ultralytics 8.3.213__py3-none-any.whl → 8.3.215__py3-none-any.whl

ultralytics/__init__.py

@@ -1,6 +1,6 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-__version__ = "8.3.213"
+__version__ = "8.3.215"
 
 import importlib
 import os

ultralytics/engine/exporter.py

@@ -385,7 +385,7 @@ class Exporter:
             assert not tflite or not ARM64 or not LINUX, "TFLite export with NMS unsupported on ARM64 Linux"
             assert not is_tf_format or TORCH_1_13, "TensorFlow exports with NMS require torch>=1.13"
             assert not onnx or TORCH_1_13, "ONNX export with NMS requires torch>=1.13"
-            if getattr(model, "end2end", False):
+            if getattr(model, "end2end", False) or isinstance(model.model[-1], RTDETRDecoder):
                 LOGGER.warning("'nms=True' is not available for end2end models. Forcing 'nms=False'.")
                 self.args.nms = False
             self.args.conf = self.args.conf or 0.25  # set conf default value for nms export
@@ -1039,7 +1039,7 @@ class Exporter:
             attempt_download_asset(f"{onnx2tf_file}.zip", unzip=True, delete=True)
 
         # Export to ONNX
-        if "rtdetr" in self.model.model[-1]._get_name().lower():
+        if isinstance(self.model.model[-1], RTDETRDecoder):
             self.args.opset = self.args.opset or 19
             assert 16 <= self.args.opset <= 19, "RTDETR export requires opset>=16;<=19"
         self.args.simplify = True

ultralytics/engine/trainer.py

@@ -170,6 +170,8 @@ class BaseTrainer:
         self.tloss = None
         self.loss_names = ["Loss"]
         self.csv = self.save_dir / "results.csv"
+        if self.csv.exists() and not self.args.resume:
+            self.csv.unlink()
         self.plot_idx = [0, 1, 2]
         self.nan_recovery_attempts = 0
 
@@ -820,16 +822,17 @@ class BaseTrainer:
         if ckpt.get("scaler") is not None:
             self.scaler.load_state_dict(ckpt["scaler"])
         if self.ema and ckpt.get("ema"):
+            self.ema = ModelEMA(self.model)  # validation with EMA creates inference tensors that can't be updated
             self.ema.ema.load_state_dict(ckpt["ema"].float().state_dict())
             self.ema.updates = ckpt["updates"]
         self.best_fitness = ckpt.get("best_fitness", 0.0)
 
     def _handle_nan_recovery(self, epoch):
-        """Detect and recover from NaN/Inf loss or fitness collapse by loading last checkpoint."""
-        loss_nan = self.tloss is not None and not torch.isfinite(self.tloss).all()
+        """Detect and recover from NaN/Inf loss and fitness collapse by loading last checkpoint."""
+        loss_nan = self.loss is not None and not self.loss.isfinite()
         fitness_nan = self.fitness is not None and not np.isfinite(self.fitness)
         fitness_collapse = self.best_fitness and self.best_fitness > 0 and self.fitness == 0
-        corrupted = RANK in {-1, 0} and (loss_nan or fitness_nan or fitness_collapse)
+        corrupted = RANK in {-1, 0} and loss_nan and (fitness_nan or fitness_collapse)
         reason = "Loss NaN/Inf" if loss_nan else "Fitness NaN/Inf" if fitness_nan else "Fitness collapse"
         if RANK != -1:  # DDP: broadcast to all ranks
             broadcast_list = [corrupted if RANK == 0 else None]
@@ -844,6 +847,7 @@ class BaseTrainer:
         if self.nan_recovery_attempts > 3:
             raise RuntimeError(f"Training failed: NaN persisted for {self.nan_recovery_attempts} epochs")
         LOGGER.warning(f"{reason} detected (attempt {self.nan_recovery_attempts}/3), recovering from last.pt...")
+        self._model_train()  # set model to train mode before loading checkpoint to avoid inference tensor errors
         _, ckpt = load_checkpoint(self.last)
         ema_state = ckpt["ema"].float().state_dict()
         if not all(torch.isfinite(v).all() for v in ema_state.values() if isinstance(v, torch.Tensor)):

ultralytics/models/yolo/classify/val.py

@@ -205,6 +205,7 @@ class ClassificationValidator(BaseValidator):
             img=batch["img"],
             batch_idx=torch.arange(batch["img"].shape[0]),
             cls=torch.argmax(preds, dim=1),
+            conf=torch.amax(preds, dim=1),
         )
         plot_images(
             batched_preds,

