ultralytics-opencv-headless 8.3.253__py3-none-any.whl → 8.4.1__py3-none-any.whl

ultralytics/utils/callbacks/platform.py

@@ -66,9 +66,11 @@ def resolve_platform_uri(uri, hard=True):
 
     api_key = os.getenv("ULTRALYTICS_API_KEY") or SETTINGS.get("api_key")
     if not api_key:
-        raise ValueError(f"ULTRALYTICS_API_KEY required for '{uri}'. Get key at https://alpha.ultralytics.com/settings")
+        raise ValueError(
+            f"ULTRALYTICS_API_KEY required for '{uri}'. Get key at https://platform.ultralytics.com/settings"
+        )
 
-    base = "https://alpha.ultralytics.com/api/webhooks"
+    base = "https://platform.ultralytics.com/api/webhooks"
     headers = {"Authorization": f"Bearer {api_key}"}
 
     # ul://username/datasets/slug
@@ -150,7 +152,7 @@ def _send(event, data, project, name, model_id=None):
         if model_id:
             payload["modelId"] = model_id
         r = requests.post(
-            "https://alpha.ultralytics.com/api/webhooks/training/metrics",
+            "https://platform.ultralytics.com/api/webhooks/training/metrics",
             json=payload,
             headers={"Authorization": f"Bearer {_api_key}"},
             timeout=10,
@@ -176,7 +178,7 @@ def _upload_model(model_path, project, name):
 
         # Get signed upload URL
         response = requests.post(
-            "https://alpha.ultralytics.com/api/webhooks/models/upload",
+            "https://platform.ultralytics.com/api/webhooks/models/upload",
             json={"project": project, "name": name, "filename": model_path.name},
             headers={"Authorization": f"Bearer {_api_key}"},
             timeout=10,
@@ -193,7 +195,7 @@ def _upload_model(model_path, project, name):
                 timeout=600,  # 10 min timeout for large models
             ).raise_for_status()
 
-        # url = f"https://alpha.ultralytics.com/{project}/{name}"
+        # url = f"https://platform.ultralytics.com/{project}/{name}"
         # LOGGER.info(f"{PREFIX}Model uploaded to {url}")
         return data.get("gcsPath")
 
@@ -276,7 +278,7 @@ def on_pretrain_routine_start(trainer):
     trainer._platform_last_upload = time()
 
     project, name = _get_project_name(trainer)
-    url = f"https://alpha.ultralytics.com/{project}/{name}"
+    url = f"https://platform.ultralytics.com/{project}/{name}"
     LOGGER.info(f"{PREFIX}Streaming to {url}")
 
     # Create callback to send console output to Platform
@@ -437,7 +439,7 @@ def on_train_end(trainer):
         name,
         getattr(trainer, "_platform_model_id", None),
     )
-    url = f"https://alpha.ultralytics.com/{project}/{name}"
+    url = f"https://platform.ultralytics.com/{project}/{name}"
     LOGGER.info(f"{PREFIX}View results at {url}")
 
 

