File size: 3,723 Bytes
a277bb8 |
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 |
# Copyright (c) Facebook, Inc. and its affiliates. All Rights Reserved
import json
from pathlib import Path
import numpy as np
import torch
from PIL import Image
from panopticapi.utils import rgb2id
from util.box_ops import masks_to_boxes
from .coco import make_coco_transforms
class CocoPanoptic:
def __init__(self, img_folder, ann_folder, ann_file, transforms=None, return_masks=True):
with open(ann_file, 'r') as f:
self.coco = json.load(f)
# sort 'images' field so that they are aligned with 'annotations'
# i.e., in alphabetical order
self.coco['images'] = sorted(self.coco['images'], key=lambda x: x['id'])
# sanity check
if "annotations" in self.coco:
for img, ann in zip(self.coco['images'], self.coco['annotations']):
assert img['file_name'][:-4] == ann['file_name'][:-4]
self.img_folder = img_folder
self.ann_folder = ann_folder
self.ann_file = ann_file
self.transforms = transforms
self.return_masks = return_masks
def __getitem__(self, idx):
ann_info = self.coco['annotations'][idx] if "annotations" in self.coco else self.coco['images'][idx]
img_path = Path(self.img_folder) / ann_info['file_name'].replace('.png', '.jpg')
ann_path = Path(self.ann_folder) / ann_info['file_name']
img = Image.open(img_path).convert('RGB')
w, h = img.size
if "segments_info" in ann_info:
masks = np.asarray(Image.open(ann_path), dtype=np.uint32)
masks = rgb2id(masks)
ids = np.array([ann['id'] for ann in ann_info['segments_info']])
masks = masks == ids[:, None, None]
masks = torch.as_tensor(masks, dtype=torch.uint8)
labels = torch.tensor([ann['category_id'] for ann in ann_info['segments_info']], dtype=torch.int64)
target = {}
target['image_id'] = torch.tensor([ann_info['image_id'] if "image_id" in ann_info else ann_info["id"]])
if self.return_masks:
target['masks'] = masks
target['labels'] = labels
target["boxes"] = masks_to_boxes(masks)
target['size'] = torch.as_tensor([int(h), int(w)])
target['orig_size'] = torch.as_tensor([int(h), int(w)])
if "segments_info" in ann_info:
for name in ['iscrowd', 'area']:
target[name] = torch.tensor([ann[name] for ann in ann_info['segments_info']])
if self.transforms is not None:
img, target = self.transforms(img, target)
return img, target
def __len__(self):
return len(self.coco['images'])
def get_height_and_width(self, idx):
img_info = self.coco['images'][idx]
height = img_info['height']
width = img_info['width']
return height, width
def build(image_set, args):
img_folder_root = Path(args.coco_path)
ann_folder_root = Path(args.coco_panoptic_path)
assert img_folder_root.exists(), f'provided COCO path {img_folder_root} does not exist'
assert ann_folder_root.exists(), f'provided COCO path {ann_folder_root} does not exist'
mode = 'panoptic'
PATHS = {
"train": ("train2017", Path("annotations") / f'{mode}_train2017.json'),
"val": ("val2017", Path("annotations") / f'{mode}_val2017.json'),
}
img_folder, ann_file = PATHS[image_set]
img_folder_path = img_folder_root / img_folder
ann_folder = ann_folder_root / f'{mode}_{img_folder}'
ann_file = ann_folder_root / ann_file
dataset = CocoPanoptic(img_folder_path, ann_folder, ann_file,
transforms=make_coco_transforms(image_set), return_masks=args.masks)
return dataset
|