一、安装
地址：MaskRCNN-Benchmark(Pytorch版本)
首先要阅读官网说明的环境要求，千万不要一股脑直接安装，不然后面程序很有可能会报错！！！
- PyTorch 1.0 from a nightly release. It will not work with 1.0 nor 1.0.1. Installation instructions can be found in https://pytorch.org/get-start...
- torchvision from master
- cocoapi
- yacs
- matplotlib
- GCC >= 4.9
- OpenCV
# first, make sure that your conda is setup properly with the right environment# for that, check that `which conda`, `which pip` and `which python` points to the# right path. From a clean conda env, this is what you need to doconda create --name maskrcnn_benchmarkconda activate maskrcnn_benchmark# this installs the right pip and dependencies for the fresh pythonconda install ipython# maskrcnn_benchmark and coco api dependenciespip install ninja yacs cython matplotlib tqdm opencv-python# follow PyTorch installation in https://pytorch.org/get-started/locally/# we give the instructions for CUDA 9.0conda install -c pytorch pytorch-nightly torchvision cudatoolkit=9.0export INSTALL_DIR=$PWD# install pycocotoolscd $INSTALL_DIRgit clone https://github.com/cocodataset/cocoapi.gitcd cocoapi/PythonAPIpython setup.py build_ext install# install apexcd $INSTALL_DIRgit clone https://github.com/NVIDIA/apex.gitcd apexpython setup.py install --cuda_ext --cpp_ext# install PyTorch Detectioncd $INSTALL_DIRgit clone https://github.com/facebookresearch/maskrcnn-benchmark.gitcd 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 itpython setup.py build developunset INSTALL_DIR# or if you are on macOS# MACOSX_DEPLOYMENT_TARGET=10.9 CC=clang CXX=clang++ python setup.py build develop一定要按上面的说明一步一步来，千万别省略，不然后面程序很有可能会报错！！！
二、数据准备
我要制作的原始数据格式是训练文件在一个文件（train），标注文件是csv格式，内容如下：
第一步，先把全部有标记的图片且分为训练集，验证集，分别存储在两个文件夹中，代码如下：
#!/usr/bin/env python# coding=UTF-8'''@Description: @Author: HuangQinJian@LastEditors: HuangQinJian@Date: 2019-05-01 12:56:08@LastEditTime: 2019-05-01 13:11:38'''import pandas as pdimport randomimport osimport shutilif not os.path.exists('trained/'): os.mkdir('trained/')if not os.path.exists('val/'): os.mkdir('val/')val_rate = 0.15img_path = 'train/'img_list = os.listdir(img_path)train = pd.read_csv('train_label_fix.csv')# print(img_list)random.shuffle(img_list)total_num = len(img_list)val_num = int(total_num*val_rate)train_num = total_num-val_numfor i in range(train_num): img_name = img_list[i] shutil.copy('train/' + img_name, 'trained/' + img_name)for j in range(val_num): img_name = img_list[j+train_num] shutil.copy('train/' + img_name, 'val/' + img_name)第二步，把csv格式的标注文件转换成coco的格式，代码如下：
#!/usr/bin/env python# coding=UTF-8'''@Description: @Author: HuangQinJian@LastEditors: HuangQinJian@Date: 2019-04-23 11:28:23@LastEditTime: 2019-05-01 13:15:57'''import sysimport osimport jsonimport cv2import pandas as pdSTART_BOUNDING_BOX_ID = 1PRE_DEFINE_CATEGORIES = {}def convert(csv_path, img_path, json_file): """ csv_path : csv文件的路径 img_path : 存放图片的文件夹 json_file : 保存生成的json文件路径 """ json_dict = {"images": [], "type": "instances", "annotations": [], "categories": []} bnd_id = START_BOUNDING_BOX_ID categories = PRE_DEFINE_CATEGORIES csv = pd.read_csv(csv_path) img_nameList = os.listdir(img_path) img_num = len(img_nameList) print("图片总数为{0}".format(img_num)) for i in range(img_num): # for i in range(30): image_id = i+1 img_name = img_nameList[i] if img_name == '60f3ea2534804c9b806e7d5ae1e229cf.jpg' or img_name == '6b292bacb2024d9b9f2d0620f489b1e4.jpg': continue # 可能需要根据具体格式修改的地方 lines = csv[csv.filename == img_name] img = cv2.imread(os.path.join(img_path, img_name)) height, width, _ = img.shape image = {'file_name': img_name, 'height': height, 'width': width, 'id': image_id} print(image) json_dict['images'].append(image) for j in range(len(lines)): # 可能需要根据具体格式修改的地方 category = str(lines.iloc[j]['type']) if category not in categories: new_id = len(categories) categories[category] = new_id category_id = categories[category] # 可能需要根据具体格式修改的地方 xmin = int(lines.iloc[j]['X1']) ymin = int(lines.iloc[j]['Y1']) xmax = int(lines.iloc[j]['X3']) ymax = int(lines.iloc[j]['Y3']) # print(xmin, ymin, xmax, ymax) assert(xmax > xmin) assert(ymax > ymin) o_width = abs(xmax - xmin) o_height = abs(ymax - ymin) ann = {'area': o_width*o_height, 'iscrowd': 0, 'image_id': image_id, 'bbox': [xmin, ymin, o_width, o_height], 'category_id': category_id, 'id': bnd_id, 'ignore': 0, 'segmentation': []} json_dict['annotations'].append(ann) bnd_id = bnd_id + 1 for cate, cid in categories.items(): cat = {'supercategory': 'none', 'id': cid, 'name': cate} json_dict['categories'].append(cat) json_fp = open(json_file, 'w') json_str = json.dumps(json_dict, indent=4) json_fp.write(json_str) json_fp.close()if __name__ == '__main__': # csv_path = 'data/train_label_fix.csv' # img_path = 'data/train/' # json_file = 'train.json' csv_path = 'train_label_fix.csv' img_path = 'trained/' json_file = 'trained.json' convert(csv_path, img_path, json_file) csv_path = 'train_label_fix.csv' img_path = 'val/' json_file = 'val.json' convert(csv_path, img_path, json_file)第三步，可视化转换后的coco的格式，以确保转换正确，代码如下：
（注意：在这一步中，需要先下载 cocoapi , 可能出现的 问题）
#!/usr/bin/env python# coding=UTF-8'''@Description: @Author: HuangQinJian@LastEditors: HuangQinJian@Date: 2019-04-23 13:43:24@LastEditTime: 2019-04-30 21:29:26'''from pycocotools.coco import COCOimport skimage.io as ioimport matplotlib.pyplot as pltimport pylabimport cv2import osfrom skimage.io import imsaveimport numpy as nppylab.rcParams['figure.figsize'] = (8.0, 10.0)img_path = 'data/train/'annFile = 'train.json'if not os.path.exists('anno_image_coco/'): os.makedirs('anno_image_coco/')def draw_rectangle(coordinates, image, image_name): for coordinate in coordinates: left = np.rint(coordinate[0]) right = np.rint(coordinate[1]) top = np.rint(coordinate[2]) bottom = np.rint(coordinate[3]) # 左上角坐标, 右下角坐标 cv2.rectangle(image, (int(left), int(right)), (int(top), int(bottom)), (0, 255, 0), 2) imsave('anno_image_coco/'+image_name, image)# 初始化标注数据的 COCO apicoco = COCO(annFile)# display COCO categories and supercategoriescats = coco.loadCats(coco.getCatIds())nms = [cat['name'] for cat in cats]# print('COCO categories: \n{}\n'.format(' '.join(nms)))nms = set([cat['supercategory'] for cat in cats])# print('COCO supercategories: \n{}'.format(' '.join(nms)))img_path = 'data/train/'img_list = os.listdir(img_path)# for i in range(len(img_list)):for i in range(7): imgIds = i+1 img = coco.loadImgs(imgIds)[0] image_name = img['file_name'] # print(img) # 加载并显示图片 # I = io.imread('%s/%s' % (img_path, img['file_name'])) # plt.axis('off') # plt.imshow(I) # plt.show() # catIds=[] 说明展示所有类别的box，也可以指定类别 annIds = coco.getAnnIds(imgIds=img['id'], catIds=[], iscrowd=None) anns = coco.loadAnns(annIds) # print(anns) coordinates = [] img_raw = cv2.imread(os.path.join(img_path, image_name)) for j in range(len(anns)): coordinate = [] coordinate.append(anns[j]['bbox'][0]) coordinate.append(anns[j]['bbox'][1]+anns[j]['bbox'][3]) coordinate.append(anns[j]['bbox'][0]+anns[j]['bbox'][2]) coordinate.append(anns[j]['bbox'][1]) # print(coordinate) coordinates.append(coordinate) # print(coordinates) draw_rectangle(coordinates, img_raw, image_name)三、文件配置
