def draw_dataset_dict(self, dic): """ Draw annotations in Detectron2 Dataset format. Args: dic (dict): annotation data of one image, in Detectron2 Dataset format. Returns: output (VisImage): image object with visualizations. """ annos = dic.get("annotations", None) if annos: boxes = [ BoxMode.convert(x["bbox"], x["bbox_mode"], BoxMode.XYXY_ABS) for x in annos ] labels = [x["category_id"] for x in annos] names = self.metadata.get("thing_classes", None) if names: labels = [names[i] for i in labels] labels = [ "{}".format(i) + ("|crowd" if a.get("iscrowd", 0) else "") for i, a in zip(labels, annos) ] self.overlay_instances(labels=labels, boxes=boxes) return self.output
def instances_to_coco_json(instances, img_id): """ Dump an "Instances" object to a COCO-format json that's used for evaluation. Args: instances (Instances): img_id (int): the image id Returns: list[dict]: list of json annotations in COCO format. """ num_instance = len(instances) if num_instance == 0: return [] boxes = instances.pred_boxes.tensor.numpy() boxes = BoxMode.convert(boxes, BoxMode.XYXY_ABS, BoxMode.XYWH_ABS) boxes = boxes.tolist() scores = instances.scores.tolist() classes = instances.pred_classes.tolist() results = [] for k in range(num_instance): result = { "image_id": img_id, "category_id": classes[k], "bbox": boxes[k], "score": scores[k], } results.append(result) return results
def annotations_to_instances(annos, image_size): """ Create an :class:`Instances` object used by the models, from instance annotations in the dataset dict. Args: annos (list[dict]): a list of instance annotations in one image, each element for one instance. image_size (tuple): height, width Returns: Instances: It will contain fields "gt_boxes", "gt_classes", if they can be obtained from `annos`. This is the format that builtin models expect. """ boxes = [ BoxMode.convert(obj["bbox"], obj["bbox_mode"], BoxMode.XYXY_ABS) for obj in annos ] target = Instances(image_size) boxes = target.gt_boxes = Boxes(boxes) boxes.clip(image_size) classes = [obj["category_id"] for obj in annos] classes = torch.tensor(classes, dtype=torch.int64) target.gt_classes = classes return target
def create_instances(predictions, image_size): ret = Instances(image_size) score = np.asarray([x["score"] for x in predictions]) chosen = (score > args.conf_threshold).nonzero()[0] score = score[chosen] bbox = np.asarray([predictions[i]["bbox"] for i in chosen]) bbox = BoxMode.convert(bbox, BoxMode.XYWH_ABS, BoxMode.XYXY_ABS) labels = np.asarray( [dataset_id_map(predictions[i]["category_id"]) for i in chosen]) ret.scores = score ret.pred_boxes = Boxes(bbox) ret.pred_classes = labels try: ret.pred_masks = [predictions[i]["segmentation"] for i in chosen] except KeyError: pass return ret
def transform_proposals(dataset_dict, image_shape, transforms, min_box_side_len, proposal_topk): """ Apply transformations to the proposals in dataset_dict, if any. Args: dataset_dict (dict): a dict read from the dataset, possibly contains fields "proposal_boxes", "proposal_objectness_logits", "proposal_bbox_mode" image_shape (tuple): height, width transforms (TransformList): min_box_side_len (int): keep proposals with at least this size proposal_topk (int): only keep top-K scoring proposals The input dict is modified in-place, with abovementioned keys removed. A new key "proposals" will be added. Its value is an `Instances` object which contains the transformed proposals in its field "proposal_boxes" and "objectness_logits". """ if "proposal_boxes" in dataset_dict: # Transform proposal boxes boxes = transforms.apply_box( BoxMode.convert( dataset_dict.pop("proposal_boxes"), dataset_dict.pop("proposal_bbox_mode"), BoxMode.XYXY_ABS, ) ) boxes = Boxes(boxes) objectness_logits = torch.as_tensor( dataset_dict.pop("proposal_objectness_logits").astype("float32") ) boxes.clip(image_shape) keep = boxes.nonempty(threshold=min_box_side_len) boxes = boxes[keep] objectness_logits = objectness_logits[keep] proposals = Instances(image_shape) proposals.proposal_boxes = boxes[:proposal_topk] proposals.objectness_logits = objectness_logits[:proposal_topk] dataset_dict["proposals"] = proposals
