ultralytics 8.3.75__py3-none-any.whl → 8.3.76__py3-none-any.whl

ultralytics/__init__.py

@@ -1,6 +1,6 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-__version__ = "8.3.75"
+__version__ = "8.3.76"
 
 import os
 

ultralytics/engine/exporter.py

@@ -1560,20 +1560,20 @@ class NMSModel(torch.nn.Module):
 
         preds = self.model(x)
         pred = preds[0] if isinstance(preds, tuple) else preds
+        kwargs = dict(device=pred.device, dtype=pred.dtype)
+        bs = pred.shape[0]
         pred = pred.transpose(-1, -2)  # shape(1,84,6300) to shape(1,6300,84)
         extra_shape = pred.shape[-1] - (4 + len(self.model.names))  # extras from Segment, OBB, Pose
+        if self.args.dynamic and self.args.batch > 1:  # batch size needs to always be same due to loop unroll
+            pad = torch.zeros(torch.max(torch.tensor(self.args.batch - bs), torch.tensor(0)), *pred.shape[1:], **kwargs)
+            pred = torch.cat((pred, pad))
         boxes, scores, extras = pred.split([4, len(self.model.names), extra_shape], dim=2)
         scores, classes = scores.max(dim=-1)
         self.args.max_det = min(pred.shape[1], self.args.max_det)  # in case num_anchors < max_det
         # (N, max_det, 4 coords + 1 class score + 1 class label + extra_shape).
-        out = torch.zeros(
-            boxes.shape[0],
-            self.args.max_det,
-            boxes.shape[-1] + 2 + extra_shape,
-            device=boxes.device,
-            dtype=boxes.dtype,
-        )
-        for i, (box, cls, score, extra) in enumerate(zip(boxes, classes, scores, extras)):
+        out = torch.zeros(bs, self.args.max_det, boxes.shape[-1] + 2 + extra_shape, **kwargs)
+        for i in range(bs):
+            box, cls, score, extra = boxes[i], classes[i], scores[i], extras[i]
             mask = score > self.args.conf
             if self.is_tf:
                 # TFLite GatherND error if mask is empty
@@ -1593,7 +1593,7 @@ class NMSModel(torch.nn.Module):
             if self.args.format == "tflite":  # TFLite is already normalized
                 nmsbox *= multiplier
             else:
-                nmsbox = multiplier * nmsbox / torch.tensor(x.shape[2:], device=box.device, dtype=box.dtype).max()
+                nmsbox = multiplier * nmsbox / torch.tensor(x.shape[2:], **kwargs).max()
             if not self.args.agnostic_nms:  # class-specific NMS
                 end = 2 if self.obb else 4
                 # fully explicit expansion otherwise reshape error
@@ -1624,4 +1624,4 @@ class NMSModel(torch.nn.Module):
             # Zero-pad to max_det size to avoid reshape error
             pad = (0, 0, 0, self.args.max_det - dets.shape[0])
             out[i] = torch.nn.functional.pad(dets, pad)
-        return (out, preds[1]) if self.model.task == "segment" else out
+        return (out[:bs], preds[1]) if self.model.task == "segment" else out[:bs]

ultralytics/engine/model.py

@@ -122,6 +122,7 @@ class Model(torch.nn.Module):
         self.metrics = None  # validation/training metrics
         self.session = None  # HUB session
         self.task = task  # task type
+        self.model_name = None  # model name
         model = str(model).strip()
 
         # Check if Ultralytics HUB model from https://hub.ultralytics.com

ultralytics/engine/results.py

@@ -1016,7 +1016,7 @@ class Boxes(BaseTensor):
         xyxy (torch.Tensor | numpy.ndarray): Boxes in [x1, y1, x2, y2] format.
         conf (torch.Tensor | numpy.ndarray): Confidence scores for each box.
         cls (torch.Tensor | numpy.ndarray): Class labels for each box.
-        id (torch.Tensor | numpy.ndarray): Tracking IDs for each box (if available).
+        id (torch.Tensor | None): Tracking IDs for each box (if available).
         xywh (torch.Tensor | numpy.ndarray): Boxes in [x, y, width, height] format.
         xyxyn (torch.Tensor | numpy.ndarray): Normalized [x1, y1, x2, y2] boxes relative to orig_shape.
         xywhn (torch.Tensor | numpy.ndarray): Normalized [x, y, width, height] boxes relative to orig_shape.

ultralytics/engine/trainer.py

@@ -493,7 +493,7 @@ class BaseTrainer:
             memory = 0
         else:
             memory = torch.cuda.memory_reserved()
-        return memory / 1e9
+        return memory / (2**30)
 
     def _clear_memory(self):
         """Clear accelerator memory on different platforms."""