ultralytics/utils/downloads.py

@@ -18,12 +18,14 @@ GITHUB_ASSETS_NAMES = frozenset(
     [f"yolov8{k}{suffix}.pt" for k in "nsmlx" for suffix in ("", "-cls", "-seg", "-pose", "-obb", "-oiv7")]
     + [f"yolo11{k}{suffix}.pt" for k in "nsmlx" for suffix in ("", "-cls", "-seg", "-pose", "-obb")]
     + [f"yolo12{k}{suffix}.pt" for k in "nsmlx" for suffix in ("",)]  # detect models only currently
+    + [f"yolo26{k}{suffix}.pt" for k in "nsmlx" for suffix in ("", "-cls", "-seg", "-pose", "-obb")]
     + [f"yolov5{k}{resolution}u.pt" for k in "nsmlx" for resolution in ("", "6")]
     + [f"yolov3{k}u.pt" for k in ("", "-spp", "-tiny")]
     + [f"yolov8{k}-world.pt" for k in "smlx"]
     + [f"yolov8{k}-worldv2.pt" for k in "smlx"]
     + [f"yoloe-v8{k}{suffix}.pt" for k in "sml" for suffix in ("-seg", "-seg-pf")]
     + [f"yoloe-11{k}{suffix}.pt" for k in "sml" for suffix in ("-seg", "-seg-pf")]
+    + [f"yoloe-26{k}{suffix}.pt" for k in "nsmlx" for suffix in ("-seg", "-seg-pf")]
     + [f"yolov9{k}.pt" for k in "tsmce"]
     + [f"yolov10{k}.pt" for k in "nsmblx"]
     + [f"yolo_nas_{k}.pt" for k in "sml"]
@@ -424,7 +426,7 @@ def get_github_assets(
 def attempt_download_asset(
     file: str | Path,
     repo: str = "ultralytics/assets",
-    release: str = "v8.3.0",
+    release: str = "v8.4.0",
     **kwargs,
 ) -> str:
     """Attempt to download a file from GitHub release assets if it is not found locally.

ultralytics/utils/export/engine.py

@@ -143,7 +143,7 @@ def onnx2engine(
         for inp in inputs:
             profile.set_shape(inp.name, min=min_shape, opt=shape, max=max_shape)
         config.add_optimization_profile(profile)
-        if int8:
+        if int8 and not is_trt10:  # deprecated in TensorRT 10, causes internal errors
             config.set_calibration_profile(profile)
 
     LOGGER.info(f"{prefix} building {'INT8' if int8 else 'FP' + ('16' if half else '32')} engine as {engine_file}")
@@ -226,12 +226,21 @@ def onnx2engine(
         config.set_flag(trt.BuilderFlag.FP16)
 
     # Write file
-    build = builder.build_serialized_network if is_trt10 else builder.build_engine
-    with build(network, config) as engine, open(engine_file, "wb") as t:
-        # Metadata
-        if metadata is not None:
-            meta = json.dumps(metadata)
-            t.write(len(meta).to_bytes(4, byteorder="little", signed=True))
-            t.write(meta.encode())
-        # Model
-        t.write(engine if is_trt10 else engine.serialize())
+    if is_trt10:
+        # TensorRT 10+ returns bytes directly, not a context manager
+        engine = builder.build_serialized_network(network, config)
+        if engine is None:
+            raise RuntimeError("TensorRT engine build failed, check logs for errors")
+        with open(engine_file, "wb") as t:
+            if metadata is not None:
+                meta = json.dumps(metadata)
+                t.write(len(meta).to_bytes(4, byteorder="little", signed=True))
+                t.write(meta.encode())
+            t.write(engine)
+    else:
+        with builder.build_engine(network, config) as engine, open(engine_file, "wb") as t:
+            if metadata is not None:
+                meta = json.dumps(metadata)
+                t.write(len(meta).to_bytes(4, byteorder="little", signed=True))
+                t.write(meta.encode())
+            t.write(engine.serialize())

