maskrcnn benchmark pytorch 训练+测试

项目网址：maskrcnn benchmark

---

一、环境搭建

1.准备工作

我的基础环境：

系统：windows 10 ，Ubutun １８.0１

Python环境：Anaconda3

conda： 4.5.4
pip ： 20.2.2
Python ：3.7.0
GPU ：
NVIDIA GeForce RTX 2060 6G (windows)
Telsa v100 16G *8 (Ubutun)
pytorch ：1.2
cuda：10.0
首先进入github网址，点击INSTALL.md

windows环境下和linux有所不同 ，严格安装他给的文档安装 不然后续会报错，这里以windows为例
#首先创建一个conda的虚拟环境并进入
open a cmd and change to desired installation directory
from now on will be refered as INSTALL_DIR
conda create --name maskrcnn_benchmark
conda activate maskrcnn_benchmark

#按照他给出的顺序安装
# this installs the right pip and dependencies for the fresh python
conda install ipython

# maskrcnn_benchmark and coco api dependencies
pip install ninja yacs cython matplotlib tqdm opencv-python

# follow PyTorch installation in https://pytorch.org/get-started/locally/
# we give the instructions for CUDA 9.0
## Important : check the cuda version installed on your computer by running the command in the cmd :
nvcc -- version

#这里他安装的cuda 9.0 实测20系列的显卡可能会与cuda9.0不匹配，我在安装9.0之后报错了，无法执行cudnn， 然后卸载重新装了10.0就解决了问题
conda install -c pytorch pytorch-nightly torchvision cudatoolkit=9.0

git clone https://github.com/cocodataset/cocoapi.git

    #To prevent installation error do the following after commiting cocooapi :
    #using file explorer  naviagate to cocoapi\PythonAPI\setup.py and change line 14 from:
    #extra_compile_args=['-Wno-cpp', '-Wno-unused-function', '-std=c99'],
    #to
    #extra_compile_args={'gcc': ['/Qstd=c99']},
    #Based on  https://github.com/cocodataset/cocoapi/issues/51

cd cocoapi/PythonAPI
python setup.py build_ext install

# navigate back to INSTALL_DIR
cd ..
cd ..
# install apex

git clone https://github.com/NVIDIA/apex.git
cd apex
python setup.py install --cuda_ext --cpp_ext
# navigate back to INSTALL_DIR
cd ..
# install PyTorch Detection

git clone https://github.com/Idolized22/maskrcnn-benchmark.git
cd maskrcnn-benchmark

# the following will install the lib with
# symbolic links, so that you can modify
# the files if you want and won't need to
# re-build it
python setup.py build develop

---

出现的问题

在 linux 下 执行 git clone https://github.com/NVIDIA/apex.git python setup.py install --cuda_ext --cpp_ext 出现 nvidia apex build error 以及 error: command 'gcc' failed with exit status 1

---

解决方案

git checkout f3a960f80244cf9e80558ab30f7f7e8cbf03c0a0

二、数据集准备

1.labelme2coco

maskrcnn benchmark 需要的数据集格式为coco数据集格式。我是通过labelme来标注数据，然后在转换为coco格式。网上有很多转换的代码，很多都有问题。在linux下测试时出现如下问题：

AssertionError: tensor([398.9765, 403.2801, 415.9314, 402.9380])

解决方法：

import argparse
import json
import matplotlib.pyplot as plt
import skimage.io as io
import cv2
from labelme import utils
import numpy as np
import glob
import PIL.Image

REQUIRE_MASK = False

class labelme2coco(object):
    def __init__(self,labelme_json=[],save_json_path='./new.json'):
        '''
        :param labelme_json: the list of all labelme json file paths
        :param save_json_path: the path to save new json
        '''
        self.labelme_json=labelme_json
        self.save_json_path=save_json_path
        self.images=[]
        self.categories=[]
        self.annotations=[]
        # self.data_coco = {}
        self.label=[]
        self.annID=1
        self.height=0
        self.width=0
        self.require_mask = REQUIRE_MASK
        self.save_json()

    def data_transfer(self):
        for num,json_file in enumerate(self.labelme_json):
            if not json_file == self.save_json_path:
                with open(json_file,'r') as fp:
                    data = json.load(fp)
                    self.images.append(self.image(data,num))
                    for shapes in data['shapes']:
                        print("label is ")
                        print(shapes['label'])
                        label=shapes['label']
    #                    if label[1] not in self.label:
                        if label not in self.label:
                            print("find new category: ")
                            self.categories.append(self.categorie(label))
                            print(self.categories)
                            # self.label.append(label[1])
                            self.label.append(label)
                        points=shapes['points']
                        self.annotations.append(self.annotation(points,label,num))
                        self.annID+=1

    def image(self,data,num):
        image={
   }
        img = utils.img_b64_to_arr(data['imageData'])
        # img=io.imread(data['imagePath'])
        # img = cv2.imread(data['imagePath'], 0)
        height, width = img.shape[:2]
        img = None
        image['height']=height
        image['width'] = width
        image['id']=num+1
        image['file_name'] = data['imagePath'].split('/')[-1]

        self.height=height
        self.width=width

        return image

    def categorie(self,label):
        categorie={
   }
        categorie['supercategory'] = label
#        categorie['supercategory'] = label
        categorie['id']=len(self.label)+1
        categorie['name'] = label
#        categorie['name'] = label[1]
        return categorie

    def annotation(self,points,label,num):
        annotation={
   }
        print(points)
        x1 = points[0][0]
        y1 = points[0][1]
        x2 = points[1][0]
        y2 = points[1][1]
        contour = np.array([[x1, y1], [x2, y1], [x2, y2], [x1, y2]]) #points = [[x1, y1], [x2, y2]] for rectangle
        contour = contour.astype(int)
        area = cv2.contourArea(contour)
        print("contour is ", contour, " area = ", area)
        annotation['segmentation']= [list(np.asarray([[x1, y1], [x2, y1], [x2, y2],