ultralytics 8.0.136 refactor and simplify package (#3748)

Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>

ultralytics/models/yolo/segment/__init__.py

@@ -0,0 +1,7 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
+
+from .predict import SegmentationPredictor, predict
+from .train import SegmentationTrainer, train
+from .val import SegmentationValidator, val
+
+__all__ = 'SegmentationPredictor', 'predict', 'SegmentationTrainer', 'train', 'SegmentationValidator', 'val'

ultralytics/models/yolo/segment/predict.py

@@ -0,0 +1,63 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
+
+import torch
+
+from ultralytics.engine.results import Results
+from ultralytics.models.yolo.detect.predict import DetectionPredictor
+from ultralytics.utils import DEFAULT_CFG, ROOT, ops
+
+
+class SegmentationPredictor(DetectionPredictor):
+
+    def __init__(self, cfg=DEFAULT_CFG, overrides=None, _callbacks=None):
+        super().__init__(cfg, overrides, _callbacks)
+        self.args.task = 'segment'
+
+    def postprocess(self, preds, img, orig_imgs):
+        """TODO: filter by classes."""
+        p = ops.non_max_suppression(preds[0],
+                                    self.args.conf,
+                                    self.args.iou,
+                                    agnostic=self.args.agnostic_nms,
+                                    max_det=self.args.max_det,
+                                    nc=len(self.model.names),
+                                    classes=self.args.classes)
+        results = []
+        proto = preds[1][-1] if len(preds[1]) == 3 else preds[1]  # second output is len 3 if pt, but only 1 if exported
+        for i, pred in enumerate(p):
+            orig_img = orig_imgs[i] if isinstance(orig_imgs, list) else orig_imgs
+            path = self.batch[0]
+            img_path = path[i] if isinstance(path, list) else path
+            if not len(pred):  # save empty boxes
+                results.append(Results(orig_img=orig_img, path=img_path, names=self.model.names, boxes=pred[:, :6]))
+                continue
+            if self.args.retina_masks:
+                if not isinstance(orig_imgs, torch.Tensor):
+                    pred[:, :4] = ops.scale_boxes(img.shape[2:], pred[:, :4], orig_img.shape)
+                masks = ops.process_mask_native(proto[i], pred[:, 6:], pred[:, :4], orig_img.shape[:2])  # HWC
+            else:
+                masks = ops.process_mask(proto[i], pred[:, 6:], pred[:, :4], img.shape[2:], upsample=True)  # HWC
+                if not isinstance(orig_imgs, torch.Tensor):
+                    pred[:, :4] = ops.scale_boxes(img.shape[2:], pred[:, :4], orig_img.shape)
+            results.append(
+                Results(orig_img=orig_img, path=img_path, names=self.model.names, boxes=pred[:, :6], masks=masks))
+        return results
+
+
+def predict(cfg=DEFAULT_CFG, use_python=False):
+    """Runs YOLO object detection on an image or video source."""
+    model = cfg.model or 'yolov8n-seg.pt'
+    source = cfg.source if cfg.source is not None else ROOT / 'assets' if (ROOT / 'assets').exists() \
+        else 'https://ultralytics.com/images/bus.jpg'
+
+    args = dict(model=model, source=source)
+    if use_python:
+        from ultralytics import YOLO
+        YOLO(model)(**args)
+    else:
+        predictor = SegmentationPredictor(overrides=args)
+        predictor.predict_cli()
+
+
+if __name__ == '__main__':
+    predict()

