ultralytics 8.2.58__tar.gz → 8.2.60__tar.gz

{ultralytics-8.2.58/ultralytics.egg-info → ultralytics-8.2.60}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ultralytics
-Version: 8.2.58
+Version: 8.2.60
 Summary: Ultralytics YOLOv8 for SOTA object detection, multi-object tracking, instance segmentation, pose estimation and image classification.
 Author: Glenn Jocher, Ayush Chaurasia, Jing Qiu
 Maintainer: Glenn Jocher, Ayush Chaurasia, Jing Qiu

{ultralytics-8.2.58 → ultralytics-8.2.60}/ultralytics/__init__.py

@@ -1,6 +1,6 @@
 # Ultralytics YOLO 🚀, AGPL-3.0 license
 
-__version__ = "8.2.58"
+__version__ = "8.2.60"
 
 import os
 

{ultralytics-8.2.58 → ultralytics-8.2.60}/ultralytics/engine/exporter.py

@@ -563,7 +563,7 @@ class Exporter:
                 LOGGER.warning(f"{prefix} WARNING ⚠️ PNNX GitHub assets not found: {e}, using default {asset}")
             unzip_dir = safe_download(f"https://github.com/pnnx/pnnx/releases/download/{release}/{asset}", delete=True)
             if check_is_path_safe(Path.cwd(), unzip_dir):  # avoid path traversal security vulnerability
-                (unzip_dir / name).rename(pnnx)  # move binary to ROOT
+                shutil.move(src=unzip_dir / name, dst=pnnx)  # move binary to ROOT
                 pnnx.chmod(0o777)  # set read, write, and execute permissions for everyone
                 shutil.rmtree(unzip_dir)  # delete unzip dir
 

{ultralytics-8.2.58 → ultralytics-8.2.60}/ultralytics/models/yolo/detect/val.py

@@ -41,6 +41,11 @@ class DetectionValidator(BaseValidator):
         self.iouv = torch.linspace(0.5, 0.95, 10)  # IoU vector for mAP@0.5:0.95
         self.niou = self.iouv.numel()
         self.lb = []  # for autolabelling
+        if self.args.save_hybrid:
+            LOGGER.warning(
+                "WARNING ⚠️ 'save_hybrid=True' will append ground truth to predictions for autolabelling.\n"
+                "WARNING ⚠️ 'save_hybrid=True' will cause incorrect mAP.\n"
+            )
 
     def preprocess(self, batch):
         """Preprocesses batch of images for YOLO training."""
@@ -53,21 +58,21 @@ class DetectionValidator(BaseValidator):
             height, width = batch["img"].shape[2:]
             nb = len(batch["img"])
             bboxes = batch["bboxes"] * torch.tensor((width, height, width, height), device=self.device)
-            self.lb = (
-                [
-                    torch.cat([batch["cls"][batch["batch_idx"] == i], bboxes[batch["batch_idx"] == i]], dim=-1)
-                    for i in range(nb)
-                ]
-                if self.args.save_hybrid
-                else []
-            )  # for autolabelling
+            self.lb = [
+                torch.cat([batch["cls"][batch["batch_idx"] == i], bboxes[batch["batch_idx"] == i]], dim=-1)
+                for i in range(nb)
+            ]
 
         return batch
 
     def init_metrics(self, model):
         """Initialize evaluation metrics for YOLO."""
         val = self.data.get(self.args.split, "")  # validation path
-        self.is_coco = isinstance(val, str) and "coco" in val and val.endswith(f"{os.sep}val2017.txt")  # is COCO
+        self.is_coco = (
+            isinstance(val, str)
+            and "coco" in val
+            and (val.endswith(f"{os.sep}val2017.txt") or val.endswith(f"{os.sep}test-dev2017.txt"))
+        )  # is COCO
         self.is_lvis = isinstance(val, str) and "lvis" in val and not self.is_coco  # is LVIS
         self.class_map = converter.coco80_to_coco91_class() if self.is_coco else list(range(len(model.names)))
         self.args.save_json |= (self.is_coco or self.is_lvis) and not self.training  # run on final val if training COCO
@@ -159,8 +164,12 @@ class DetectionValidator(BaseValidator):
             if self.args.save_json:
                 self.pred_to_json(predn, batch["im_file"][si])
             if self.args.save_txt:
-                file = self.save_dir / "labels" / f'{Path(batch["im_file"][si]).stem}.txt'
-                self.save_one_txt(predn, self.args.save_conf, pbatch["ori_shape"], file)
+                self.save_one_txt(
+                    predn,
+                    self.args.save_conf,
+                    pbatch["ori_shape"],
+                    self.save_dir / "labels" / f'{Path(batch["im_file"][si]).stem}.txt',
+                )
 
     def finalize_metrics(self, *args, **kwargs):
         """Set final values for metrics speed and confusion matrix."""
@@ -260,12 +269,14 @@ class DetectionValidator(BaseValidator):
 
