ultralytics 8.3.215__tar.gz → 8.3.217__tar.gz

{ultralytics-8.3.215 → ultralytics-8.3.217}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ultralytics
-Version: 8.3.215
+Version: 8.3.217
 Summary: Ultralytics YOLO 🚀 for SOTA object detection, multi-object tracking, instance segmentation, pose estimation and image classification.
 Author-email: Glenn Jocher <glenn.jocher@ultralytics.com>, Jing Qiu <jing.qiu@ultralytics.com>
 Maintainer-email: Ultralytics <hello@ultralytics.com>

{ultralytics-8.3.215 → ultralytics-8.3.217}/ultralytics/__init__.py

@@ -1,6 +1,6 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-__version__ = "8.3.215"
+__version__ = "8.3.217"
 
 import importlib
 import os

{ultralytics-8.3.215 → ultralytics-8.3.217}/ultralytics/cfg/datasets/coco-pose.yaml

@@ -22,6 +22,27 @@ flip_idx: [0, 2, 1, 4, 3, 6, 5, 8, 7, 10, 9, 12, 11, 14, 13, 16, 15]
 names:
   0: person
 
+# Keypoint names per class
+kpt_names:
+  0:
+    - nose
+    - left_eye
+    - right_eye
+    - left_ear
+    - right_ear
+    - left_shoulder
+    - right_shoulder
+    - left_elbow
+    - right_elbow
+    - left_wrist
+    - right_wrist
+    - left_hip
+    - right_hip
+    - left_knee
+    - right_knee
+    - left_ankle
+    - right_ankle
+
 # Download script/URL (optional)
 download: |
   from pathlib import Path

{ultralytics-8.3.215 → ultralytics-8.3.217}/ultralytics/cfg/datasets/coco8-pose.yaml

@@ -22,5 +22,26 @@ flip_idx: [0, 2, 1, 4, 3, 6, 5, 8, 7, 10, 9, 12, 11, 14, 13, 16, 15]
 names:
   0: person
 
+# Keypoint names per class
+kpt_names:
+  0:
+    - nose
+    - left_eye
+    - right_eye
+    - left_ear
+    - right_ear
+    - left_shoulder
+    - right_shoulder
+    - left_elbow
+    - right_elbow
+    - left_wrist
+    - right_wrist
+    - left_hip
+    - right_hip
+    - left_knee
+    - right_knee
+    - left_ankle
+    - right_ankle
+
 # Download script/URL (optional)
 download: https://github.com/ultralytics/assets/releases/download/v0.0.0/coco8-pose.zip

{ultralytics-8.3.215 → ultralytics-8.3.217}/ultralytics/cfg/datasets/dog-pose.yaml

@@ -20,5 +20,33 @@ kpt_shape: [24, 3] # number of keypoints, number of dims (2 for x,y or 3 for x,y
 names:
   0: dog
 
+# Keypoint names per class
+kpt_names:
+  0:
+    - front_left_paw
+    - front_left_knee
+    - front_left_elbow
+    - rear_left_paw
+    - rear_left_knee
+    - rear_left_elbow
+    - front_right_paw
+    - front_right_knee
+    - front_right_elbow
+    - rear_right_paw
+    - rear_right_knee
+    - rear_right_elbow
+    - tail_start
+    - tail_end
+    - left_ear_base
+    - right_ear_base
+    - nose
+    - chin
+    - left_ear_tip
+    - right_ear_tip
+    - left_eye
+    - right_eye
+    - withers
+    - throat
+
 # Download script/URL (optional)
 download: https://github.com/ultralytics/assets/releases/download/v0.0.0/dog-pose.zip

{ultralytics-8.3.215 → ultralytics-8.3.217}/ultralytics/cfg/datasets/hand-keypoints.yaml