ultralytics/trackers/track.py

@@ -66,25 +66,23 @@ def on_predict_postprocess_end(predictor: object, persist: bool = False) -> None
         >>> predictor = YourPredictorClass()
         >>> on_predict_postprocess_end(predictor, persist=True)
     """
-    path, im0s = predictor.batch[:2]
-
     is_obb = predictor.args.task == "obb"
     is_stream = predictor.dataset.mode == "stream"
-    for i in range(len(im0s)):
+    for i, result in enumerate(predictor.results):
         tracker = predictor.trackers[i if is_stream else 0]
-        vid_path = predictor.save_dir / Path(path[i]).name
+        vid_path = predictor.save_dir / Path(result.path).name
         if not persist and predictor.vid_path[i if is_stream else 0] != vid_path:
             tracker.reset()
             predictor.vid_path[i if is_stream else 0] = vid_path
 
-        det = (predictor.results[i].obb if is_obb else predictor.results[i].boxes).cpu().numpy()
+        det = (result.obb if is_obb else result.boxes).cpu().numpy()
         if len(det) == 0:
             continue
-        tracks = tracker.update(det, im0s[i])
+        tracks = tracker.update(det, result.orig_img)
         if len(tracks) == 0:
             continue
         idx = tracks[:, -1].astype(int)
-        predictor.results[i] = predictor.results[i][idx]
+        predictor.results[i] = result[idx]
 
         update_args = {"obb" if is_obb else "boxes": torch.as_tensor(tracks[:, :-1])}
         predictor.results[i].update(**update_args)

ultralytics/utils/torch_utils.py

@@ -302,15 +302,22 @@ def model_info(model, detailed=False, verbose=True, imgsz=640):
         return
     n_p = get_num_params(model)  # number of parameters
     n_g = get_num_gradients(model)  # number of gradients
-    n_l = len(list(model.modules()))  # number of layers
+    layers = __import__("collections").OrderedDict((n, m) for n, m in model.named_modules() if len(m._modules) == 0)
+    n_l = len(layers)  # number of layers
     if detailed:
-        LOGGER.info(f"{'layer':>5}{'name':>40}{'gradient':>10}{'parameters':>12}{'shape':>20}{'mu':>10}{'sigma':>10}")
-        for i, (name, p) in enumerate(model.named_parameters()):
-            name = name.replace("module_list.", "")
-            LOGGER.info(
-                f"{i:>5g}{name:>40s}{p.requires_grad!r:>10}{p.numel():>12g}{str(list(p.shape)):>20s}"
-                f"{p.mean():>10.3g}{p.std():>10.3g}{str(p.dtype):>15s}"
-            )
+        h = f"{'layer':>5}{'name':>40}{'type':>20}{'gradient':>10}{'parameters':>12}{'shape':>20}{'mu':>10}{'sigma':>10}"
+        LOGGER.info(h)
+        for i, (mn, m) in enumerate(layers.items()):
+            mn = mn.replace("module_list.", "")
+            mt = m.__class__.__name__
+            if len(m._parameters):
+                for pn, p in m.named_parameters():
+                    LOGGER.info(
+                        f"{i:>5g}{mn + '.' + pn:>40}{mt:>20}{p.requires_grad!r:>10}{p.numel():>12g}"
+                        f"{str(list(p.shape)):>20}{p.mean():>10.3g}{p.std():>10.3g}{str(p.dtype).replace('torch.', ''):>15}"
+                    )
+            else:  # layers with no learnable params
+                LOGGER.info(f"{i:>5g}{mn:>40}{mt:>20}{False!r:>10}{0:>12g}{str([]):>20}{'-':>10}{'-':>10}{'-':>15}")
 
     flops = get_flops(model, imgsz)  # imgsz may be int or list, i.e. imgsz=640 or imgsz=[640, 320]
     fused = " (fused)" if getattr(model, "is_fused", lambda: False)() else ""

{ultralytics-8.3.75.dist-info → ultralytics-8.3.76.dist-info}/METADATA

@@ -1,6 +1,6 @@
 Metadata-Version: 2.2
 Name: ultralytics
-Version: 8.3.75
+Version: 8.3.76
 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-8.3.75.dist-info → ultralytics-8.3.76.dist-info}/RECORD

