File size: 6,700 Bytes
bdec3d7 |
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 |
# Copyright (c) Facebook, Inc. and its affiliates.
import copy
import logging
import numpy as np
import pycocotools.mask as mask_util
import torch
from torch.nn import functional as F
from detectron2.data import detection_utils as utils
from detectron2.data import transforms as T
from detectron2.projects.point_rend import ColorAugSSDTransform
from detectron2.structures import BitMasks, Instances, polygons_to_bitmask
from modeling.utils import configurable
__all__ = ["MaskFormerInstanceDatasetMapper"]
class MaskFormerInstanceDatasetMapper:
"""
A callable which takes a dataset dict in Detectron2 Dataset format,
and map it into a format used by MaskFormer for instance segmentation.
The callable currently does the following:
1. Read the image from "file_name"
2. Applies geometric transforms to the image and annotation
3. Find and applies suitable cropping to the image and annotation
4. Prepare image and annotation to Tensors
"""
@configurable
def __init__(
self,
is_train=True,
*,
augmentations,
image_format,
size_divisibility,
):
"""
NOTE: this interface is experimental.
Args:
is_train: for training or inference
augmentations: a list of augmentations or deterministic transforms to apply
image_format: an image format supported by :func:`detection_utils.read_image`.
size_divisibility: pad image size to be divisible by this value
"""
self.is_train = is_train
self.tfm_gens = augmentations
self.img_format = image_format
self.size_divisibility = size_divisibility
logger = logging.getLogger(__name__)
mode = "training" if is_train else "inference"
logger.info(f"[{self.__class__.__name__}] Augmentations used in {mode}: {augmentations}")
@classmethod
def from_config(cls, cfg, is_train=True):
# Build augmentation
cfg_input = cfg['INPUT']
augs = [
T.ResizeShortestEdge(
cfg_input['MIN_SIZE_TRAIN'],
cfg_input['MAX_SIZE_TRAIN'],
cfg_input['MIN_SIZE_TRAIN_SAMPLING'],
)
]
cfg_input_crop = cfg_input['CROP']
if cfg_input_crop['ENABLED']:
augs.append(
T.RandomCrop(
cfg_input_crop['TYPE'],
cfg_input_crop['SIZE'],
)
)
if cfg_input['COLOR_AUG_SSD']:
augs.append(ColorAugSSDTransform(img_format=cfg_input['FORMAT']))
augs.append(T.RandomFlip())
ret = {
"is_train": is_train,
"augmentations": augs,
"image_format": cfg_input['FORMAT'],
"size_divisibility": cfg_input['SIZE_DIVISIBILITY'],
}
return ret
def __call__(self, dataset_dict):
"""
Args:
dataset_dict (dict): Metadata of one image, in Detectron2 Dataset format.
Returns:
dict: a format that builtin models in detectron2 accept
"""
assert self.is_train, "MaskFormerPanopticDatasetMapper should only be used for training!"
dataset_dict = copy.deepcopy(dataset_dict) # it will be modified by code below
image = utils.read_image(dataset_dict["file_name"], format=self.img_format)
utils.check_image_size(dataset_dict, image)
aug_input = T.AugInput(image)
aug_input, transforms = T.apply_transform_gens(self.tfm_gens, aug_input)
image = aug_input.image
# transform instnace masks
assert "annotations" in dataset_dict
for anno in dataset_dict["annotations"]:
anno.pop("keypoints", None)
annos = [
utils.transform_instance_annotations(obj, transforms, image.shape[:2])
for obj in dataset_dict.pop("annotations")
if obj.get("iscrowd", 0) == 0
]
if len(annos):
assert "segmentation" in annos[0]
segms = [obj["segmentation"] for obj in annos]
masks = []
for segm in segms:
if isinstance(segm, list):
# polygon
masks.append(polygons_to_bitmask(segm, *image.shape[:2]))
elif isinstance(segm, dict):
# COCO RLE
masks.append(mask_util.decode(segm))
elif isinstance(segm, np.ndarray):
assert segm.ndim == 2, "Expect segmentation of 2 dimensions, got {}.".format(
segm.ndim
)
# mask array
masks.append(segm)
else:
raise ValueError(
"Cannot convert segmentation of type '{}' to BitMasks!"
"Supported types are: polygons as list[list[float] or ndarray],"
" COCO-style RLE as a dict, or a binary segmentation mask "
" in a 2D numpy array of shape HxW.".format(type(segm))
)
# Pad image and segmentation label here!
image = torch.as_tensor(np.ascontiguousarray(image.transpose(2, 0, 1)))
masks = [torch.from_numpy(np.ascontiguousarray(x)) for x in masks]
classes = [int(obj["category_id"]) for obj in annos]
classes = torch.tensor(classes, dtype=torch.int64)
if self.size_divisibility > 0:
image_size = (image.shape[-2], image.shape[-1])
padding_size = [
0,
self.size_divisibility - image_size[1],
0,
self.size_divisibility - image_size[0],
]
# pad image
image = F.pad(image, padding_size, value=128).contiguous()
# pad mask
masks = [F.pad(x, padding_size, value=0).contiguous() for x in masks]
image_shape = (image.shape[-2], image.shape[-1]) # h, w
# Pytorch's dataloader is efficient on torch.Tensor due to shared-memory,
# but not efficient on large generic data structures due to the use of pickle & mp.Queue.
# Therefore it's important to use torch.Tensor.
dataset_dict["image"] = image
# Prepare per-category binary masks
instances = Instances(image_shape)
instances.gt_classes = classes
if len(masks) == 0:
# Some image does not have annotation (all ignored)
instances.gt_masks = torch.zeros((0, image.shape[-2], image.shape[-1]))
else:
masks = BitMasks(torch.stack(masks))
instances.gt_masks = masks.tensor
dataset_dict["instances"] = instances
return dataset_dict
|