File size: 6,442 Bytes
e8861c0 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 |
import os
import torch
import torch.utils.data
import torchvision
from pycocotools import mask as coco_mask
from pycocotools.coco import COCO
def convert_coco_poly_to_mask(segmentations, height, width):
masks = []
for polygons in segmentations:
rles = coco_mask.frPyObjects(polygons, height, width)
mask = coco_mask.decode(rles)
if len(mask.shape) < 3:
mask = mask[..., None]
mask = torch.as_tensor(mask, dtype=torch.uint8)
mask = mask.any(dim=2)
masks.append(mask)
if masks:
masks = torch.stack(masks, dim=0)
else:
masks = torch.zeros((0, height, width), dtype=torch.uint8)
return masks
class ConvertCocoPolysToMask:
def __call__(self, image, target):
w, h = image.size
image_id = target["image_id"]
anno = target["annotations"]
anno = [obj for obj in anno if obj["iscrowd"] == 0]
boxes = [obj["bbox"] for obj in anno]
# guard against no boxes via resizing
boxes = torch.as_tensor(boxes, dtype=torch.float32).reshape(-1, 4)
boxes[:, 2:] += boxes[:, :2]
boxes[:, 0::2].clamp_(min=0, max=w)
boxes[:, 1::2].clamp_(min=0, max=h)
classes = [obj["category_id"] for obj in anno]
classes = torch.tensor(classes, dtype=torch.int64)
segmentations = [obj["segmentation"] for obj in anno]
masks = convert_coco_poly_to_mask(segmentations, h, w)
keypoints = None
if anno and "keypoints" in anno[0]:
keypoints = [obj["keypoints"] for obj in anno]
keypoints = torch.as_tensor(keypoints, dtype=torch.float32)
num_keypoints = keypoints.shape[0]
if num_keypoints:
keypoints = keypoints.view(num_keypoints, -1, 3)
keep = (boxes[:, 3] > boxes[:, 1]) & (boxes[:, 2] > boxes[:, 0])
boxes = boxes[keep]
classes = classes[keep]
masks = masks[keep]
if keypoints is not None:
keypoints = keypoints[keep]
target = {}
target["boxes"] = boxes
target["labels"] = classes
target["masks"] = masks
target["image_id"] = image_id
if keypoints is not None:
target["keypoints"] = keypoints
# for conversion to coco api
area = torch.tensor([obj["area"] for obj in anno])
iscrowd = torch.tensor([obj["iscrowd"] for obj in anno])
target["area"] = area
target["iscrowd"] = iscrowd
return image, target
def _coco_remove_images_without_annotations(dataset, cat_list=None):
def _has_only_empty_bbox(anno):
return all(any(o <= 1 for o in obj["bbox"][2:]) for obj in anno)
def _count_visible_keypoints(anno):
return sum(sum(1 for v in ann["keypoints"][2::3] if v > 0) for ann in anno)
min_keypoints_per_image = 10
def _has_valid_annotation(anno):
# if it's empty, there is no annotation
if len(anno) == 0:
return False
# if all boxes have close to zero area, there is no annotation
if _has_only_empty_bbox(anno):
return False
# keypoints task have a slight different criteria for considering
# if an annotation is valid
if "keypoints" not in anno[0]:
return True
# for keypoint detection tasks, only consider valid images those
# containing at least min_keypoints_per_image
if _count_visible_keypoints(anno) >= min_keypoints_per_image:
return True
return False
ids = []
for ds_idx, img_id in enumerate(dataset.ids):
ann_ids = dataset.coco.getAnnIds(imgIds=img_id, iscrowd=None)
anno = dataset.coco.loadAnns(ann_ids)
if cat_list:
anno = [obj for obj in anno if obj["category_id"] in cat_list]
if _has_valid_annotation(anno):
ids.append(ds_idx)
dataset = torch.utils.data.Subset(dataset, ids)
return dataset
def convert_to_coco_api(ds):
coco_ds = COCO()
# annotation IDs need to start at 1, not 0, see torchvision issue #1530
ann_id = 1
dataset = {"images": [], "categories": [], "annotations": []}
categories = set()
for img_idx in range(len(ds)):
# find better way to get target
# targets = ds.get_annotations(img_idx)
img, targets = ds[img_idx]
image_id = targets["image_id"].item()
img_dict = {}
img_dict["id"] = image_id
img_dict["height"] = img.shape[-2]
img_dict["width"] = img.shape[-1]
dataset["images"].append(img_dict)
bboxes = targets["boxes"].clone()
bboxes[:, 2:] -= bboxes[:, :2]
bboxes = bboxes.tolist()
labels = targets["labels"].tolist()
areas = targets["area"].tolist()
iscrowd = targets["iscrowd"].tolist()
if "masks" in targets:
masks = targets["masks"]
# make masks Fortran contiguous for coco_mask
masks = masks.permute(0, 2, 1).contiguous().permute(0, 2, 1)
if "keypoints" in targets:
keypoints = targets["keypoints"]
keypoints = keypoints.reshape(keypoints.shape[0], -1).tolist()
num_objs = len(bboxes)
for i in range(num_objs):
ann = {}
ann["image_id"] = image_id
ann["bbox"] = bboxes[i]
ann["category_id"] = labels[i]
categories.add(labels[i])
ann["area"] = areas[i]
ann["iscrowd"] = iscrowd[i]
ann["id"] = ann_id
if "masks" in targets:
ann["segmentation"] = coco_mask.encode(masks[i].numpy())
if "keypoints" in targets:
ann["keypoints"] = keypoints[i]
ann["num_keypoints"] = sum(k != 0 for k in keypoints[i][2::3])
dataset["annotations"].append(ann)
ann_id += 1
dataset["categories"] = [{"id": i} for i in sorted(categories)]
coco_ds.dataset = dataset
coco_ds.createIndex()
return coco_ds
def get_coco_api_from_dataset(dataset):
# FIXME: This is... awful?
for _ in range(10):
if isinstance(dataset, torchvision.datasets.CocoDetection):
break
if isinstance(dataset, torch.utils.data.Subset):
dataset = dataset.dataset
if isinstance(dataset, torchvision.datasets.CocoDetection):
return dataset.coco
return convert_to_coco_api(dataset)
|