Spaces:
Runtime error
Runtime error
File size: 9,704 Bytes
4121bec |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 |
# Copyright (c) Facebook, Inc. and its affiliates.
import copy
import logging
import numpy as np
from typing import List, Optional, Union
import torch
from detectron2.config import configurable
from . import detection_utils as utils
from . import transforms as T
"""
This file contains the default mapping that's applied to "dataset dicts".
"""
__all__ = ["DatasetMapper"]
class DatasetMapper:
"""
A callable which takes a dataset dict in Detectron2 Dataset format,
and map it into a format used by the model.
This is the default callable to be used to map your dataset dict into training data.
You may need to follow it to implement your own one for customized logic,
such as a different way to read or transform images.
See :doc:`/tutorials/data_loading` for details.
The callable currently does the following:
1. Read the image from "file_name"
2. Applies cropping/geometric transforms to the image and annotations
3. Prepare data and annotations to Tensor and :class:`Instances`
"""
@configurable
def __init__(
self,
is_train: bool,
*,
augmentations: List[Union[T.Augmentation, T.Transform]],
image_format: str,
use_instance_mask: bool = False,
use_keypoint: bool = False,
instance_mask_format: str = "polygon",
keypoint_hflip_indices: Optional[np.ndarray] = None,
precomputed_proposal_topk: Optional[int] = None,
recompute_boxes: bool = False,
filter_open_cls: bool = False,
clip_crop: bool = False,
):
"""
NOTE: this interface is experimental.
Args:
is_train: whether it's used in 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`.
use_instance_mask: whether to process instance segmentation annotations, if available
use_keypoint: whether to process keypoint annotations if available
instance_mask_format: one of "polygon" or "bitmask". Process instance segmentation
masks into this format.
keypoint_hflip_indices: see :func:`detection_utils.create_keypoint_hflip_indices`
precomputed_proposal_topk: if given, will load pre-computed
proposals from dataset_dict and keep the top k proposals for each image.
recompute_boxes: whether to overwrite bounding box annotations
by computing tight bounding boxes from instance mask annotations.
filter_open_cls: open-set setting, filter the open-set categories during training
clip_crop: the mode that directly use CLIP on cropped image regions
"""
if recompute_boxes:
assert use_instance_mask, "recompute_boxes requires instance masks"
# fmt: off
self.is_train = is_train
self.augmentations = T.AugmentationList(augmentations)
self.image_format = image_format
self.use_instance_mask = use_instance_mask
self.instance_mask_format = instance_mask_format
self.use_keypoint = use_keypoint
self.keypoint_hflip_indices = keypoint_hflip_indices
self.proposal_topk = precomputed_proposal_topk
self.recompute_boxes = recompute_boxes
self.filter_open_cls = filter_open_cls
self.clip_crop = clip_crop
# fmt: on
logger = logging.getLogger(__name__)
mode = "training" if is_train else "inference"
logger.info(f"[DatasetMapper] Augmentations used in {mode}: {augmentations}")
@classmethod
def from_config(cls, cfg, is_train: bool = True):
augs = utils.build_augmentation(cfg, is_train)
if cfg.INPUT.CROP.ENABLED and is_train:
augs.insert(0, T.RandomCrop(cfg.INPUT.CROP.TYPE, cfg.INPUT.CROP.SIZE))
recompute_boxes = cfg.MODEL.MASK_ON
else:
recompute_boxes = False
ret = {
"is_train": is_train,
"augmentations": augs,
"image_format": cfg.INPUT.FORMAT,
"use_instance_mask": cfg.MODEL.MASK_ON,
"instance_mask_format": cfg.INPUT.MASK_FORMAT,
"use_keypoint": cfg.MODEL.KEYPOINT_ON,
"recompute_boxes": recompute_boxes,
}
if cfg.MODEL.KEYPOINT_ON:
ret["keypoint_hflip_indices"] = utils.create_keypoint_hflip_indices(cfg.DATASETS.TRAIN)
if cfg.MODEL.LOAD_PROPOSALS:
ret["precomputed_proposal_topk"] = (
cfg.DATASETS.PRECOMPUTED_PROPOSAL_TOPK_TRAIN
if is_train
else cfg.DATASETS.PRECOMPUTED_PROPOSAL_TOPK_TEST
)
# open-set setting, filter the open-set categories during training
# filter_open_cls = cfg.SOLVER.IMS_PER_BATCH < 10 # debug
# if filter_open_cls:
# ret["filter_open_cls"] = True
# CLIP inference on cropped image regions
if cfg.MODEL.META_ARCHITECTURE in ["CLIPRCNN", "CLIPFastRCNN"]:
ret["clip_crop"] = True
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
"""
dataset_dict = copy.deepcopy(dataset_dict) # it will be modified by code below
# USER: Write your own image loading if it's not from a file
image = utils.read_image(dataset_dict["file_name"], format=self.image_format)
utils.check_image_size(dataset_dict, image)