ultralytics/models/yolo/segment/predict.py

@@ -108,6 +108,7 @@ class SegmentationPredictor(DetectionPredictor):
             masks = ops.process_mask(proto, pred[:, 6:], pred[:, :4], img.shape[2:], upsample=True)  # HWC
             pred[:, :4] = ops.scale_boxes(img.shape[2:], pred[:, :4], orig_img.shape)
         if masks is not None:
-            keep = masks.sum((-2, -1)) > 0  # only keep predictions with masks
-            pred, masks = pred[keep], masks[keep]
+            keep = masks.amax((-2, -1)) > 0  # only keep predictions with masks
+            if not all(keep):  # most predictions have masks
+                pred, masks = pred[keep], masks[keep]  # indexing is slow
         return Results(orig_img, path=img_path, names=self.model.names, boxes=pred[:, :6], masks=masks)

ultralytics/utils/export/__init__.py

@@ -8,6 +8,7 @@ from pathlib import Path
 import torch
 
 from ultralytics.utils import IS_JETSON, LOGGER
+from ultralytics.utils.torch_utils import TORCH_2_4
 
 from .imx import torch2imx  # noqa
 
@@ -36,6 +37,7 @@ def torch2onnx(
     Notes:
         Setting `do_constant_folding=True` may cause issues with DNN inference for torch>=1.12.
     """
+    kwargs = {"dynamo": False} if TORCH_2_4 else {}
     torch.onnx.export(
         torch_model,
         im,
@@ -46,6 +48,7 @@ def torch2onnx(
         input_names=input_names,
         output_names=output_names,
         dynamic_axes=dynamic or None,
+        **kwargs,
     )
 
 

ultralytics/utils/ops.py

@@ -517,12 +517,19 @@ def crop_mask(masks, boxes):
     Returns:
         (torch.Tensor): Cropped masks.
     """
-    _, h, w = masks.shape
-    x1, y1, x2, y2 = torch.chunk(boxes[:, :, None], 4, 1)  # x1 shape(n,1,1)
-    r = torch.arange(w, device=masks.device, dtype=x1.dtype)[None, None, :]  # rows shape(1,1,w)
-    c = torch.arange(h, device=masks.device, dtype=x1.dtype)[None, :, None]  # cols shape(1,h,1)
-
-    return masks * ((r >= x1) * (r < x2) * (c >= y1) * (c < y2))
+    n, h, w = masks.shape
+    if n < 50:  # faster for fewer masks (predict)
+        for i, (x1, y1, x2, y2) in enumerate(boxes.round().int()):
+            masks[i, :y1] = 0
+            masks[i, y2:] = 0
+            masks[i, :, :x1] = 0
+            masks[i, :, x2:] = 0
+        return masks
+    else:  # faster for more masks (val)
+        x1, y1, x2, y2 = torch.chunk(boxes[:, :, None], 4, 1)  # x1 shape(n,1,1)
+        r = torch.arange(w, device=masks.device, dtype=x1.dtype)[None, None, :]  # rows shape(1,1,w)
+        c = torch.arange(h, device=masks.device, dtype=x1.dtype)[None, :, None]  # cols shape(1,h,1)
+        return masks * ((r >= x1) * (r < x2) * (c >= y1) * (c < y2))
 
 
 def process_mask(protos, masks_in, bboxes, shape, upsample: bool = False):
@@ -554,7 +561,7 @@ def process_mask(protos, masks_in, bboxes, shape, upsample: bool = False):
 
     masks = crop_mask(masks, downsampled_bboxes)  # CHW
     if upsample:
-        masks = F.interpolate(masks[None], shape, mode="bilinear", align_corners=False)[0]  # CHW
+        masks = F.interpolate(masks[None], shape, mode="bilinear")[0]  # CHW
     return masks.gt_(0.0)
 