ultralytics/models/yolo/segment/train.py

@@ -0,0 +1,65 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
+from copy import copy
+
+from ultralytics.models import yolo
+from ultralytics.nn.tasks import SegmentationModel
+from ultralytics.utils import DEFAULT_CFG, RANK
+from ultralytics.utils.plotting import plot_images, plot_results
+
+
+# BaseTrainer python usage
+class SegmentationTrainer(yolo.detect.DetectionTrainer):
+
+    def __init__(self, cfg=DEFAULT_CFG, overrides=None, _callbacks=None):
+        """Initialize a SegmentationTrainer object with given arguments."""
+        if overrides is None:
+            overrides = {}
+        overrides['task'] = 'segment'
+        super().__init__(cfg, overrides, _callbacks)
+
+    def get_model(self, cfg=None, weights=None, verbose=True):
+        """Return SegmentationModel initialized with specified config and weights."""
+        model = SegmentationModel(cfg, ch=3, nc=self.data['nc'], verbose=verbose and RANK == -1)
+        if weights:
+            model.load(weights)
+
+        return model
+
+    def get_validator(self):
+        """Return an instance of SegmentationValidator for validation of YOLO model."""
+        self.loss_names = 'box_loss', 'seg_loss', 'cls_loss', 'dfl_loss'
+        return yolo.segment.SegmentationValidator(self.test_loader, save_dir=self.save_dir, args=copy(self.args))
+
+    def plot_training_samples(self, batch, ni):
+        """Creates a plot of training sample images with labels and box coordinates."""
+        plot_images(batch['img'],
+                    batch['batch_idx'],
+                    batch['cls'].squeeze(-1),
+                    batch['bboxes'],
+                    batch['masks'],
+                    paths=batch['im_file'],
+                    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, segment=True, on_plot=self.on_plot)  # save results.png
+
+
+def train(cfg=DEFAULT_CFG, use_python=False):
+    """Train a YOLO segmentation model based on passed arguments."""
+    model = cfg.model or 'yolov8n-seg.pt'
+    data = cfg.data or 'coco128-seg.yaml'  # or yolo.ClassificationDataset("mnist")
+    device = cfg.device if cfg.device is not None else ''
+
+    args = dict(model=model, data=data, device=device)
+    if use_python:
+        from ultralytics import YOLO
+        YOLO(model).train(**args)
+    else:
+        trainer = SegmentationTrainer(overrides=args)
+        trainer.train()
+
+
+if __name__ == '__main__':
+    train()