@@ -22,5 +22,30 @@ flip_idx:
 names:
   0: hand
 
+# Keypoint names per class
+kpt_names:
+  0:
+    - wrist
+    - thumb_cmc
+    - thumb_mcp
+    - thumb_ip
+    - thumb_tip
+    - index_mcp
+    - index_pip
+    - index_dip
+    - index_tip
+    - middle_mcp
+    - middle_pip
+    - middle_dip
+    - middle_tip
+    - ring_mcp
+    - ring_pip
+    - ring_dip
+    - ring_tip
+    - pinky_mcp
+    - pinky_pip
+    - pinky_dip
+    - pinky_tip
+
 # Download script/URL (optional)
 download: https://github.com/ultralytics/assets/releases/download/v0.0.0/hand-keypoints.zip

{ultralytics-8.3.215 → ultralytics-8.3.217}/ultralytics/cfg/datasets/tiger-pose.yaml

@@ -21,5 +21,21 @@ flip_idx: [0, 1, 2, 3, 4, 5, 6, 7, 8, 9, 10, 11]
 names:
   0: tiger
 
+# Keypoint names per class
+kpt_names:
+  0:
+    - nose
+    - head
+    - withers
+    - tail_base
+    - right_hind_hock
+    - right_hind_paw
+    - left_hind_paw
+    - left_hind_hock
+    - right_front_wrist
+    - right_front_paw
+    - left_front_wrist
+    - left_front_paw
+
 # Download script/URL (optional)
 download: https://github.com/ultralytics/assets/releases/download/v0.0.0/tiger-pose.zip

{ultralytics-8.3.215 → ultralytics-8.3.217}/ultralytics/data/build.py

@@ -181,7 +181,15 @@ def build_grounding(
     )
 
 
-def build_dataloader(dataset, batch: int, workers: int, shuffle: bool = True, rank: int = -1, drop_last: bool = False):
+def build_dataloader(
+    dataset,
+    batch: int,
+    workers: int,
+    shuffle: bool = True,
+    rank: int = -1,
+    drop_last: bool = False,
+    pin_memory: bool = True,
+):
     """
     Create and return an InfiniteDataLoader or DataLoader for training or validation.
 
@@ -192,6 +200,7 @@ def build_dataloader(dataset, batch: int, workers: int, shuffle: bool = True, ra
         shuffle (bool, optional): Whether to shuffle the dataset.
         rank (int, optional): Process rank in distributed training. -1 for single-GPU training.
         drop_last (bool, optional): Whether to drop the last incomplete batch.
+        pin_memory (bool, optional): Whether to use pinned memory for dataloader.
 
     Returns:
         (InfiniteDataLoader): A dataloader that can be used for training or validation.
@@ -214,7 +223,7 @@ def build_dataloader(dataset, batch: int, workers: int, shuffle: bool = True, ra
         num_workers=nw,
         sampler=sampler,
         prefetch_factor=4 if nw > 0 else None,  # increase over default 2
-        pin_memory=nd > 0,
+        pin_memory=nd > 0 and pin_memory,
         collate_fn=getattr(dataset, "collate_fn", None),
         worker_init_fn=seed_worker,
         generator=generator,

{ultralytics-8.3.215 → ultralytics-8.3.217}/ultralytics/engine/exporter.py

@@ -502,6 +502,8 @@ class Exporter:
             self.metadata["dla"] = dla  # make sure `AutoBackend` uses correct dla device if it has one
         if model.task == "pose":
             self.metadata["kpt_shape"] = model.model[-1].kpt_shape
+            if hasattr(model, "kpt_names"):
+                self.metadata["kpt_names"] = model.kpt_names
 
         LOGGER.info(
             f"\n{colorstr('PyTorch:')} starting from '{file}' with input shape {tuple(im.shape)} BCHW and "

