的模型

1.使用标注软件VIA（VGG Image Annotator）标注需要训练的数据

2.然后仿照 Mask_RCNN/samples/balloon/balloon.py 修改代码

（1）修改Config类中的

NAME="custom"

（2）修改Dataset类中的load_balloon函数，修改成自己的函数名，然后加入自己的实例标签

self.add_class("custom", 1, "custom")

修改

self.add_image(
                "custom",
                image_id=a['filename'],  # use file name as a unique image id
                path=image_path,
                width=width, height=height,
                polygons=polygons)

（3）修改Dataset类中的load_mask函数中

if image_info["source"] != "custom":

（4）修改Dataset类中的image_reference函数中

if info["source"] == "balloon":

然后在终端输入：

python3 custom.py train --dataset=/path/to/datasetfolder --weights=coco

（dataset：训练样本的路径）开启训练，这里只训练heads layer（可以参程序中train函数），所以训练速度很快，很少的数据也能参与训练，结果也会比较理想。

测试时，只要把上述命令中的train换成splash，加入测试图片或视频的路径即可。

在GTX 1080显卡上测试速度，检测一张图片需要2-3s的时间，查了一下Issues中有个人解释的是：如果是GTX 1080Ti的检测一张能达到1s以下。