使用Mask RCNN训练自定义数据集时遇[WinError 123]路径语法错误

我是Python新手，在Conda环境的Jupyter Notebook里用mask-rcnn-tf2做车辆目标检测，训练自定义数据集时每次都触发路径语法错误，卡在这了。

我的代码 #

from mrcnn.utils import Dataset
from mrcnn.visualize import display_instances
from mrcnn.utils import extract_bboxes
from mrcnn.config import Config
from mrcnn.model import MaskRCNN
 # class that defines and loads the kangaroo dataset
class Contest(Dataset):
    # load the dataset definitions
    def load_dataset(self, dataset_csv,image_dir, is_train=True):
        # define one class
        self.add_class("dataset", 1, "Car")
        # define data locations
        images_dir = image_dir + 'train_images/'
        # annotations_dir = dataset_dir + '/annots/'
        # find all images
        #for filename in os.listdir(images_dir):
        for id, filename in zip(id_s,img):
            # extract image id
            #print(i)
            image_id = id
            # skip bad images
            #if image_id in ["100"]:
                #continue
            # skip all images after 150 if we are building the train set
            if is_train and int(image_id) >= 5000:
                continue
            # skip all images before 150 if we are building the test/val set
            if not is_train and int(image_id) >= 4000:
                continue
            img_path = images_dir + filename
            if os.path.isfile(img_path) == False:
                continue
            # if im.size == 0:
            #   continue
            # ann_path = annotations_dir + image_id + '.xml'
            # add to dataset
            self.add_image('dataset', image_id=image_id, path=img_path)
 
    def extract_boxes(self,dataset_csv,image_id): #For getting all the bbox category ids and width and height of the image on the bases of image id
  # box = np.array([])
        info = self.image_info[image_id]
        box = list()
        # bbox = data[data['image_id']==image_id]['bbox']
        for i in range(len(b_mat)):
            if b_mat[i][2] == 1 and b_mat[i][1] == info['id']:     
                # print(b_mat[i][0])
                bbox = b_mat[i][0]
                box.append(bbox)
        wid = data[data['image_id']==image_id]['width'].unique()[0]
        hei = data[data['image_id']==image_id]['height'].unique()[0]
        return box  , wid ,hei

    # load the masks for an image
    def load_mask(self, image_id):
        # get details of image
        info = self.image_info[image_id]
        #print(info[0])
        # define box file location
        #path = info['annotation']
        # load XML
        boxes, w, h = self.extract_boxes(data,image_id)
        # create one array for all masks, each on a different channel
        masks = zeros([h, w, len(boxes)], dtype='uint8')
        # create masks
        class_ids = list()
        for i in range(len(boxes)):
            box = boxes[i]
            row_s, col_s = box[0], box[1]
            row_e, col_e = box[0]+box[2], box[1]+box[3]
            #print(i)
            #masks[row_e-row_s:col_e-col_s,col_s-col_e:row_s-row_e,i] = 1
            #masks[row_s:row_e,col_s:col_e,i] = 1
            masks[col_s:col_e, row_s:row_e,i] = 1
            #masks[col_s:row_s, col_e:row_e,i] = 1
            #print(row_s,row_e ,col_s,col_e,info,image_id)
            #print(row_s,row_e, col_s,col_e)
            #print(box[0], box[1], box[2], box[3],info['id'])
            class_ids.append(self.class_names.index('Car'))
        return masks, asarray(class_ids, dtype='int32')
 