{ultralytics-8.3.215 → ultralytics-8.3.217}/ultralytics/engine/results.py

@@ -527,7 +527,7 @@ class Results(SimpleClass, DataExportMixin):
         """
         assert color_mode in {"instance", "class"}, f"Expected color_mode='instance' or 'class', not {color_mode}."
         if img is None and isinstance(self.orig_img, torch.Tensor):
-            img = (self.orig_img[0].detach().permute(1, 2, 0).contiguous() * 255).to(torch.uint8).cpu().numpy()
+            img = (self.orig_img[0].detach().permute(1, 2, 0).contiguous() * 255).byte().cpu().numpy()
 
         names = self.names
         is_obb = self.obb is not None

{ultralytics-8.3.215 → ultralytics-8.3.217}/ultralytics/models/sam/build.py

@@ -11,6 +11,7 @@ from functools import partial
 import torch
 
 from ultralytics.utils.downloads import attempt_download_asset
+from ultralytics.utils.torch_utils import TORCH_1_13
 
 from .modules.decoders import MaskDecoder
 from .modules.encoders import FpnNeck, Hiera, ImageEncoder, ImageEncoderViT, MemoryEncoder, PromptEncoder
@@ -207,7 +208,7 @@ def _build_sam(
     if checkpoint is not None:
         checkpoint = attempt_download_asset(checkpoint)
         with open(checkpoint, "rb") as f:
-            state_dict = torch.load(f)
+            state_dict = torch.load(f, weights_only=False) if TORCH_1_13 else torch.load(f)
         sam.load_state_dict(state_dict)
     sam.eval()
     return sam
@@ -302,7 +303,7 @@ def _build_sam2(
     if checkpoint is not None:
         checkpoint = attempt_download_asset(checkpoint)
         with open(checkpoint, "rb") as f:
-            state_dict = torch.load(f)["model"]
+            state_dict = (torch.load(f, weights_only=False) if TORCH_1_13 else torch.load(f))["model"]
         sam2.load_state_dict(state_dict)
     sam2.eval()
     return sam2

{ultralytics-8.3.215 → ultralytics-8.3.217}/ultralytics/models/yolo/detect/val.py

@@ -300,7 +300,13 @@ class DetectionValidator(BaseValidator):
         """
         dataset = self.build_dataset(dataset_path, batch=batch_size, mode="val")
         return build_dataloader(
-            dataset, batch_size, self.args.workers, shuffle=False, rank=-1, drop_last=self.args.compile
+            dataset,
+            batch_size,
+            self.args.workers,
+            shuffle=False,
+            rank=-1,
+            drop_last=self.args.compile,
+            pin_memory=self.training,
         )
 
     def plot_val_samples(self, batch: dict[str, Any], ni: int) -> None:

{ultralytics-8.3.215 → ultralytics-8.3.217}/ultralytics/models/yolo/pose/train.py

@@ -91,6 +91,11 @@ class PoseTrainer(yolo.detect.DetectionTrainer):
         """Set keypoints shape attribute of PoseModel."""
         super().set_model_attributes()
         self.model.kpt_shape = self.data["kpt_shape"]
+        kpt_names = self.data.get("kpt_names")
+        if not kpt_names:
+            names = list(map(str, range(self.model.kpt_shape[0])))
+            kpt_names = {i: names for i in range(self.model.nc)}
+        self.model.kpt_names = kpt_names
 
     def get_validator(self):
         """Return an instance of the PoseValidator class for validation."""

{ultralytics-8.3.215 → ultralytics-8.3.217}/ultralytics/models/yolo/segment/val.py

@@ -173,7 +173,7 @@ class SegmentationValidator(DetectionValidator):
         if gt_cls.shape[0] == 0 or preds["cls"].shape[0] == 0:
             tp_m = np.zeros((preds["cls"].shape[0], self.niou), dtype=bool)
         else:
-            iou = mask_iou(batch["masks"].flatten(1), preds["masks"].flatten(1))
+            iou = mask_iou(batch["masks"].flatten(1), preds["masks"].flatten(1).float())  # float, uint8
             tp_m = self.match_predictions(preds["cls"], gt_cls, iou).cpu().numpy()
         tp.update({"tp_m": tp_m})  # update tp with mask IoU
         return tp