在训练自己的数据集过程中需要修改的地方可能很多，下面我就列出常用的几个：
- 修改
maskrcnn_benchmark/config/paths_catalog.py中数据集路径：
class DatasetCatalog(object): # 看自己的实际情况修改路径！！！ # 看自己的实际情况修改路径！！！ # 看自己的实际情况修改路径！！！ DATA_DIR = "" DATASETS = { "coco_2017_train": { "img_dir": "coco/train2017", "ann_file": "coco/annotations/instances_train2017.json" }, "coco_2017_val": { "img_dir": "coco/val2017", "ann_file": "coco/annotations/instances_val2017.json" }, # 改成训练集所在路径！！！ # 改成训练集所在路径！！！ # 改成训练集所在路径！！！ "coco_2014_train": { "img_dir": "/data1/hqj/traffic-sign-identification/trained", "ann_file": "/data1/hqj/traffic-sign-identification/trained.json" }, # 改成验证集所在路径！！！ # 改成验证集所在路径！！！ # 改成验证集所在路径！！！ "coco_2014_val": { "img_dir": "/data1/hqj/traffic-sign-identification/val", "ann_file": "/data1/hqj/traffic-sign-identification/val.json" }, # 改成测试集所在路径！！！ # 改成测试集所在路径！！！ # 改成测试集所在路径！！！ "coco_2014_test": { "img_dir": "/data1/hqj/traffic-sign-identification/test" ...- config下的配置文件：
由于这个文件下的参数很多，往往需要根据自己的具体需求改，我就列出自己的配置（使用的是e2e_faster_rcnn_X_101_32x8d_FPN_1x.yaml，其中我有注释的必须改，比如 NUM_CLASSES）：
INPUT: MIN_SIZE_TRAIN: (1000,) MAX_SIZE_TRAIN: 1667 MIN_SIZE_TEST: 1000 MAX_SIZE_TEST: 1667MODEL: META_ARCHITECTURE: "GeneralizedRCNN" WEIGHT: "catalog://ImageNetPretrained/FAIR/20171220/X-101-32x8d" BACKBONE: CONV_BODY: "R-101-FPN" RPN: USE_FPN: True BATCH_SIZE_PER_IMAGE: 128 ANCHOR_SIZES: (16, 32, 64, 128, 256) ANCHOR_STRIDE: (4, 8, 16, 32, 64) PRE_NMS_TOP_N_TRAIN: 2000 PRE_NMS_TOP_N_TEST: 1000 POST_NMS_TOP_N_TEST: 1000 FPN_POST_NMS_TOP_N_TEST: 1000 FPN_POST_NMS_TOP_N_TRAIN: 1000 ASPECT_RATIOS : (1.0,) FPN: USE_GN: True ROI_HEADS: # 是否使用FPN USE_FPN: True ROI_BOX_HEAD: USE_GN: True POOLER_RESOLUTION: 7 POOLER_SCALES: (0.25, 0.125, 0.0625, 0.03125) POOLER_SAMPLING_RATIO: 2 FEATURE_EXTRACTOR: "FPN2MLPFeatureExtractor" PREDICTOR: "FPNPredictor" # 修改成自己任务所需要检测的类别数+1 NUM_CLASSES: 22 RESNETS: BACKBONE_OUT_CHANNELS: 256 STRIDE_IN_1X1: False NUM_GROUPS: 32 WIDTH_PER_GROUP: 8DATASETS: # paths_catalog.py文件中的配置，数据集指定时如果仅有一个数据集不要忘了逗号（如：("coco_2014_val",)） TRAIN: ("coco_2014_train",) TEST: ("coco_2014_val",)DATALOADER: SIZE_DIVISIBILITY: 32SOLVER: BASE_LR: 0.001 WEIGHT_DECAY: 0.0001 STEPS: (240000, 320000) MAX_ITER: 360000 # 很重要的设置，具体可以参见官网说明：https://github.com/facebookresearch/maskrcnn-benchmark/blob/master/README.md IMS_PER_BATCH: 1 # 保存模型的间隔 CHECKPOINT_PERIOD: 18000# 输出文件路径OUTPUT_DIR: "./weight/"- 如果只做检测任务的话，删除
maskrcnn-benchmark/maskrcnn_benchmark/data/datasets/coco.py中 82-84这三行比较保险。
maskrcnn_benchmark/engine/trainer.py中 第 90 行可设置输出日志的间隔（默认20，我感觉输出太频繁，看你自己）
四、模型训练
- 单GPU
官网给出的是：
python /path_to_maskrcnn_benchmark/tools/train_net.py --config-file "/path/to/config/file.yaml"但是这个默认会使用第一个GPU，如果想指定GPU的话，可以使用以下命令：
# 3是要使用GPU的IDCUDA_VISIBLE_DEVICES=3 python /path_to_maskrcnn_benchmark/tools/train_net.py --config-file "/path/to/config/file.yaml"如果出现内存溢出的情况，这时候就需要调整参数，具体可以参见官网：内存溢出解决
- 多GPU
官网给出的是：
export NGPUS=8python -m torch.distributed.launch --nproc_per_node=$NGPUS /path_to_maskrcnn_benchmark/tools/train_net.py --config-file "path/to/config/file.yaml" MODEL.RPN.FPN_POST_NMS_TOP_N_TRAIN images_per_gpu x 1000但是这个默认会随机使用GPU，如果想指定GPU的话，可以使用以下命令：