 
@@ -600,7 +607,7 @@ def scale_masks(masks, shape, padding: bool = True):
     top, left = (int(round(pad_h - 0.1)), int(round(pad_w - 0.1))) if padding else (0, 0)
     bottom = mh - int(round(pad_h + 0.1))
     right = mw - int(round(pad_w + 0.1))
-    return F.interpolate(masks[..., top:bottom, left:right], shape, mode="bilinear", align_corners=False)  # NCHW masks
+    return F.interpolate(masks[..., top:bottom, left:right], shape, mode="bilinear")  # NCHW masks
 
 
 def scale_coords(img1_shape, coords, img0_shape, ratio_pad=None, normalize: bool = False, padding: bool = True):

ultralytics/utils/plotting.py

@@ -778,10 +778,10 @@ def plot_images(
             idx = batch_idx == i
             classes = cls[idx].astype("int")
             labels = confs is None
+            conf = confs[idx] if confs is not None else None  # check for confidence presence (label vs pred)
 
             if len(bboxes):
                 boxes = bboxes[idx]
-                conf = confs[idx] if confs is not None else None  # check for confidence presence (label vs pred)
                 if len(boxes):
                     if boxes[:, :4].max() <= 1.1:  # if normalized with tolerance 0.1
                         boxes[..., [0, 2]] *= w  # scale to pixels
@@ -805,7 +805,8 @@ def plot_images(
                 for c in classes:
                     color = colors(c)
                     c = names.get(c, c) if names else c
-                    annotator.text([x, y], f"{c}", txt_color=color, box_color=(64, 64, 64, 128))
+                    label = f"{c}" if labels else f"{c} {conf[0]:.1f}"
+                    annotator.text([x, y], label, txt_color=color, box_color=(64, 64, 64, 128))
 
             # Plot keypoints
             if len(kpts):

{ultralytics-8.3.213.dist-info → ultralytics-8.3.215.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ultralytics
-Version: 8.3.213
+Version: 8.3.215
 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-8.3.213.dist-info → ultralytics-8.3.215.dist-info}/RECORD

