def __getitem__(self, index: int):
"""See superclass for documentation
Notes
-----
The return value is a dict with the following fields:
image_id: int
The index of the image in the split
image_path: str
The path to the image on the file system
category_id : int
The single label of the image selected
"""
img = load_pil_image(self.images_path[index])
if self.transform is not None:
img = self.transform(img)
target = self.parse_json(index)
annotations = target.pop("annotations")
tags = [
self.classes.index(a["name"]) for a in annotations if "tag" in a
]
if len(tags) > 1:
raise ValueError(
f"Multiple tags defined for this image ({tags}). This is not supported at the moment."
)
if len(tags) == 0:
raise ValueError(
f"No tags defined for this image ({self.annotations_path[index]})."
f"This is not valid in a classification dataset.")
target["category_id"] = tags[0]
return img, target
def _return_std(image_path, mean):
img = np.array(load_pil_image(image_path)) / 255.0
m2 = np.square(
np.array([
img[:, :, 0] - mean[0], img[:, :, 1] - mean[1],
img[:, :, 2] - mean[2]
]))
return np.sum(np.sum(m2, axis=1), 1), m2.size / 3.0
def _return_mean(image_path):
img = np.array(load_pil_image(image_path))
mean = np.array([
np.mean(img[:, :, 0]),
np.mean(img[:, :, 1]),
np.mean(img[:, :, 2])
])
return mean / 255.0
def __getitem__(self, index: int):
"""See superclass for documentation
Notes
-----
The return value is a dict with the following fields:
image_id : int
Index of the image inside the dataset
image_path: str
The path to the image on the file system
mask : tensor(H, W)
Segmentation mask where each pixel encodes a class label
"""
img = load_pil_image(self.images_path[index])
target = self.parse_json(index)
annotations = []
for obj in target["annotations"]:
sequences = convert_polygons_to_sequences(
obj["polygon"]["path"],
height=target["height"],
width=target["width"],
)
# Discard polygons with less than three points
sequences[:] = [s for s in sequences if len(s) >= 6]
if not sequences:
continue
annotations.append({
"category_id": self.classes.index(obj["name"]),
"segmentation": sequences
})
target["annotations"] = annotations
img, target = self.convert_polygons(img, target)
if self.transform is not None:
img, target = self.transform(img, target)
return img, target
def __getitem__(self, index: int):
img = load_pil_image(self.images_path[index])
target = self.parse_json(index)
return img, target
def get_image(self, index: int):
return load_pil_image(self.images_path[index])
def get_image(self, index: int) -> PILImage.Image:
return load_pil_image(self.images_path[index])
def __getitem__(self, index: int):
"""
Notes
-----
The return value is a dict with the following fields:
image_id : int
Index of the image inside the dataset
image_path: str
The path to the image on the file system
labels : tensor(n)
The class label of each one of the instances
masks : tensor(n, H, W)
Segmentation mask of each one of the instances
boxes : tensor(n, 4)
Coordinates of the bounding box enclosing the instances as [x, y, x, y]
area : float
Area in pixels of each one of the instances
"""
img = load_pil_image(self.images_path[index])
target = self.parse_json(index)
annotations = []
for annotation in target["annotations"]:
if "polygon" not in annotation and "complex_polygon" not in annotation:
print(
f"Warning: missing polygon in annotation {self.annotations_path[index]}"
)
# Extract the sequences of coordinates from the polygon annotation
annotation_type = "polygon" if "polygon" in annotation else "complex_polygon"
sequences = convert_polygons_to_sequences(
annotation[annotation_type]["path"],
height=target["height"],
width=target["width"],
)
# Compute the bbox of the polygon
x_coords = [s[0::2] for s in sequences]
y_coords = [s[1::2] for s in sequences]
min_x = np.min([np.min(x_coord) for x_coord in x_coords])
min_y = np.min([np.min(y_coord) for y_coord in y_coords])
max_x = np.max([np.max(x_coord) for x_coord in x_coords])
max_y = np.max([np.max(y_coord) for y_coord in y_coords])
w = max_x - min_x + 1
h = max_y - min_y + 1
# Compute the area of the polygon
# TODO fix with addictive/subtractive paths in complex polygons
poly_area = np.sum([
polygon_area(x_coord, y_coord)
for x_coord, y_coord in zip(x_coords, y_coords)
])
# Create and append the new entry for this annotation
annotations.append({
"category_id":
self.classes.index(annotation["name"]),
"segmentation":
sequences,
"bbox": [min_x, min_y, w, h],
"area":
poly_area,
})
target["annotations"] = annotations
img, target = self.convert_polygons(img, target)
if self.transform is not None:
img, target = self.transform(img, target)
return img, target