{ultralytics-8.3.215 → ultralytics-8.3.217}/ultralytics/nn/autobackend.py

@@ -19,6 +19,7 @@ from PIL import Image
 from ultralytics.utils import ARM64, IS_JETSON, LINUX, LOGGER, PYTHON_VERSION, ROOT, YAML, is_jetson
 from ultralytics.utils.checks import check_requirements, check_suffix, check_version, check_yaml, is_rockchip
 from ultralytics.utils.downloads import attempt_download_asset, is_url
+from ultralytics.utils.nms import non_max_suppression
 
 
 def check_class_names(names: list | dict) -> dict[int, str]:
@@ -585,7 +586,7 @@ class AutoBackend(nn.Module):
             for k, v in metadata.items():
                 if k in {"stride", "batch", "channels"}:
                     metadata[k] = int(v)
-                elif k in {"imgsz", "names", "kpt_shape", "args"} and isinstance(v, str):
+                elif k in {"imgsz", "names", "kpt_shape", "kpt_names", "args"} and isinstance(v, str):
                     metadata[k] = eval(v)
             stride = metadata["stride"]
             task = metadata["task"]
@@ -593,6 +594,7 @@ class AutoBackend(nn.Module):
             imgsz = metadata["imgsz"]
             names = metadata["names"]
             kpt_shape = metadata.get("kpt_shape")
+            kpt_names = metadata.get("kpt_names")
             end2end = metadata.get("args", {}).get("nms", False)
             dynamic = metadata.get("args", {}).get("dynamic", dynamic)
             ch = metadata.get("channels", 3)
@@ -853,7 +855,10 @@ class AutoBackend(nn.Module):
         if any(warmup_types) and (self.device.type != "cpu" or self.triton):
             im = torch.empty(*imgsz, dtype=torch.half if self.fp16 else torch.float, device=self.device)  # input
             for _ in range(2 if self.jit else 1):
-                self.forward(im)  # warmup
+                self.forward(im)  # warmup model
+                warmup_boxes = torch.rand(1, 84, 16, device=self.device)  # 16 boxes works best empirically
+                warmup_boxes[:, :4] *= imgsz[-1]
+                non_max_suppression(warmup_boxes)  # warmup NMS
 
     @staticmethod
     def _model_type(p: str = "path/to/model.pt") -> list[bool]:

{ultralytics-8.3.215 → ultralytics-8.3.217}/ultralytics/utils/ops.py

@@ -548,21 +548,16 @@ def process_mask(protos, masks_in, bboxes, shape, upsample: bool = False):
             are the height and width of the input image. The mask is applied to the bounding boxes.
     """
     c, mh, mw = protos.shape  # CHW
-    ih, iw = shape
     masks = (masks_in @ protos.float().view(c, -1)).view(-1, mh, mw)  # CHW
-    width_ratio = mw / iw
-    height_ratio = mh / ih
 
-    downsampled_bboxes = bboxes.clone()
-    downsampled_bboxes[:, 0] *= width_ratio
-    downsampled_bboxes[:, 2] *= width_ratio
-    downsampled_bboxes[:, 3] *= height_ratio
-    downsampled_bboxes[:, 1] *= height_ratio
+    width_ratio = mw / shape[1]
+    height_ratio = mh / shape[0]
+    ratios = torch.tensor([[width_ratio, height_ratio, width_ratio, height_ratio]], device=bboxes.device)
 
-    masks = crop_mask(masks, downsampled_bboxes)  # CHW
+    masks = crop_mask(masks, boxes=bboxes * ratios)  # CHW
     if upsample:
         masks = F.interpolate(masks[None], shape, mode="bilinear")[0]  # CHW
-    return masks.gt_(0.0)
+    return masks.gt_(0.0).byte()
 
 
 def process_mask_native(protos, masks_in, bboxes, shape):
@@ -582,7 +577,7 @@ def process_mask_native(protos, masks_in, bboxes, shape):
     masks = (masks_in @ protos.float().view(c, -1)).view(-1, mh, mw)
     masks = scale_masks(masks[None], shape)[0]  # CHW
     masks = crop_mask(masks, bboxes)  # CHW
-    return masks.gt_(0.0)
+    return masks.gt_(0.0).byte()
 
 
 def scale_masks(masks, shape, padding: bool = True):
@@ -679,7 +674,7 @@ def masks2segments(masks, strategy: str = "all"):
     from ultralytics.data.converter import merge_multi_segment
 