     def save_one_txt(self, predn, save_conf, shape, file):
         """Save YOLO detections to a txt file in normalized coordinates in a specific format."""
-        gn = torch.tensor(shape)[[1, 0, 1, 0]]  # normalization gain whwh
-        for *xyxy, conf, cls in predn.tolist():
-            xywh = (ops.xyxy2xywh(torch.tensor(xyxy).view(1, 4)) / gn).view(-1).tolist()  # normalized xywh
-            line = (cls, *xywh, conf) if save_conf else (cls, *xywh)  # label format
-            with open(file, "a") as f:
-                f.write(("%g " * len(line)).rstrip() % line + "\n")
+        from ultralytics.engine.results import Results
+
+        Results(
+            np.zeros((shape[0], shape[1]), dtype=np.uint8),
+            path=None,
+            names=self.names,
+            boxes=predn[:, :6],
+        ).save_txt(file, save_conf=save_conf)
 
     def pred_to_json(self, predn, filename):
         """Serialize YOLO predictions to COCO json format."""

{ultralytics-8.2.58 → ultralytics-8.2.60}/ultralytics/models/yolo/obb/val.py

@@ -130,13 +130,19 @@ class OBBValidator(DetectionValidator):
 
     def save_one_txt(self, predn, save_conf, shape, file):
         """Save YOLO detections to a txt file in normalized coordinates in a specific format."""
-        gn = torch.tensor(shape)[[1, 0]]  # normalization gain whwh
-        for *xywh, conf, cls, angle in predn.tolist():
-            xywha = torch.tensor([*xywh, angle]).view(1, 5)
-            xyxyxyxy = (ops.xywhr2xyxyxyxy(xywha) / gn).view(-1).tolist()  # normalized xywh
-            line = (cls, *xyxyxyxy, conf) if save_conf else (cls, *xyxyxyxy)  # label format
-            with open(file, "a") as f:
-                f.write(("%g " * len(line)).rstrip() % line + "\n")
+        import numpy as np
+
+        from ultralytics.engine.results import Results
+
+        rboxes = torch.cat([predn[:, :4], predn[:, -1:]], dim=-1)
+        # xywh, r, conf, cls
+        obb = torch.cat([rboxes, predn[:, 4:6]], dim=-1)
+        Results(
+            np.zeros((shape[0], shape[1]), dtype=np.uint8),
+            path=None,
+            names=self.names,
+            obb=obb,
+        ).save_txt(file, save_conf=save_conf)
 
     def eval_json(self, stats):
         """Evaluates YOLO output in JSON format and returns performance statistics."""

{ultralytics-8.2.58 → ultralytics-8.2.60}/ultralytics/models/yolo/pose/val.py

@@ -147,8 +147,14 @@ class PoseValidator(DetectionValidator):
             # 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')
+            if self.args.save_txt:
+                self.save_one_txt(
+                    predn,
+                    pred_kpts,
+                    self.args.save_conf,
+                    pbatch["ori_shape"],
+                    self.save_dir / "labels" / f'{Path(batch["im_file"][si]).stem}.txt',
+                )
 
     def _process_batch(self, detections, gt_bboxes, gt_cls, pred_kpts=None, gt_kpts=None):
         """
@@ -217,6 +223,18 @@ class PoseValidator(DetectionValidator):
             on_plot=self.on_plot,
         )  # pred
 
+    def save_one_txt(self, predn, pred_kpts, save_conf, shape, file):
+        """Save YOLO detections to a txt file in normalized coordinates in a specific format."""
+        from ultralytics.engine.results import Results
+
+        Results(
+            np.zeros((shape[0], shape[1]), dtype=np.uint8),
+            path=None,
+            names=self.names,
+            boxes=predn[:, :6],
+            keypoints=pred_kpts,
+        ).save_txt(file, save_conf=save_conf)
+
     def pred_to_json(self, predn, filename):
         """Converts YOLO predictions to COCO JSON format."""
         stem = Path(filename).stem

{ultralytics-8.2.58 → ultralytics-8.2.60}/ultralytics/models/yolo/segment/val.py

@@ -48,9 +48,8 @@ class SegmentationValidator(DetectionValidator):
         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
+        # more accurate vs faster
+        self.process = ops.process_mask_native if self.args.save_json or self.args.save_txt else ops.process_mask
         self.stats = dict(tp_m=[], tp=[], conf=[], pred_cls=[], target_cls=[], target_img=[])
 
     def get_desc(self):
@@ -148,14 +147,23 @@ class SegmentationValidator(DetectionValidator):
 
