回传数据解析，兼容v5和v10

ultralytics/models/yolo/pose/__init__.py

@@ -0,0 +1,7 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
+
+from .predict import PosePredictor
+from .train import PoseTrainer
+from .val import PoseValidator
+
+__all__ = "PoseTrainer", "PoseValidator", "PosePredictor"

ultralytics/models/yolo/pose/predict.py

@@ -0,0 +1,58 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
+
+from ultralytics.engine.results import Results
+from ultralytics.models.yolo.detect.predict import DetectionPredictor
+from ultralytics.utils import DEFAULT_CFG, LOGGER, ops
+
+
+class PosePredictor(DetectionPredictor):
+    """
+    A class extending the DetectionPredictor class for prediction based on a pose model.
+
+    Example:
+        ```python
+        from ultralytics.utils import ASSETS
+        from ultralytics.models.yolo.pose import PosePredictor
+
+        args = dict(model='yolov8n-pose.pt', source=ASSETS)
+        predictor = PosePredictor(overrides=args)
+        predictor.predict_cli()
+        ```
+    """
+
+    def __init__(self, cfg=DEFAULT_CFG, overrides=None, _callbacks=None):
+        """Initializes PosePredictor, sets task to 'pose' and logs a warning for using 'mps' as device."""
+        super().__init__(cfg, overrides, _callbacks)
+        self.args.task = "pose"
+        if isinstance(self.args.device, str) and self.args.device.lower() == "mps":
+            LOGGER.warning(
+                "WARNING ⚠️ Apple MPS known Pose bug. Recommend 'device=cpu' for Pose models. "
+                "See https://github.com/ultralytics/ultralytics/issues/4031."
+            )
+
+    def postprocess(self, preds, img, orig_imgs):
+        """Return detection results for a given input image or list of images."""
+        preds = ops.non_max_suppression(
+            preds,
+            self.args.conf,
+            self.args.iou,
+            agnostic=self.args.agnostic_nms,
+            max_det=self.args.max_det,
+            classes=self.args.classes,
+            nc=len(self.model.names),
+        )
+
+        if not isinstance(orig_imgs, list):  # input images are a torch.Tensor, not a list
+            orig_imgs = ops.convert_torch2numpy_batch(orig_imgs)
+
+        results = []
+        for i, pred in enumerate(preds):
+            orig_img = orig_imgs[i]
+            pred[:, :4] = ops.scale_boxes(img.shape[2:], pred[:, :4], orig_img.shape).round()
+            pred_kpts = pred[:, 6:].view(len(pred), *self.model.kpt_shape) if len(pred) else pred[:, 6:]
+            pred_kpts = ops.scale_coords(img.shape[2:], pred_kpts, orig_img.shape)
+            img_path = self.batch[0][i]
+            results.append(
+                Results(orig_img, path=img_path, names=self.model.names, boxes=pred[:, :6], keypoints=pred_kpts)
+            )
+        return results