# USER: Remove if you don't do semantic/panoptic segmentation.
if "sem_seg_file_name" in dataset_dict:
sem_seg_gt = utils.read_image(dataset_dict.pop("sem_seg_file_name"), "L").squeeze(2)
else:
sem_seg_gt = None
aug_input = T.AugInput(image, sem_seg=sem_seg_gt)
transforms = self.augmentations(aug_input)
# if self.clip_crop: # load original images into CLIP model, without resizing
# pass
# else:
image, sem_seg_gt = aug_input.image, aug_input.sem_seg
image_shape = image.shape[:2] # 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"] = torch.as_tensor(np.ascontiguousarray(image.transpose(2, 0, 1)))
if sem_seg_gt is not None:
dataset_dict["sem_seg"] = torch.as_tensor(sem_seg_gt.astype("long"))
# USER: Remove if you don't use pre-computed proposals.
# Most users would not need this feature.
if self.proposal_topk is not None:
utils.transform_proposals(
dataset_dict, image_shape, transforms, proposal_topk=self.proposal_topk
)
if not self.is_train:
if self.clip_crop: # still load the GT annotations
pass
else:
# USER: Modify this if you want to keep them for some reason.
dataset_dict.pop("annotations", None)
dataset_dict.pop("sem_seg_file_name", None)
return dataset_dict
if "annotations" in dataset_dict:
# if self.filter_open_cls: # filter categories for open-set training
# obj_annos = dataset_dict['annotations']
# clean_obj_annos = [obj_anno for obj_anno in obj_annos if obj_anno['frequency'] != 'r'] # filter rare classes
# if len(clean_obj_annos) == 0: # empty annotation
# print("\n\nImage {} has no annotation after filtering open-set classes!\n\n".format(dataset_dict['image_id']))
# clean_obj_annos = obj_annos[0] # keep one for compatability, fix it later
# dataset_dict['annotations'] = clean_obj_annos
# USER: Modify this if you want to keep them for some reason.
for anno in dataset_dict["annotations"]:
if not self.use_instance_mask:
anno.pop("segmentation", None)
if not self.use_keypoint:
anno.pop("keypoints", None)
# USER: Implement additional transformations if you have other types of data
annos = [
utils.transform_instance_annotations(
obj, transforms, image_shape, keypoint_hflip_indices=self.keypoint_hflip_indices
)
for obj in dataset_dict.pop("annotations")
if obj.get("iscrowd", 0) == 0
]
instances = utils.annotations_to_instances(
annos, image_shape, mask_format=self.instance_mask_format
)
# After transforms such as cropping are applied, the bounding box may no longer
# tightly bound the object. As an example, imagine a triangle object
# [(0,0), (2,0), (0,2)] cropped by a box [(1,0),(2,2)] (XYXY format). The tight
# bounding box of the cropped triangle should be [(1,0),(2,1)], which is not equal to
# the intersection of original bounding box and the cropping box.
if self.recompute_boxes:
instances.gt_boxes = instances.gt_masks.get_bounding_boxes()
dataset_dict["instances"] = utils.filter_empty_instances(instances)
return dataset_dict
|