@@ -7,7 +7,7 @@ tests/test_exports.py,sha256=3o-qqPrPqjD1a_U6KBvwAusZ_Wy6S1WzmuvgRRUXmcA,11099
 tests/test_integrations.py,sha256=ehRcYMpGvUI3KvgsaT1pkN1rXkr7tDSlYYMqIcXyGbg,6220
 tests/test_python.py,sha256=x2q5Wx3eOl32ymmr_4p6srz7ebO-O8zFttuerys_OWg,28083
 tests/test_solutions.py,sha256=oaTz5BttPDIeHkQh9oEaw-O73L4iYDP3Lfe82V7DeKM,13416
-ultralytics/__init__.py,sha256=1UAecgYYPQuMuPeNmOT8HW8hSQkiu5Z6jQ9yehBWUqo,1302
+ultralytics/__init__.py,sha256=dmbmHo4Y45gksyF8apNMs_hdC1hRyuEN84ldiJzcluk,1302
 ultralytics/py.typed,sha256=la67KBlbjXN-_-DfGNcdOcjYumVpKG_Tkw-8n5dnGB4,8
 ultralytics/assets/bus.jpg,sha256=wCAZxJecGR63Od3ZRERe9Aja1Weayrb9Ug751DS_vGM,137419
 ultralytics/assets/zidane.jpg,sha256=Ftc4aeMmen1O0A3o6GCDO9FlfBslLpTAw0gnetx7bts,50427
@@ -121,11 +121,11 @@ ultralytics/data/scripts/get_coco.sh,sha256=UuJpJeo3qQpTHVINeOpmP0NYmg8PhEFE3A8J
 ultralytics/data/scripts/get_coco128.sh,sha256=qmRQl_hOKrsdHrTrnyQuFIH01oDz3lfaz138OgGfLt8,650
 ultralytics/data/scripts/get_imagenet.sh,sha256=hr42H16bM47iT27rgS7MpEo-GeOZAYUQXgr0B2cwn48,1705
 ultralytics/engine/__init__.py,sha256=lm6MckFYCPTbqIoX7w0s_daxdjNeBeKW6DXppv1-QUM,70
-ultralytics/engine/exporter.py,sha256=BFzmv7tn2e9zUPwFspb677o1QzzJlOfcVyl3gXmVGWg,71438
+ultralytics/engine/exporter.py,sha256=zVr6VjYY3iGz47brTlzkBTNAcxhPY4kDbYKIZkz9Lzo,71479
 ultralytics/engine/model.py,sha256=uX6cTFdlLllGRbz8Lr90IZGb4OrtMDIHQEg7DxUqwe8,53449
 ultralytics/engine/predictor.py,sha256=4lfw2RbBDE7939011FcSCuznscrcnMuabZtc8GXaKO4,22735
 ultralytics/engine/results.py,sha256=uQ_tgvdxKAg28pRgb5WCHiqx9Ktu7wYiVbwZy_IJ5bo,71499
-ultralytics/engine/trainer.py,sha256=cd1Qq0SxToCLh7NWIRKKTyWZ-rGQGi3TjwKZ0u02gWk,43529
+ultralytics/engine/trainer.py,sha256=URv3-BKeipw0Szl1xrnTH5cCIU3_SA10mx89GSA7Vs4,43832
 ultralytics/engine/tuner.py,sha256=8uiZ9DSYdjHmbhfiuzbMPw--1DLS3cpfZPeSzJ9dGEA,21664
 ultralytics/engine/validator.py,sha256=s7cKMqj2HgVm-GL9bUc76QBeue2jb4cKPk-uQQG5nck,16949
 ultralytics/hub/__init__.py,sha256=xCF02lzlPKbdmGfO3NxLuXl5Kb0MaBZp_-fAWDHZ8zw,6698
@@ -170,7 +170,7 @@ ultralytics/models/yolo/model.py,sha256=PH8nXl0ZulgjWMr9M-XAK2TcdaBNXX5AzofIhcKb
 ultralytics/models/yolo/classify/__init__.py,sha256=9--HVaNOfI1K7rn_rRqclL8FUAnpfeBrRqEQIaQw2xM,383
 ultralytics/models/yolo/classify/predict.py,sha256=o7pDE8xwjkHUUIIOph7ZVQZyGZyob24dYDQ460v_7R0,4149
 ultralytics/models/yolo/classify/train.py,sha256=juAdpi0wIsnleACkq9Rct9io-Gr1A4gG511VqIUvu8E,9656
-ultralytics/models/yolo/classify/val.py,sha256=vmafe9oCqpy8Elab3jZwxMtXhzHodCVRo_vrsOLLhuQ,10091
+ultralytics/models/yolo/classify/val.py,sha256=FUTTrvIMlFxdJm8dlrsguKsDvfRdDtGNlIMdJ_-PMtE,10134
 ultralytics/models/yolo/detect/__init__.py,sha256=GIRsLYR-kT4JJx7lh4ZZAFGBZj0aebokuU0A7JbjDVA,257
 ultralytics/models/yolo/detect/predict.py,sha256=Vtpqb2gHI7hv9TaBBXsnoScQ8HrSnj0PPOkEu07MwLc,5394
 ultralytics/models/yolo/detect/train.py,sha256=rnmCt0TG5bdySE2TVUsUqwyyF_LTy4dZdlACoM1MhcU,10554
@@ -184,7 +184,7 @@ ultralytics/models/yolo/pose/predict.py,sha256=3fgu4EKcVRKlP7fySDVsngl4ufk2f71P8
 ultralytics/models/yolo/pose/train.py,sha256=AstxnvJcoF5qnDEZSs45U2cGdMdSltX1HuSVwCZqMHQ,4712
 ultralytics/models/yolo/pose/val.py,sha256=MK-GueXmXrl7eZ5WHYjJMghE4AYJTEut7AuS-G5D1gw,12650
 ultralytics/models/yolo/segment/__init__.py,sha256=3IThhZ1wlkY9FvmWm9cE-5-ZyE6F1FgzAtQ6jOOFzzw,275