@@ -7,7 +7,7 @@ tests/test_exports.py,sha256=T_z_NUS9URQXv83k5XNLHTuksJ8srtzbZnWuiiQWM98,9260
 tests/test_integrations.py,sha256=p3DMnnPMKsV0Qm82JVJUIY1UZ67xRgF9E8AaL76TEHE,6154
 tests/test_python.py,sha256=tW-EFJC2rjl_DvAa8khXGWYdypseQjrLjGHhe2p9r9A,23238
 tests/test_solutions.py,sha256=aY0G3vNzXGCENG9FD76MfUp7jgzeESPsUvbvQYBUvH0,4205
-ultralytics/__init__.py,sha256=V35DQdcyQzSsLZd4nWJc6HD71QYZmWTkqcv_BkpwpW4,709
+ultralytics/__init__.py,sha256=EJlzPDNmMx9lP1HbgFSshFYdnHAVry65hDNaGnuXWqU,709
 ultralytics/assets/bus.jpg,sha256=wCAZxJecGR63Od3ZRERe9Aja1Weayrb9Ug751DS_vGM,137419
 ultralytics/assets/zidane.jpg,sha256=Ftc4aeMmen1O0A3o6GCDO9FlfBslLpTAw0gnetx7bts,50427
 ultralytics/cfg/__init__.py,sha256=qP44HnFP4QcC5FQz29A-EGTuwdtxXAzPvw_IvCVmiqA,39771
@@ -102,11 +102,11 @@ ultralytics/data/loaders.py,sha256=JOwXbz-dxgG2bx0_cQHp-olz5FleoCX8EzrUvZ77vvg,2
 ultralytics/data/split_dota.py,sha256=YI-i2MqdiBt06W67TJnBXQHJrqTnkJDJ3zzoL0UZVro,10733
 ultralytics/data/utils.py,sha256=5YMU5396oAFPwTy2y0MCU2WipF6Rt-7xNtmHKRCA4fI,33838
 ultralytics/engine/__init__.py,sha256=lm6MckFYCPTbqIoX7w0s_daxdjNeBeKW6DXppv1-QUM,70
-ultralytics/engine/exporter.py,sha256=P2kMamiLXaVUCEjYzvHx4xF7WdcnjHyripCCo1poKoA,76864
-ultralytics/engine/model.py,sha256=8CnLnd_c8Ecey4q2JZFJBbUPOYflr5cgjJnw4sH3Vyo,53382
+ultralytics/engine/exporter.py,sha256=nrO0UdRMzhb_hp-IXAstBmMHJoax-P7Fqe7a8u2954A,77113
+ultralytics/engine/model.py,sha256=s8HsSBvdRgSbnKGULr7YW-ZWJKJsQpOoHd9Aih_nMt0,53427
 ultralytics/engine/predictor.py,sha256=jiYDAjupOlRUpPvw9tu7or9PjXtLm-YCRiawANtWxj0,17881
-ultralytics/engine/results.py,sha256=8iHooY3IpBsARBo9LsQJYUfJHlcXk7T7urB3gP6rViU,78120
-ultralytics/engine/trainer.py,sha256=6LTw_52KBLuaQf6rAn-VQ8702cibBkGoaom-aKMbQrw,37417
+ultralytics/engine/results.py,sha256=hWlO2e58BPUJ5R4Jl4iirBPaZ8BypcNu_cNQ2NHpUqM,78111
+ultralytics/engine/trainer.py,sha256=hrqaO3cgf0VPVLHKv0tHk4W3gcasgqq_KF-DkgnIjus,37421
 ultralytics/engine/tuner.py,sha256=EUlTs7KJQ2RVABm8pihr_14M_Z2kGSzJaWH-Y9TJYDw,11976
 ultralytics/engine/validator.py,sha256=r27X8HGeDEwq7V5sFjEQH_3EnP1CyG-HcOLpFABUisU,15034
 ultralytics/hub/__init__.py,sha256=1ifzSYV0PIT4ZWOm2V7HnpGyY3G3hCz0malw3AXHFlY,5660
@@ -199,7 +199,7 @@ ultralytics/trackers/__init__.py,sha256=Zlu_Ig5osn7hqch_g5Be_e4pwZUkeeTQiesJCi0p
 ultralytics/trackers/basetrack.py,sha256=h0fcxzCdZf_56H1NG_mCIATaz_cWj0e9aJKE1xgmtFQ,4451
 ultralytics/trackers/bot_sort.py,sha256=xUmlj0agS0PGjy97N3C0jLMV07yvsurE5QcnuoV_Ecw,10522
 ultralytics/trackers/byte_tracker.py,sha256=CT_Yjw2ahHoprEfNcTM0hBMoGss5qcqt6Paxk956lYU,20846
-ultralytics/trackers/track.py,sha256=RWG2sc2HkGaajwLMZp7A_5HusxYKNR8gky4igvZpzug,4021