ultralytics/models/yolo/pose/train.py

@@ -0,0 +1,79 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
+
+from copy import copy
+
+from ultralytics.models import yolo
+from ultralytics.nn.tasks import PoseModel
+from ultralytics.utils import DEFAULT_CFG, LOGGER
+from ultralytics.utils.plotting import plot_images, plot_results
+
+
+class PoseTrainer(yolo.detect.DetectionTrainer):
+    """
+    A class extending the DetectionTrainer class for training based on a pose model.
+
+    Example:
+        ```python
+        from ultralytics.models.yolo.pose import PoseTrainer
+
+        args = dict(model='yolov8n-pose.pt', data='coco8-pose.yaml', epochs=3)
+        trainer = PoseTrainer(overrides=args)
+        trainer.train()
+        ```
+    """
+
+    def __init__(self, cfg=DEFAULT_CFG, overrides=None, _callbacks=None):
+        """Initialize a PoseTrainer object with specified configurations and overrides."""
+        if overrides is None:
+            overrides = {}
+        overrides["task"] = "pose"
+        super().__init__(cfg, overrides, _callbacks)
+
+        if isinstance(self.args.device, str) and self.args.device.lower() == "mps":
+            LOGGER.warning(
+                "WARNING ⚠️ Apple MPS known Pose bug. Recommend 'device=cpu' for Pose models. "
+                "See https://github.com/ultralytics/ultralytics/issues/4031."
+            )
+
+    def get_model(self, cfg=None, weights=None, verbose=True):
+        """Get pose estimation model with specified configuration and weights."""
+        model = PoseModel(cfg, ch=3, nc=self.data["nc"], data_kpt_shape=self.data["kpt_shape"], verbose=verbose)
+        if weights:
+            model.load(weights)
+
+        return model
+
+    def set_model_attributes(self):
+        """Sets keypoints shape attribute of PoseModel."""
+        super().set_model_attributes()
+        self.model.kpt_shape = self.data["kpt_shape"]
+
+    def get_validator(self):
+        """Returns an instance of the PoseValidator class for validation."""
+        self.loss_names = "box_loss", "pose_loss", "kobj_loss", "cls_loss", "dfl_loss"
+        return yolo.pose.PoseValidator(
+            self.test_loader, save_dir=self.save_dir, args=copy(self.args), _callbacks=self.callbacks
+        )
+
+    def plot_training_samples(self, batch, ni):
+        """Plot a batch of training samples with annotated class labels, bounding boxes, and keypoints."""
+        images = batch["img"]
+        kpts = batch["keypoints"]
+        cls = batch["cls"].squeeze(-1)
+        bboxes = batch["bboxes"]
+        paths = batch["im_file"]
+        batch_idx = batch["batch_idx"]
+        plot_images(
+            images,
+            batch_idx,
+            cls,
+            bboxes,
+            kpts=kpts,
+            paths=paths,
+            fname=self.save_dir / f"train_batch{ni}.jpg",
+            on_plot=self.on_plot,
+        )
+
+    def plot_metrics(self):
+        """Plots training/val metrics."""
+        plot_results(file=self.csv, pose=True, on_plot=self.on_plot)  # save results.png