ultralytics/models/yolo/segment/val.py

@@ -0,0 +1,262 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
+
+from multiprocessing.pool import ThreadPool
+from pathlib import Path
+
+import numpy as np
+import torch
+import torch.nn.functional as F
+
+from ultralytics.models.yolo.detect import DetectionValidator
+from ultralytics.utils import DEFAULT_CFG, LOGGER, NUM_THREADS, ops
+from ultralytics.utils.checks import check_requirements
+from ultralytics.utils.metrics import SegmentMetrics, box_iou, mask_iou
+from ultralytics.utils.plotting import output_to_target, plot_images
+
+
+class SegmentationValidator(DetectionValidator):
+
+    def __init__(self, dataloader=None, save_dir=None, pbar=None, args=None, _callbacks=None):
+        """Initialize SegmentationValidator and set task to 'segment', metrics to SegmentMetrics."""
+        super().__init__(dataloader, save_dir, pbar, args, _callbacks)
+        self.args.task = 'segment'
+        self.metrics = SegmentMetrics(save_dir=self.save_dir, on_plot=self.on_plot)
+
+    def preprocess(self, batch):
+        """Preprocesses batch by converting masks to float and sending to device."""
+        batch = super().preprocess(batch)
+        batch['masks'] = batch['masks'].to(self.device).float()
+        return batch
+
+    def init_metrics(self, model):
+        """Initialize metrics and select mask processing function based on save_json flag."""
+        super().init_metrics(model)
+        self.plot_masks = []
+        if self.args.save_json:
+            check_requirements('pycocotools>=2.0.6')
+            self.process = ops.process_mask_upsample  # more accurate
+        else:
+            self.process = ops.process_mask  # faster
+
+    def get_desc(self):
+        """Return a formatted description of evaluation metrics."""
+        return ('%22s' + '%11s' * 10) % ('Class', 'Images', 'Instances', 'Box(P', 'R', 'mAP50', 'mAP50-95)', 'Mask(P',
+                                         'R', 'mAP50', 'mAP50-95)')
+
+    def postprocess(self, preds):
+        """Postprocesses YOLO predictions and returns output detections with proto."""
+        p = ops.non_max_suppression(preds[0],
+                                    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)
+        proto = preds[1][-1] if len(preds[1]) == 3 else preds[1]  # second output is len 3 if pt, but only 1 if exported
+        return p, proto
+
+    def update_metrics(self, preds, batch):
+        """Metrics."""
+        for si, (pred, proto) in enumerate(zip(preds[0], preds[1])):
+            idx = batch['batch_idx'] == si
+            cls = batch['cls'][idx]
+            bbox = batch['bboxes'][idx]
+            nl, npr = cls.shape[0], pred.shape[0]  # number of labels, predictions
+            shape = batch['ori_shape'][si]
+            correct_masks = torch.zeros(npr, self.niou, dtype=torch.bool, device=self.device)  # init
+            correct_bboxes = torch.zeros(npr, self.niou, dtype=torch.bool, device=self.device)  # init
+            self.seen += 1
+
+            if npr == 0:
+                if nl:
+                    self.stats.append((correct_bboxes, correct_masks, *torch.zeros(
+                        (2, 0), device=self.device), cls.squeeze(-1)))
+                    if self.args.plots:
+                        self.confusion_matrix.process_batch(detections=None, labels=cls.squeeze(-1))
+                continue
+
+            # Masks
+            midx = [si] if self.args.overlap_mask else idx
+            gt_masks = batch['masks'][midx]
+            pred_masks = self.process(proto, pred[:, 6:], pred[:, :4], shape=batch['img'][si].shape[1:])
+
+            # Predictions
+            if self.args.single_cls:
+                pred[:, 5] = 0
+            predn = pred.clone()
+            ops.scale_boxes(batch['img'][si].shape[1:], predn[:, :4], shape,
+                            ratio_pad=batch['ratio_pad'][si])  # native-space pred
+
+            # Evaluate
+            if nl:
+                height, width = batch['img'].shape[2:]
+                tbox = ops.xywh2xyxy(bbox) * torch.tensor(
+                    (width, height, width, height), device=self.device)  # target boxes
+                ops.scale_boxes(batch['img'][si].shape[1:], tbox, shape,
+                                ratio_pad=batch['ratio_pad'][si])  # native-space labels
+                labelsn = torch.cat((cls, tbox), 1)  # native-space labels
+                correct_bboxes = self._process_batch(predn, labelsn)
+                # TODO: maybe remove these `self.` arguments as they already are member variable
+                correct_masks = self._process_batch(predn,
+                                                    labelsn,
+                                                    pred_masks,
+                                                    gt_masks,
+                                                    overlap=self.args.overlap_mask,
+                                                    masks=True)
+                if self.args.plots:
+                    self.confusion_matrix.process_batch(predn, labelsn)
+
+            # Append correct_masks, correct_boxes, pconf, pcls, tcls
+            self.stats.append((correct_bboxes, correct_masks, pred[:, 4], pred[:, 5], cls.squeeze(-1)))
+
+            pred_masks = torch.as_tensor(pred_masks, dtype=torch.uint8)
+            if self.args.plots and self.batch_i < 3:
+                self.plot_masks.append(pred_masks[:15].cpu())  # filter top 15 to plot
+
+            # Save