def gen_crop_transform_with_instance(crop_size, image_size, instance): """ Generate a CropTransform so that the cropping region contains the center of the given instance. Args: crop_size (tuple): h, w in pixels image_size (tuple): h, w instance (dict): an annotation dict of one instance, in Detectron2's dataset format. """ crop_size = np.asarray(crop_size, dtype=np.int32) bbox = BoxMode.convert(instance["bbox"], instance["bbox_mode"], BoxMode.XYXY_ABS) center_yx = (bbox[1] + bbox[3]) * 0.5, (bbox[0] + bbox[2]) * 0.5 min_yx = np.maximum(np.floor(center_yx).astype(np.int32) - crop_size, 0) max_yx = np.maximum(np.asarray(image_size, dtype=np.int32) - crop_size, 0) max_yx = np.minimum(max_yx, np.ceil(center_yx).astype(np.int32)) y0 = np.random.randint(min_yx[0], max_yx[0] + 1) x0 = np.random.randint(min_yx[1], max_yx[1] + 1) return T.CropTransform(x0, y0, crop_size[1], crop_size[0])
def transform_instance_annotations(annotation, transforms, image_size): """ Apply transforms to box of annotations of a single instance. It will use `transforms.apply_box` for the box,. If you need anything more specially designed for each data structure, you'll need to implement your own version of this function or the transforms. Args: annotation (dict): dict of instance annotations for a single instance. transforms (TransformList): image_size (tuple): the height, width of the transformed image Returns: dict: the same input dict with fields "bbox" transformed according to `transforms`. The "bbox_mode" field will be set to XYXY_ABS. """ bbox = BoxMode.convert(annotation["bbox"], annotation["bbox_mode"], BoxMode.XYXY_ABS) # Note that bbox is 1d (per-instance bounding box) annotation["bbox"] = transforms.apply_box([bbox])[0] annotation["bbox_mode"] = BoxMode.XYXY_ABS return annotation
def convert_to_coco_dict(dataset_name): """ Convert a dataset in detectron2's standard format into COCO json format Generic dataset description can be found here: https://detectron2.readthedocs.io/tutorials/datasets.html#register-a-dataset COCO data format description can be found here: http://cocodataset.org/#format-data Args: dataset_name: name of the source dataset must be registered in DatastCatalog and in detectron2's standard format Returns: coco_dict: serializable dict in COCO json format """ dataset_dicts = DatasetCatalog.get(dataset_name) categories = [{ "id": id, "name": name } for id, name in enumerate( MetadataCatalog.get(dataset_name).thing_classes)] logger.info("Converting dataset dicts into COCO format") coco_images = [] coco_annotations = [] for image_id, image_dict in enumerate(dataset_dicts): coco_image = { "id": image_dict.get("image_id", image_id), "width": image_dict["width"], "height": image_dict["height"], "file_name": image_dict["file_name"], } coco_images.append(coco_image) anns_per_image = image_dict["annotations"] for annotation in anns_per_image: # create a new dict with only COCO fields coco_annotation = {} # COCO requirement: XYWH box format bbox = annotation["bbox"] bbox_mode = annotation["bbox_mode"] bbox = BoxMode.convert(bbox, bbox_mode, BoxMode.XYWH_ABS) # Computing areas using bounding boxes bbox_xy = BoxMode.convert(bbox, BoxMode.XYWH_ABS, BoxMode.XYXY_ABS) area = Boxes([bbox_xy]).area()[0].item() # COCO requirement: # linking annotations to images # "id" field must start with 1 coco_annotation["id"] = len(coco_annotations) + 1 coco_annotation["image_id"] = coco_image["id"] coco_annotation["bbox"] = [round(float(x), 3) for x in bbox] coco_annotation["area"] = area coco_annotation["category_id"] = annotation["category_id"] coco_annotation["iscrowd"] = annotation.get("iscrowd", 0) coco_annotations.append(coco_annotation) logger.info( "Conversion finished, " f"num images: {len(coco_images)}, num annotations: {len(coco_annotations)}" ) info = { "date_created": str(datetime.datetime.now()), "description": "Automatically generated COCO json file for Detectron2.", } coco_dict = { "info": info, "images": coco_images, "annotations": coco_annotations, "categories": categories, "licenses": None, } return coco_dict