+ultralytics/trackers/track.py,sha256=PtGB4CTMdylvccrzho37nysMvVS8gSINGFgZY0n-AuU,3973
 ultralytics/trackers/utils/__init__.py,sha256=lm6MckFYCPTbqIoX7w0s_daxdjNeBeKW6DXppv1-QUM,70
 ultralytics/trackers/utils/gmc.py,sha256=kU54RozuGJcAVlyb5_HjXiNIUIX5VuH613AMc6Gdnwg,14597
 ultralytics/trackers/utils/kalman_filter.py,sha256=OBvemZXptgn9v1sgBLvFomCqOWwjIB3-8wBbc8nakHo,21377
@@ -219,7 +219,7 @@ ultralytics/utils/ops.py,sha256=izQr5GvgzmaD-GXaqxIjLE525JnvgLetOtuq_EOaxM8,3458
 ultralytics/utils/patches.py,sha256=ARR89dP4YKq7Dd3g2eU-ukbnc2lo3BELukL_1c_d854,3298
 ultralytics/utils/plotting.py,sha256=hKji4TyxAmCXdSL264VX6dsC2AZYiL9StShI02dcAOM,62990
 ultralytics/utils/tal.py,sha256=DO-c006HEI62pcrNRpmt4lpqJPC5yu3veRDOvUuExno,18498
-ultralytics/utils/torch_utils.py,sha256=AsdLP_MADVY9sq4mF3u4GMCDvx9Z32flQZKmiVy4LcA,33404
+ultralytics/utils/torch_utils.py,sha256=Q7B84IsAs29pehadJJ25jQOxuCTGVMj1x8TJNYLsijs,33878
 ultralytics/utils/triton.py,sha256=2L1_rZ8xCJEjexRVj75g9YU-u4tQln_DJ5N1Yr_0bSs,4071
 ultralytics/utils/tuner.py,sha256=gySDBzTlq_klTOq6CGEyUN58HXzPCulObaMBHacXzHo,6294
 ultralytics/utils/callbacks/__init__.py,sha256=hzL63Rce6VkZhP4Lcim9LKjadixaQG86nKqPhk7IkS0,242
@@ -233,9 +233,9 @@ ultralytics/utils/callbacks/neptune.py,sha256=waZ_bRu0-qBKujTLuqonC2gx2DkgBuVnfq
 ultralytics/utils/callbacks/raytune.py,sha256=A_NVWjyPNf2m6iB-mbW7SMpyqM9QBvpbPa-MCMFMtdk,727
 ultralytics/utils/callbacks/tensorboard.py,sha256=JHOEVlNQ5dYJPd4Z-EvqbXowuK5uA0p8wPgyyaIUQs0,4194
 ultralytics/utils/callbacks/wb.py,sha256=ayhT2y62AcSOacnawshATU0rWrlSFQ77mrGgBdRl3W4,7086
-ultralytics-8.3.75.dist-info/LICENSE,sha256=DZak_2itbUtvHzD3E7GNUYSRK6jdOJ-GqncQ2weavLA,34523
-ultralytics-8.3.75.dist-info/METADATA,sha256=7kTsfctoPrVnBtozBr7k4N8h1W8aFqHg-7_CmpIVo4w,35158
-ultralytics-8.3.75.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
-ultralytics-8.3.75.dist-info/entry_points.txt,sha256=YM_wiKyTe9yRrsEfqvYolNO5ngwfoL4-NwgKzc8_7sI,93
-ultralytics-8.3.75.dist-info/top_level.txt,sha256=XP49TwiMw4QGsvTLSYiJhz1xF_k7ev5mQ8jJXaXi45Q,12
-ultralytics-8.3.75.dist-info/RECORD,,
+ultralytics-8.3.76.dist-info/LICENSE,sha256=DZak_2itbUtvHzD3E7GNUYSRK6jdOJ-GqncQ2weavLA,34523
+ultralytics-8.3.76.dist-info/METADATA,sha256=8w-KvGSLIOXISAZ524SnU3jgFOca5sxJY9NGByF7T-0,35158
+ultralytics-8.3.76.dist-info/WHEEL,sha256=In9FTNxeP60KnTkGw7wk6mJPYd_dQSjEZmXdBdMCI-8,91
+ultralytics-8.3.76.dist-info/entry_points.txt,sha256=YM_wiKyTe9yRrsEfqvYolNO5ngwfoL4-NwgKzc8_7sI,93
+ultralytics-8.3.76.dist-info/top_level.txt,sha256=XP49TwiMw4QGsvTLSYiJhz1xF_k7ev5mQ8jJXaXi45Q,12
+ultralytics-8.3.76.dist-info/RECORD,,