     segments = []
-    for x in masks.int().cpu().numpy().astype("uint8"):
+    for x in masks.byte().cpu().numpy():
         c = cv2.findContours(x, cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE)[0]
         if c:
             if strategy == "all":  # merge and concatenate all segments
@@ -706,7 +701,7 @@ def convert_torch2numpy_batch(batch: torch.Tensor) -> np.ndarray:
     Returns:
         (np.ndarray): Output NumPy array batch with shape (Batch, Height, Width, Channels) and dtype uint8.
     """
-    return (batch.permute(0, 2, 3, 1).contiguous() * 255).clamp(0, 255).to(torch.uint8).cpu().numpy()
+    return (batch.permute(0, 2, 3, 1).contiguous() * 255).clamp(0, 255).byte().cpu().numpy()
 
 
 def clean_str(s):

{ultralytics-8.3.215 → ultralytics-8.3.217}/ultralytics/utils/plotting.py

@@ -384,25 +384,32 @@ class Annotator:
                 overlay[mask.astype(bool)] = colors[i]
             self.im = cv2.addWeighted(self.im, 1 - alpha, overlay, alpha, 0)
         else:
-            assert isinstance(masks, torch.Tensor), "`masks` must be a torch.Tensor if `im_gpu` is provided."
+            assert isinstance(masks, torch.Tensor), "'masks' must be a torch.Tensor if 'im_gpu' is provided."
             if len(masks) == 0:
                 self.im[:] = im_gpu.permute(1, 2, 0).contiguous().cpu().numpy() * 255
+                return
             if im_gpu.device != masks.device:
                 im_gpu = im_gpu.to(masks.device)
+
+            ih, iw = self.im.shape[:2]
+            if not retina_masks:
+                # Use scale_masks to properly remove padding and upsample, convert bool to float first
+                masks = ops.scale_masks(masks[None].float(), (ih, iw))[0] > 0.5
+                # Convert original BGR image to RGB tensor
+                im_gpu = (
+                    torch.from_numpy(self.im).to(masks.device).permute(2, 0, 1).flip(0).contiguous().float() / 255.0
+                )
+
             colors = torch.tensor(colors, device=masks.device, dtype=torch.float32) / 255.0  # shape(n,3)
             colors = colors[:, None, None]  # shape(n,1,1,3)
             masks = masks.unsqueeze(3)  # shape(n,h,w,1)
             masks_color = masks * (colors * alpha)  # shape(n,h,w,3)
-
             inv_alpha_masks = (1 - masks * alpha).cumprod(0)  # shape(n,h,w,1)
             mcs = masks_color.max(dim=0).values  # shape(n,h,w,3)
 
-            im_gpu = im_gpu.flip(dims=[0])  # flip channel
-            im_gpu = im_gpu.permute(1, 2, 0).contiguous()  # shape(h,w,3)
+            im_gpu = im_gpu.flip(dims=[0]).permute(1, 2, 0).contiguous()  # shape(h,w,3)
             im_gpu = im_gpu * inv_alpha_masks[-1] + mcs
-            im_mask = im_gpu * 255
-            im_mask_np = im_mask.byte().cpu().numpy()
-            self.im[:] = im_mask_np if retina_masks else ops.scale_image(im_mask_np, self.im.shape)
+            self.im[:] = (im_gpu * 255).byte().cpu().numpy()
         if self.pil:
             # Convert im back to PIL and update draw
             self.fromarray(self.im)

{ultralytics-8.3.215 → ultralytics-8.3.217}/ultralytics.egg-info/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ultralytics
-Version: 8.3.215
+Version: 8.3.217
 Summary: Ultralytics YOLO 🚀 for SOTA object detection, multi-object tracking, instance segmentation, pose estimation and image classification.
 Author-email: Glenn Jocher <glenn.jocher@ultralytics.com>, Jing Qiu <jing.qiu@ultralytics.com>
 Maintainer-email: Ultralytics <hello@ultralytics.com>