maskrcnn正常运行系列（CPU）

TR.lee

已于 2023-12-09 16:09:53 修改

阅读量312

点赞数

文章标签： python 深度学习机器学习

于 2023-04-20 12:26:38 首次发布

本文链接：https://blog.csdn.net/qq_43404472/article/details/130263502

版权

在这里插入图片描述

Mask_RCNN-2.1系列

1. 首先，在已有的训练结果基础上，测试环境是否可以正常运行。

1.训练代码：

python balloon.py train --dataset=../../balloon --weights=coco

环境正确的话，进行训练过程。

2.测试代码：

python balloon.py splash --weights=./logs/balloon20230405T1526/mask_rcnn_balloon_0001.h5 --image=../../balloon/val/3800636873_ace2c2795f_b.jpg

测试结果返回显示实例分割图片。
在这里插入图片描述

2. 其次，测试自己数据集上的运行结果。

（1）数据集。
训练集：
在这里插入图片描述

测试集：

（2）训练代码：train_test.py

# -*- 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 + 2  # background + 1 shapes  注意这里我是4类，所以是4+1

    # 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 = 256
    IMAGE_MAX_DIM = 1