+            if self.args.save_json:
+                pred_masks = ops.scale_image(pred_masks.permute(1, 2, 0).contiguous().cpu().numpy(),
+                                             shape,
+                                             ratio_pad=batch['ratio_pad'][si])
+                self.pred_to_json(predn, batch['im_file'][si], pred_masks)
+            # if self.args.save_txt:
+            #    save_one_txt(predn, save_conf, shape, file=save_dir / 'labels' / f'{path.stem}.txt')
+
+    def finalize_metrics(self, *args, **kwargs):
+        """Sets speed and confusion matrix for evaluation metrics."""
+        self.metrics.speed = self.speed
+        self.metrics.confusion_matrix = self.confusion_matrix
+
+    def _process_batch(self, detections, labels, pred_masks=None, gt_masks=None, overlap=False, masks=False):
+        """
+        Return correct prediction matrix
+        Arguments:
+            detections (array[N, 6]), x1, y1, x2, y2, conf, class
+            labels (array[M, 5]), class, x1, y1, x2, y2
+        Returns:
+            correct (array[N, 10]), for 10 IoU levels
+        """
+        if masks:
+            if overlap:
+                nl = len(labels)
+                index = torch.arange(nl, device=gt_masks.device).view(nl, 1, 1) + 1
+                gt_masks = gt_masks.repeat(nl, 1, 1)  # shape(1,640,640) -> (n,640,640)
+                gt_masks = torch.where(gt_masks == index, 1.0, 0.0)
+            if gt_masks.shape[1:] != pred_masks.shape[1:]:
+                gt_masks = F.interpolate(gt_masks[None], pred_masks.shape[1:], mode='bilinear', align_corners=False)[0]
+                gt_masks = gt_masks.gt_(0.5)
+            iou = mask_iou(gt_masks.view(gt_masks.shape[0], -1), pred_masks.view(pred_masks.shape[0], -1))
+        else:  # boxes
+            iou = box_iou(labels[:, 1:], detections[:, :4])
+
+        correct = np.zeros((detections.shape[0], self.iouv.shape[0])).astype(bool)
+        correct_class = labels[:, 0:1] == detections[:, 5]
+        for i in range(len(self.iouv)):
+            x = torch.where((iou >= self.iouv[i]) & correct_class)  # IoU > threshold and classes match
+            if x[0].shape[0]:
+                matches = torch.cat((torch.stack(x, 1), iou[x[0], x[1]][:, None]),
+                                    1).cpu().numpy()  # [label, detect, iou]
+                if x[0].shape[0] > 1:
+                    matches = matches[matches[:, 2].argsort()[::-1]]
+                    matches = matches[np.unique(matches[:, 1], return_index=True)[1]]
+                    # matches = matches[matches[:, 2].argsort()[::-1]]
+                    matches = matches[np.unique(matches[:, 0], return_index=True)[1]]
+                correct[matches[:, 1].astype(int), i] = True
+        return torch.tensor(correct, dtype=torch.bool, device=detections.device)
+
+    def plot_val_samples(self, batch, ni):
+        """Plots validation samples with bounding box labels."""
+        plot_images(batch['img'],
+                    batch['batch_idx'],
+                    batch['cls'].squeeze(-1),
+                    batch['bboxes'],
+                    batch['masks'],
+                    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 batch predictions with masks and bounding boxes."""
+        plot_images(
+            batch['img'],
+            *output_to_target(preds[0], max_det=15),  # not set to self.args.max_det due to slow plotting speed
+            torch.cat(self.plot_masks, dim=0) if len(self.plot_masks) else self.plot_masks,
+            paths=batch['im_file'],
+            fname=self.save_dir / f'val_batch{ni}_pred.jpg',
+            names=self.names,
+            on_plot=self.on_plot)  # pred
+        self.plot_masks.clear()
+
+    def pred_to_json(self, predn, filename, pred_masks):
+        """Save one JSON result."""
+        # Example result = {"image_id": 42, "category_id": 18, "bbox": [258.15, 41.29, 348.26, 243.78], "score": 0.236}
+        from pycocotools.mask import encode  # noqa
+
+        def single_encode(x):
+            """Encode predicted masks as RLE and append results to jdict."""
+            rle = encode(np.asarray(x[:, :, None], order='F', dtype='uint8'))[0]
+            rle['counts'] = rle['counts'].decode('utf-8')
+            return rle
+
+        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
+        pred_masks = np.transpose(pred_masks, (2, 0, 1))
+        with ThreadPool(NUM_THREADS) as pool:
+            rles = pool.map(single_encode, pred_masks)
+        for i, (p, b) in enumerate(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],
+                'score': round(p[4], 5),
+                'segmentation': rles[i]})
+
+    def eval_json(self, stats):
+        """Return COCO-style object detection evaluation metrics."""
+        if self.args.save_json and self.is_coco and len(self.jdict):
+            anno_json = self.data['path'] / 'annotations/instances_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, 'segm')]):
+                    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
+
+
+def val(cfg=DEFAULT_CFG, use_python=False):
+    """Validate trained YOLO model on validation data."""
+    model = cfg.model or 'yolov8n-seg.pt'
+    data = cfg.data or 'coco128-seg.yaml'
+
+    args = dict(model=model, data=data)
+    if use_python:
+        from ultralytics import YOLO
+        YOLO(model).val(**args)
+    else:
+        validator = SegmentationValidator(args=args)
+        validator(model=args['model'])
+
+
+if __name__ == '__main__':
+    val()