    # load an image reference
    def image_reference(self, image_id):
        info = self.image_info[image_id]
        return info['path']
    # define a configuration for the model
class CarConfig(Config):
    # define the name of the configuration
    NAME = "Contest_cfg"
    # number of classes (background + kangaroo)
    NUM_CLASSES = 1 + 1
    # number of training steps per epoch
    STEPS_PER_EPOCH = 200
# train set
image_dir = 'G:/My Drive/train_images/'
train_set = Contest()
train_set.load_dataset(data,image_dir,is_train=True)
train_set.prepare()
print('Train: %d' % len(train_set.image_ids))
test_set = Contest()
test_set.load_dataset(data,image_dir, is_train=False)
test_set.prepare()
print('Test: %d' % len(test_set.image_ids))
# image_id = 1
# # load the image
# image = train_set.load_image(image_id)
# # load the masks and the class ids
# mask, class_ids = train_set.load_mask(image_id)
# # extract bounding boxes from the masks
# bbox = extract_bboxes(mask)
# # display image with masks and bounding boxes
# display_instances(image, bbox, mask, class_ids, train_set.class_names)
#prepare config
config = CarConfig()
config.display()
# define the model
model = MaskRCNN(mode='training', model_dir=r"D:/", config=config)
# load weights (mscoco) and exclude the output layers
model.load_weights(r"D:/Najam/mask_rcnn_coco.h5", by_name=True, exclude=["mrcnn_class_logits", "mrcnn_bbox_fc",  "mrcnn_bbox", "mrcnn_mask"])
# train weights (output layers or 'heads')
model.train(train_set,test_set, learning_rate=config.LEARNING_RATE, epochs=3, layers='head')

报错信息 #

OSError                                   Traceback (most recent call last)
<ipython-input-25-c0b9708402b6> in <module>
    118 model.load_weights(r"D:/Najam/mask_rcnn_coco.h5", by_name=True, exclude=["mrcnn_class_logits", "mrcnn_bbox_fc",  "mrcnn_bbox", "mrcnn_mask"])
    119 # train weights (output layers or 'heads')
--> 120 model.train(train_set,test_set, learning_rate=config.LEARNING_RATE, epochs=3, layers='head')

D:\Najam\matterport\mrcnn\model.py in train(self, train_dataset, val_dataset, learning_rate, epochs, layers, augmentation, custom_callbacks, no_augmentation_sources)
   2345                                        batch_size=self.config.BATCH_SIZE)
   2346 
--> 2347         # Create log_dir if it does not exist
   2348         if not os.path.exists(self.log_dir):
   2349             print(self.log_dir)

~\anaconda3\envs\myenv\lib\os.py in makedirs(name, mode, exist_ok)
    208     if head and tail and not path.exists(head):
    209         try:
--> 210             makedirs(head, mode, exist_ok)
    211         except FileExistsError:
    212             # Defeats race condition when another thread created the path

~\anaconda3\envs\myenv\lib\os.py in makedirs(name, mode, exist_ok)
    208     if head and tail and not path.exists(head):
    209         try:
--> 210             makedirs(head, mode, exist_ok)
    211         except FileExistsError:
    212             # Defeats race condition when another thread created the path

~\anaconda3\envs\myenv\lib\os.py in makedirs(name, mode, exist_ok)
    218             return
    219     try:
--> 220         mkdir(name, mode)
    221     except OSError:
    222         # Cannot rely on checking for EEXIST, since the operating system

OSError: [WinError 123] The filename, directory name, or volume label syntax is incorrect: '//'

核心问题修复 #

错误的直接原因是初始化MaskRCNN时指定的model_dir=r"D:/"有问题。Windows系统下，单独的磁盘根路径D:/会导致MaskRCNN内部生成日志目录时解析出无效的//路径，触发WinError 123。

修改方式很简单，把model_dir改成具体的子目录（确保目录存在，或者让代码能创建它）：

model = MaskRCNN(mode='training', model_dir=r"D:/MaskRCNN_Train_Logs/", config=config)

额外路径优化建议 #

1. 避免字符串拼接路径：别用images_dir = image_dir + 'train_images/'这种方式，改用os.path.join()，跨系统兼容性更好：

   import os
   images_dir = os.path.join(image_dir, 'train_images')
   

2. 处理带空格的路径：你的image_dir = 'G:/My Drive/train_images/'包含空格，虽然Windows支持，但用os.path.join或者原始字符串（r"..."）能避免潜在问题。

内容的提问来源于stack exchange，提问作者najam iqbal