-ultralytics/models/yolo/segment/predict.py,sha256=HePes5rQ9v3iTCpn3vrIee0SsAsJuJm-X7tHA8Tixc8,5384
+ultralytics/models/yolo/segment/predict.py,sha256=Qf6B4v2O8usK5wHfbre4gkJjEWKidxZRhetWv4nyr6M,5470
 ultralytics/models/yolo/segment/train.py,sha256=5aPK5FDHLzbXb3R5TCpsAr1O6-8rtupOIoDokY8bSDs,3032
 ultralytics/models/yolo/segment/val.py,sha256=fJLDJpK1RZgeMvmtf47BjHhZ9lzX_4QfUuBzGXZqIhA,11289
 ultralytics/models/yolo/world/__init__.py,sha256=nlh8I6t8hMGz_vZg8QSlsUW1R-2eKvn9CGUoPPQEGhA,131
@@ -253,9 +253,9 @@ ultralytics/utils/logger.py,sha256=o_vH4CCgQat6_Sbmwm1sUAJ4muAgVcsUed-WqpGNQZw,1
 ultralytics/utils/loss.py,sha256=wJ0F2DpRTI9-e9adxIm2io0zcXRa0RTWFTOc7WmS1-A,39827
 ultralytics/utils/metrics.py,sha256=DC-JuakuhHfeCeLvUHb7wj1HPhuFakx00rqXicTka5Y,68834
 ultralytics/utils/nms.py,sha256=AVOmPuUTEJqmq2J6rvjq-nHNxYIyabgzHdc41siyA0w,14161
-ultralytics/utils/ops.py,sha256=PW3fgw1d18CA2ZNQZVJqUy054cJ_9tIcxd1XnA0FPgU,26905
+ultralytics/utils/ops.py,sha256=BEmngjdKDwOETKawf0QiLk1M3NT5HQF6KN-zIsWXpm4,27184
 ultralytics/utils/patches.py,sha256=0-2G4jXCIPnMonlft-cPcjfFcOXQS6ODwUDNUwanfg4,6541
-ultralytics/utils/plotting.py,sha256=TtEAUGpGh0cL_5RvUD3jyils5pY1yke1_d_bOvZ3Ivc,47948
+ultralytics/utils/plotting.py,sha256=jpnOxvfabGPBHCP-G-oVAc1PAURhEx90ygEh0xyAW84,48014
 ultralytics/utils/tal.py,sha256=7KQYNyetfx18CNc_bvNG7BDb44CIU3DEu4qziVVvNAE,20869
 ultralytics/utils/torch_utils.py,sha256=FU3tzaAYZP_FIrusfOxVrfgBN2e7u7QvHY9yM-xB3Jc,40332
 ultralytics/utils/tqdm.py,sha256=ny5RIg2OTkWQ7gdaXfYaoIgR0Xn2_hNGB6tUpO2Unns,16137
@@ -273,11 +273,11 @@ ultralytics/utils/callbacks/platform.py,sha256=a7T_8htoBB0uX1WIc392UJnhDjxkRyQMv
 ultralytics/utils/callbacks/raytune.py,sha256=S6Bq16oQDQ8BQgnZzA0zJHGN_BBr8iAM_WtGoLiEcwg,1283
 ultralytics/utils/callbacks/tensorboard.py,sha256=_4nfGK1dDLn6ijpvphBDhc-AS8qhS3jjY2CAWB7SNF0,5283
 ultralytics/utils/callbacks/wb.py,sha256=ngQO8EJ1kxJDF1YajScVtzBbm26jGuejA0uWeOyvf5A,7685
-ultralytics/utils/export/__init__.py,sha256=jQtf716PP0jt7bMoY9FkqmjG26KbvDzuR84jGhaBi2U,9901
+ultralytics/utils/export/__init__.py,sha256=eZg5z2I61k8H0ykQLc22HhKwFRsLxwuSlDVMuUlYXfU,10023
 ultralytics/utils/export/imx.py,sha256=Jl5nuNxqaP_bY5yrV2NypmoJSrexHE71TxR72SDdjcg,11394
-ultralytics-8.3.213.dist-info/licenses/LICENSE,sha256=DZak_2itbUtvHzD3E7GNUYSRK6jdOJ-GqncQ2weavLA,34523
-ultralytics-8.3.213.dist-info/METADATA,sha256=zqGruJez5idEZDj2scHT0U4ngoHqw_uD17u250Q9o50,37667
-ultralytics-8.3.213.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
-ultralytics-8.3.213.dist-info/entry_points.txt,sha256=YM_wiKyTe9yRrsEfqvYolNO5ngwfoL4-NwgKzc8_7sI,93
-ultralytics-8.3.213.dist-info/top_level.txt,sha256=XP49TwiMw4QGsvTLSYiJhz1xF_k7ev5mQ8jJXaXi45Q,12
-ultralytics-8.3.213.dist-info/RECORD,,
+ultralytics-8.3.215.dist-info/licenses/LICENSE,sha256=DZak_2itbUtvHzD3E7GNUYSRK6jdOJ-GqncQ2weavLA,34523
+ultralytics-8.3.215.dist-info/METADATA,sha256=z9qikjofNwe1ERqgaBi9v8igy3gcAHpve13eV1ftuWc,37667
+ultralytics-8.3.215.dist-info/WHEEL,sha256=_zCd3N1l69ArxyTb8rzEoP9TpbYXkqRFSNOD5OuxnTs,91
+ultralytics-8.3.215.dist-info/entry_points.txt,sha256=YM_wiKyTe9yRrsEfqvYolNO5ngwfoL4-NwgKzc8_7sI,93
+ultralytics-8.3.215.dist-info/top_level.txt,sha256=XP49TwiMw4QGsvTLSYiJhz1xF_k7ev5mQ8jJXaXi45Q,12
+ultralytics-8.3.215.dist-info/RECORD,,