我正在尝试制作一个程序，可以使跑道和滑行道之间的分类使用掩码rcnn。在json格式导入自定义数据集后，我得到键错误
class CustomDataset(utils.Dataset):
def load_custom(self, dataset_dir, subset):
"""Load a subset of the Horse-Man dataset.
dataset_dir: Root directory of the dataset.
subset: Subset to load: train or val
"""
# Add classes. We have only one class to add.
self.add_class("object", 1, "runway")
self.add_class("object", 2, "taxiway")
# self.add_class("object", 3, "xyz") #likewise
# Train or validation dataset?
assert subset in ["trainn", "vall"]
dataset_dir = os.path.join(dataset_dir, subset)
# Load annotations
# VGG Image Annotator saves each image in the form:
# { 'filename': '28503151_5b5b7ec140_b.jpg',
# 'regions': {
# '0': {
# 'region_attributes': {},
# 'shape_attributes': {
# 'all_points_x': [...],
# 'all_points_y': [...],
# 'name': 'polygon'}},
# ... more regions ...
# },
# 'size': 100202
# }
# We mostly care about the x and y coordinates of each region
annotations1 = json.load(open(os.path.join(dataset_dir, "f11_json.json")))
# print(annotations1)
annotations = list(annotations1.values()) # don't need the dict keys
# The VIA tool saves images in the JSON even if they don't have any
# annotations. Skip unannotated images.
annotations = [a for a in annotations if a['regions']]
# Add images
for a in annotations:
# print(a)
# Get the x, y coordinaets of points of the polygons that make up
# the outline of each object instance. There are stores in the
# shape_attributes (see json format above)
polygons = [r['shape_attributes'] for r in a['regions']]
objects = [s['region_attributes']['names'] for s in a['regions']]
print("objects:",objects)
name_dict = {"runway": 1,"taxiway": 2} #,"xyz": 3}
# key = tuple(name_dict)
num_ids = [name_dict[a] for a in objects]
# num_ids = [int(n['Event']) for n in objects]
# load_mask() needs the image size to convert polygons to masks.
# Unfortunately, VIA doesn't include it in JSON, so we must read
# the image. This is only managable since the dataset is tiny.
print("numids",num_ids)
image_path = os.path.join(dataset_dir, a['filename'])
image = skimage.io.imread(image_path)
height, width = image.shape[:2]
self.add_image(
"object", ## for a single class just add the name here
image_id=a['filename'], # use file name as a unique image id
path=image_path,
width=width, height=height,
polygons=polygons,
num_ids=num_ids
)
def load_mask(self, image_id):
"""Generate instance masks for an image.
Returns:
masks: A bool array of shape [height, width, instance count] with
one mask per instance.
class_ids: a 1D array of class IDs of the instance masks.
"""
# If not a Horse/Man dataset image, delegate to parent class.
image_info = self.image_info[image_id]
if image_info["source"] != "object":
return super(self.__class__, self).load_mask(image_id)
# Convert polygons to a bitmap mask of shape
# [height, width, instance_count]
info = self.image_info[image_id]
if info["source"] != "object":
return super(self.__class__, self).load_mask(image_id)
num_ids = info['num_ids']
mask = np.zeros([info["height"], info["width"], len(info["polygons"])],
dtype=np.uint8)
for i, p in enumerate(info["polygons"]):
# Get indexes of pixels inside the polygon and set them to 1
rr, cc = skimage.draw.polygon(p['all_points_y'], p['all_points_x'])
mask[rr, cc, i] = 1
# Return mask, and array of class IDs of each instance. Since we have
# one class ID only, we return an array of 1s
# Map class names to class IDs.
num_ids = np.array(num_ids, dtype=np.int32)
return mask, num_ids #np.ones([mask.shape[-1]], dtype=np.int32)
def image_reference(self, image_id):
"""Return the path of the image."""
info = self.image_info[image_id]
if info["source"] == "object":
return info["path"]
else:
super(self.__class__, self).image_reference(image_id)
误差
objects: ['runway', 'runway', 'taxiway', 'taxiway', 'taxiway',
'taxiway', 'taxiway']
numids [1, 1, 2, 2, 2, 2, 2]
objects: ['runway', 'runway', 'taxiway', 'taxiway']
numids [1, 1, 2, 2]
error
<ipython-input-8-fac8e3d87b86> in <listcomp>(.0)
45 # shape_attributes (see json format above)
46 polygons = [r['shape_attributes'] for r in a['regions']]
---> 47 objects = [s['region_attributes']['names'] for s in a['regions']]
48 print("objects:",objects)
49 name_dict = {"runway": 1,"taxiway": 2} #,"xyz": 3}
KeyError: 'names'
我所做的所有可能的变化,但仍得到同样的错误。基本上我是在自定义数据集上做图像分类在这个我导入了自定义数据集的json文件。
根据评论中的文件格式，我认为应该是name，而不是names:
{ 'filename': '28503151_5b5b7ec140_b.jpg',
'regions': {
'0': {
'region_attributes': {},
'shape_attributes': {
'all_points_x': [...],
'all_points_y': [...],
'name': 'polygon'}},
... more regions ...
},
'size': 100202
}
'name': 'polygon'}},
我通过重新检查我在VGG工具中的注释来解决这个错误，发现我双标记(错误标记)了两个文件。
所以我的建议是重新检查VGG注释工具中的所有文件，并检查丢失或多次标记的文件。
感谢