ultralytics/models/yolo/pose/val.py

@@ -0,0 +1,248 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
+
+from pathlib import Path
+
+import numpy as np
+import torch
+
+from ultralytics.models.yolo.detect import DetectionValidator
+from ultralytics.utils import LOGGER, ops
+from ultralytics.utils.checks import check_requirements
+from ultralytics.utils.metrics import OKS_SIGMA, PoseMetrics, box_iou, kpt_iou
+from ultralytics.utils.plotting import output_to_target, plot_images
+
+
+class PoseValidator(DetectionValidator):
+    """
+    A class extending the DetectionValidator class for validation based on a pose model.
+
+    Example:
+        ```python
+        from ultralytics.models.yolo.pose import PoseValidator
+
+        args = dict(model='yolov8n-pose.pt', data='coco8-pose.yaml')
+        validator = PoseValidator(args=args)
+        validator()
+        ```
+    """
+
+    def __init__(self, dataloader=None, save_dir=None, pbar=None, args=None, _callbacks=None):
+        """Initialize a 'PoseValidator' object with custom parameters and assigned attributes."""
+        super().__init__(dataloader, save_dir, pbar, args, _callbacks)
+        self.sigma = None
+        self.kpt_shape = None
+        self.args.task = "pose"
+        self.metrics = PoseMetrics(save_dir=self.save_dir, on_plot=self.on_plot)
+        if isinstance(self.args.device, str) and self.args.device.lower() == "mps":
+            LOGGER.warning(
+                "WARNING ⚠️ Apple MPS known Pose bug. Recommend 'device=cpu' for Pose models. "
+                "See https://github.com/ultralytics/ultralytics/issues/4031."
+            )
+
+    def preprocess(self, batch):
+        """Preprocesses the batch by converting the 'keypoints' data into a float and moving it to the device."""
+        batch = super().preprocess(batch)
+        batch["keypoints"] = batch["keypoints"].to(self.device).float()
+        return batch
+
+    def get_desc(self):
+        """Returns description of evaluation metrics in string format."""
+        return ("%22s" + "%11s" * 10) % (
+            "Class",
+            "Images",
+            "Instances",
+            "Box(P",
+            "R",
+            "mAP50",
+            "mAP50-95)",
+            "Pose(P",
+            "R",
+            "mAP50",
+            "mAP50-95)",
+        )
+
+    def postprocess(self, preds):
+        """Apply non-maximum suppression and return detections with high confidence scores."""
+        return ops.non_max_suppression(
+            preds,
+            self.args.conf,
+            self.args.iou,
+            labels=self.lb,
+            multi_label=True,
+            agnostic=self.args.single_cls,
+            max_det=self.args.max_det,
+            nc=self.nc,
+        )
+
+    def init_metrics(self, model):
+        """Initiate pose estimation metrics for YOLO model."""
+        super().init_metrics(model)
+        self.kpt_shape = self.data["kpt_shape"]
+        is_pose = self.kpt_shape == [17, 3]
+        nkpt = self.kpt_shape[0]
+        self.sigma = OKS_SIGMA if is_pose else np.ones(nkpt) / nkpt
+        self.stats = dict(tp_p=[], tp=[], conf=[], pred_cls=[], target_cls=[])
+
+    def _prepare_batch(self, si, batch):
+        """Prepares a batch for processing by converting keypoints to float and moving to device."""
+        pbatch = super()._prepare_batch(si, batch)
+        kpts = batch["keypoints"][batch["batch_idx"] == si]
+        h, w = pbatch["imgsz"]
+        kpts = kpts.clone()
+        kpts[..., 0] *= w
+        kpts[..., 1] *= h
+        kpts = ops.scale_coords(pbatch["imgsz"], kpts, pbatch["ori_shape"], ratio_pad=pbatch["ratio_pad"])
+        pbatch["kpts"] = kpts
+        return pbatch
+
+    def _prepare_pred(self, pred, pbatch):
+        """Prepares and scales keypoints in a batch for pose processing."""
+        predn = super()._prepare_pred(pred, pbatch)
+        nk = pbatch["kpts"].shape[1]
+        pred_kpts = predn[:, 6:].view(len(predn), nk, -1)
+        ops.scale_coords(pbatch["imgsz"], pred_kpts, pbatch["ori_shape"], ratio_pad=pbatch["ratio_pad"])
+        return predn, pred_kpts
+
+    def update_metrics(self, preds, batch):
+        """Metrics."""
+        for si, pred in enumerate(preds):
+            self.seen += 1
+            npr = len(pred)
+            stat = dict(
+                conf=torch.zeros(0, device=self.device),
+                pred_cls=torch.zeros(0, device=self.device),
+                tp=torch.zeros(npr, self.niou, dtype=torch.bool, device=self.device),
+                tp_p=torch.zeros(npr, self.niou, dtype=torch.bool, device=self.device),
+            )
+            pbatch = self._prepare_batch(si, batch)
+            cls, bbox = pbatch.pop("cls"), pbatch.pop("bbox")
+            nl = len(cls)
+            stat["target_cls"] = cls
+            if npr == 0:
+                if nl:
+                    for k in self.stats.keys():
+                        self.stats[k].append(stat[k])
+                    if self.args.plots:
+                        self.confusion_matrix.process_batch(detections=None, gt_bboxes=bbox, gt_cls=cls)
+                continue
+
+            # Predictions
+            if self.args.single_cls:
+                pred[:, 5] = 0
+            predn, pred_kpts = self._prepare_pred(pred, pbatch)
+            stat["conf"] = predn[:, 4]
+            stat["pred_cls"] = predn[:, 5]
+
+            # Evaluate
+            if nl:
+                stat["tp"] = self._process_batch(predn, bbox, cls)
+                stat["tp_p"] = self._process_batch(predn, bbox, cls, pred_kpts, pbatch["kpts"])
+                if self.args.plots:
+                    self.confusion_matrix.process_batch(predn, bbox, cls)
+
+            for k in self.stats.keys():
+                self.stats[k].append(stat[k])
+
+            # Save
+            if self.args.save_json:
+                self.pred_to_json(predn, batch["im_file"][si])
+            # if self.args.save_txt:
+            #    save_one_txt(predn, save_conf, shape, file=save_dir / 'labels' / f'{path.stem}.txt')
+
+    def _process_batch(self, detections, gt_bboxes, gt_cls, pred_kpts=None, gt_kpts=None):
+        """
+        Return correct prediction matrix.
+
+        Args:
+            detections (torch.Tensor): Tensor of shape [N, 6] representing detections.
+                Each detection is of the format: x1, y1, x2, y2, conf, class.
+            labels (torch.Tensor): Tensor of shape [M, 5] representing labels.
+                Each label is of the format: class, x1, y1, x2, y2.
+            pred_kpts (torch.Tensor, optional): Tensor of shape [N, 51] representing predicted keypoints.
+                51 corresponds to 17 keypoints each with 3 values.
+            gt_kpts (torch.Tensor, optional): Tensor of shape [N, 51] representing ground truth keypoints.
+
+        Returns:
+            torch.Tensor: Correct prediction matrix of shape [N, 10] for 10 IoU levels.
+        """
+        if pred_kpts is not None and gt_kpts is not None:
+            # `0.53` is from https://github.com/jin-s13/xtcocoapi/blob/master/xtcocotools/cocoeval.py#L384
+            area = ops.xyxy2xywh(gt_bboxes)[:, 2:].prod(1) * 0.53
+            iou = kpt_iou(gt_kpts, pred_kpts, sigma=self.sigma, area=area)
+        else:  # boxes
+            iou = box_iou(gt_bboxes, detections[:, :4])
+
+        return self.match_predictions(detections[:, 5], gt_cls, iou)
+
+    def plot_val_samples(self, batch, ni):
+        """Plots and saves validation set samples with predicted bounding boxes and keypoints."""
+        plot_images(
+            batch["img"],
+            batch["batch_idx"],
+            batch["cls"].squeeze(-1),
+            batch["bboxes"],
+            kpts=batch["keypoints"],
+            paths=batch["im_file"],
+            fname=self.save_dir / f"val_batch{ni}_labels.jpg",
+            names=self.names,
+            on_plot=self.on_plot,
+        )
+
+    def plot_predictions(self, batch, preds, ni):
+        """Plots predictions for YOLO model."""
+        pred_kpts = torch.cat([p[:, 6:].view(-1, *self.kpt_shape) for p in preds], 0)
+        plot_images(
+            batch["img"],
+            *output_to_target(preds, max_det=self.args.max_det),
+            kpts=pred_kpts,
+            paths=batch["im_file"],
+            fname=self.save_dir / f"val_batch{ni}_pred.jpg",
+            names=self.names,
+            on_plot=self.on_plot,
+        )  # pred
+
+    def pred_to_json(self, predn, filename):
+        """Converts YOLO predictions to COCO JSON format."""
+        stem = Path(filename).stem
+        image_id = int(stem) if stem.isnumeric() else stem
+        box = ops.xyxy2xywh(predn[:, :4])  # xywh
+        box[:, :2] -= box[:, 2:] / 2  # xy center to top-left corner
+        for p, b in zip(predn.tolist(), box.tolist()):
+            self.jdict.append(
+                {
+                    "image_id": image_id,
+                    "category_id": self.class_map[int(p[5])],
+                    "bbox": [round(x, 3) for x in b],
+                    "keypoints": p[6:],
+                    "score": round(p[4], 5),
+                }
+            )
+
+    def eval_json(self, stats):
+        """Evaluates object detection model using COCO JSON format."""
+        if self.args.save_json and self.is_coco and len(self.jdict):
+            anno_json = self.data["path"] / "annotations/person_keypoints_val2017.json"  # annotations
+            pred_json = self.save_dir / "predictions.json"  # predictions
+            LOGGER.info(f"\nEvaluating pycocotools mAP using {pred_json} and {anno_json}...")
+            try:  # https://github.com/cocodataset/cocoapi/blob/master/PythonAPI/pycocoEvalDemo.ipynb
+                check_requirements("pycocotools>=2.0.6")
+                from pycocotools.coco import COCO  # noqa
+                from pycocotools.cocoeval import COCOeval  # noqa
+
+                for x in anno_json, pred_json:
+                    assert x.is_file(), f"{x} file not found"
+                anno = COCO(str(anno_json))  # init annotations api
+                pred = anno.loadRes(str(pred_json))  # init predictions api (must pass string, not Path)
+                for i, eval in enumerate([COCOeval(anno, pred, "bbox"), COCOeval(anno, pred, "keypoints")]):
+                    if self.is_coco:
+                        eval.params.imgIds = [int(Path(x).stem) for x in self.dataloader.dataset.im_files]  # im to eval
+                    eval.evaluate()
+                    eval.accumulate()
+                    eval.summarize()
+                    idx = i * 4 + 2
+                    stats[self.metrics.keys[idx + 1]], stats[self.metrics.keys[idx]] = eval.stats[
+                        :2
+                    ]  # update mAP50-95 and mAP50
+            except Exception as e:
+                LOGGER.warning(f"pycocotools unable to run: {e}")
+        return stats