             # Save
             if self.args.save_json:
-                pred_masks = ops.scale_image(
-                    pred_masks.permute(1, 2, 0).contiguous().cpu().numpy(),
+                self.pred_to_json(
+                    predn,
+                    batch["im_file"][si],
+                    ops.scale_image(
+                        pred_masks.permute(1, 2, 0).contiguous().cpu().numpy(),
+                        pbatch["ori_shape"],
+                        ratio_pad=batch["ratio_pad"][si],
+                    ),
+                )
+            if self.args.save_txt:
+                self.save_one_txt(
+                    predn,
+                    pred_masks,
+                    self.args.save_conf,
                     pbatch["ori_shape"],
-                    ratio_pad=batch["ratio_pad"][si],
+                    self.save_dir / "labels" / f'{Path(batch["im_file"][si]).stem}.txt',
                 )
-                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."""
@@ -235,6 +243,18 @@ class SegmentationValidator(DetectionValidator):
         )  # pred
         self.plot_masks.clear()
 
+    def save_one_txt(self, predn, pred_masks, save_conf, shape, file):
+        """Save YOLO detections to a txt file in normalized coordinates in a specific format."""
+        from ultralytics.engine.results import Results
+
+        Results(
+            np.zeros((shape[0], shape[1]), dtype=np.uint8),
+            path=None,
+            names=self.names,
+            boxes=predn[:, :6],
+            masks=pred_masks,
+        ).save_txt(file, save_conf=save_conf)
+
     def pred_to_json(self, predn, filename, pred_masks):
         """
         Save one JSON result.

{ultralytics-8.2.58 → ultralytics-8.2.60}/ultralytics/nn/modules/block.py

@@ -855,7 +855,7 @@ class Attention(nn.Module):
         self.head_dim = dim // num_heads
         self.key_dim = int(self.head_dim * attn_ratio)
         self.scale = self.key_dim**-0.5
-        nh_kd = nh_kd = self.key_dim * num_heads
+        nh_kd = self.key_dim * num_heads
         h = dim + nh_kd * 2
         self.qkv = Conv(dim, h, 1, act=False)
         self.proj = Conv(dim, dim, 1, act=False)

{ultralytics-8.2.58 → ultralytics-8.2.60}/ultralytics/solutions/streamlit_inference.py

@@ -99,24 +99,26 @@ def inference():
 
         stop_button = st.button("Stop")  # Button to stop the inference
 
-        prev_time = 0
         while videocapture.isOpened():
             success, frame = videocapture.read()
             if not success:
                 st.warning("Failed to read frame from webcam. Please make sure the webcam is connected properly.")
                 break
 
-            curr_time = time.time()
-            fps = 1 / (curr_time - prev_time)
-            prev_time = curr_time
+            prev_time = time.time()
 
             # Store model predictions
-            if enable_trk:
+            if enable_trk == "Yes":
                 results = model.track(frame, conf=conf, iou=iou, classes=selected_ind, persist=True)
             else:
                 results = model(frame, conf=conf, iou=iou, classes=selected_ind)
             annotated_frame = results[0].plot()  # Add annotations on frame
 
+            # Calculate model FPS
+            curr_time = time.time()
+            fps = 1 / (curr_time - prev_time)
+            prev_time = curr_time
+
             # display frame
             org_frame.image(frame, channels="BGR")
             ann_frame.image(annotated_frame, channels="BGR")

{ultralytics-8.2.58 → ultralytics-8.2.60}/ultralytics/utils/ops.py

@@ -652,27 +652,6 @@ def crop_mask(masks, boxes):
     return masks * ((r >= x1) * (r < x2) * (c >= y1) * (c < y2))
 
 
-def process_mask_upsample(protos, masks_in, bboxes, shape):
-    """
-    Takes the output of the mask head, and applies the mask to the bounding boxes. This produces masks of higher quality
-    but is slower.
-
-    Args:
-        protos (torch.Tensor): [mask_dim, mask_h, mask_w]
-        masks_in (torch.Tensor): [n, mask_dim], n is number of masks after nms
-        bboxes (torch.Tensor): [n, 4], n is number of masks after nms
-        shape (tuple): the size of the input image (h,w)
-
-    Returns:
-        (torch.Tensor): The upsampled masks.
-    """
-    c, mh, mw = protos.shape  # CHW
-    masks = (masks_in @ protos.float().view(c, -1)).view(-1, mh, mw)
-    masks = F.interpolate(masks[None], shape, mode="bilinear", align_corners=False)[0]  # CHW
-    masks = crop_mask(masks, bboxes)  # CHW
-    return masks.gt_(0.0)
-
-
 def process_mask(protos, masks_in, bboxes, shape, upsample=False):
     """
     Apply masks to bounding boxes using the output of the mask head.

{ultralytics-8.2.58 → ultralytics-8.2.60/ultralytics.egg-info}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.1
 Name: ultralytics
-Version: 8.2.58
+Version: 8.2.60
 Summary: Ultralytics YOLOv8 for SOTA object detection, multi-object tracking, instance segmentation, pose estimation and image classification.
 Author: Glenn Jocher, Ayush Chaurasia, Jing Qiu
 Maintainer: Glenn Jocher, Ayush Chaurasia, Jing Qiu