# --nproc_per_node=4 是指使用GPU的数目为4CUDA_VISIBLE_DEVICES=0,1,2,3 python -m torch.distributed.launch --nproc_per_node=4 /path_to_maskrcnn_benchmark/tools/train_net.py --config-file "path/to/config/file.yaml"遗憾的是，多GPU在我的服务器上一直运行不成功，还请大家帮忙解决！！！
问题地址：Multi-GPU training error
五、模型验证
- 修改 config 配置文件中
WEIGHT: "../weight/model_final.pth"（此处应为训练完保存的权重） - 运行命令：
CUDA_VISIBLE_DEVICES=5 python tools/test_net.py --config-file "/path/to/config/file.yaml" TEST.IMS_PER_BATCH 8其中TEST.IMS_PER_BATCH 8也可以在config文件中直接配置：
TEST: IMS_PER_BATCH: 8六、模型预测
- 修改 config 配置文件中
WEIGHT: "../weight/model_final.pth"（此处应为训练完保存的权重） - 修改
demo/predictor.py中 CATEGORIES ，替换成自己数据的物体类别（如果想可视化结果，没有可以不改，可以参考demo/下面的例子）：
class COCODemo(object): # COCO categories for pretty print CATEGORIES = [ "__background", ... ]- 新建一个文件
demo/predict.py（需要修改的地方已做注释）
#!/usr/bin/env python# coding=UTF-8'''@Description:@Author: HuangQinJian@LastEditors: HuangQinJian@Date: 2019-05-01 12:36:04@LastEditTime: 2019-05-03 17:29:23'''import osimport matplotlib.pylab as pylabimport matplotlib.pyplot as pltimport numpy as npimport pandas as pdfrom PIL import Imagefrom maskrcnn_benchmark.config import cfgfrom predictor import COCODemofrom tqdm import tqdm# this makes our figures biggerpylab.rcParams['figure.figsize'] = 20, 12# 替换成自己的配置文件# 替换成自己的配置文件# 替换成自己的配置文件config_file = "../configs/e2e_faster_rcnn_R_50_FPN_1x.yaml"# update the config options with the config filecfg.merge_from_file(config_file)# manual override some optionscfg.merge_from_list(["MODEL.DEVICE", "cuda"])def load(img_path): pil_image = Image.open(img_path).convert("RGB") # convert to BGR format image = np.array(pil_image)[:, :, [2, 1, 0]] return image# 根据自己的需求改# 根据自己的需求改# 根据自己的需求改coco_demo = COCODemo( cfg, min_image_size=1600, confidence_threshold=0.7,)# 测试图片的路径# 测试图片的路径# 测试图片的路径imgs_dir = '/data1/hqj/traffic-sign-identification/test'img_names = os.listdir(imgs_dir)submit_v4 = pd.DataFrame()empty_v4 = pd.DataFrame()filenameList = []X1List = []X2List = []X3List = []X4List = []Y1List = []Y2List = []Y3List = []Y4List = []TypeList = []empty_img_name = []# for img_name in img_names:for i, img_name in enumerate(tqdm(img_names)): path = os.path.join(imgs_dir, img_name) image = load(path) # compute predictions predictions = coco_demo.compute_prediction(image) try: scores = predictions.get_field("scores").numpy() bbox = predictions.bbox[np.argmax(scores)].numpy() labelList = predictions.get_field("labels").numpy() label = labelList[np.argmax(scores)] filenameList.append(img_name) X1List.append(round(bbox[0])) Y1List.append(round(bbox[1])) X2List.append(round(bbox[2])) Y2List.append(round(bbox[1])) X3List.append(round(bbox[2])) Y3List.append(round(bbox[3])) X4List.append(round(bbox[0])) Y4List.append(round(bbox[3])) TypeList.append(label) # print(filenameList, X1List, X2List, X3List, X4List, Y1List, # Y2List, Y3List, Y4List, TypeList) print(label) except: empty_img_name.append(img_name) print(empty_img_name)submit_v4['filename'] = filenameListsubmit_v4['X1'] = X1Listsubmit_v4['Y1'] = Y1Listsubmit_v4['X2'] = X2Listsubmit_v4['Y2'] = Y2Listsubmit_v4['X3'] = X3Listsubmit_v4['Y3'] = Y3Listsubmit_v4['X4'] = X4Listsubmit_v4['Y4'] = Y4Listsubmit_v4['type'] = TypeListempty_v4['filename'] = empty_img_namesubmit_v4.to_csv('submit_v4.csv', index=None)empty_v4.to_csv('empty_v4.csv', index=None)- 运行命令：
CUDA_VISIBLE_DEVICES=5 python demo/predict.py七、结束语
1. 若有修改maskrcnn-benchmark文件夹下的代码，一定要重新编译！一定要重新编译！一定要重新编译！
2. 更多精彩内容，欢迎前往我的 CSDN