ultralytics/utils/export/imx.py

@@ -21,27 +21,27 @@ from ultralytics.utils.torch_utils import copy_attr
 MCT_CONFIG = {
     "YOLO11": {
         "detect": {
-            "layer_names": ["sub", "mul_2", "add_14", "cat_21"],
+            "layer_names": ["sub", "mul_2", "add_14", "cat_19"],
             "weights_memory": 2585350.2439,
             "n_layers": 238,
         },
         "pose": {
-            "layer_names": ["sub", "mul_2", "add_14", "cat_22", "cat_23", "mul_4", "add_15"],
+            "layer_names": ["sub", "mul_2", "add_14", "cat_21", "cat_22", "mul_4", "add_15"],
             "weights_memory": 2437771.67,
             "n_layers": 257,
         },
         "classify": {"layer_names": [], "weights_memory": np.inf, "n_layers": 112},
-        "segment": {"layer_names": ["sub", "mul_2", "add_14", "cat_22"], "weights_memory": 2466604.8, "n_layers": 265},
+        "segment": {"layer_names": ["sub", "mul_2", "add_14", "cat_21"], "weights_memory": 2466604.8, "n_layers": 265},
     },
     "YOLOv8": {
-        "detect": {"layer_names": ["sub", "mul", "add_6", "cat_17"], "weights_memory": 2550540.8, "n_layers": 168},
+        "detect": {"layer_names": ["sub", "mul", "add_6", "cat_15"], "weights_memory": 2550540.8, "n_layers": 168},
         "pose": {
-            "layer_names": ["add_7", "mul_2", "cat_19", "mul", "sub", "add_6", "cat_18"],
+            "layer_names": ["add_7", "mul_2", "cat_17", "mul", "sub", "add_6", "cat_18"],
             "weights_memory": 2482451.85,
             "n_layers": 187,
         },
         "classify": {"layer_names": [], "weights_memory": np.inf, "n_layers": 73},
-        "segment": {"layer_names": ["sub", "mul", "add_6", "cat_18"], "weights_memory": 2580060.0, "n_layers": 195},
+        "segment": {"layer_names": ["sub", "mul", "add_6", "cat_17"], "weights_memory": 2580060.0, "n_layers": 195},
     },
 }
 
@@ -104,10 +104,13 @@ class FXModel(torch.nn.Module):
         return x
 
 
-def _inference(self, x: list[torch.Tensor]) -> tuple[torch.Tensor]:
+def _inference(self, x: list[torch.Tensor] | dict[str, torch.Tensor]) -> tuple[torch.Tensor]:
     """Decode boxes and cls scores for imx object detection."""
-    x_cat = torch.cat([xi.view(x[0].shape[0], self.no, -1) for xi in x], 2)
-    box, cls = x_cat.split((self.reg_max * 4, self.nc), 1)
+    if isinstance(x, dict):
+        box, cls = x["boxes"], x["scores"]
+    else:
+        x_cat = torch.cat([xi.view(x[0].shape[0], self.no, -1) for xi in x], 2)
+        box, cls = x_cat.split((self.reg_max * 4, self.nc), 1)
     dbox = self.decode_bboxes(self.dfl(box), self.anchors.unsqueeze(0)) * self.strides
     return dbox.transpose(1, 2), cls.sigmoid().permute(0, 2, 1)
 
@@ -115,9 +118,17 @@ def _inference(self, x: list[torch.Tensor]) -> tuple[torch.Tensor]:
 def pose_forward(self, x: list[torch.Tensor]) -> tuple[torch.Tensor, torch.Tensor, torch.Tensor]:
     """Forward pass for imx pose estimation, including keypoint decoding."""
     bs = x[0].shape[0]  # batch size
-    kpt = torch.cat([self.cv4[i](x[i]).view(bs, self.nk, -1) for i in range(self.nl)], -1)  # (bs, 17*3, h*w)
+    nk_out = getattr(self, "nk_output", self.nk)
+    kpt = torch.cat([self.cv4[i](x[i]).view(bs, nk_out, -1) for i in range(self.nl)], -1)
+
+    # If using Pose26 with 5 dims, convert to 3 dims for export
+    if hasattr(self, "nk_output") and self.nk_output != self.nk:
+        spatial = kpt.shape[-1]
+        kpt = kpt.view(bs, self.kpt_shape[0], self.kpt_shape[1] + 2, spatial)
+        kpt = kpt[:, :, :-2, :]  # Remove sigma_x, sigma_y
+        kpt = kpt.view(bs, self.nk, spatial)
     x = Detect.forward(self, x)
-    pred_kpt = self.kpts_decode(bs, kpt)
+    pred_kpt = self.kpts_decode(kpt)
     return *x, pred_kpt.permute(0, 2, 1)
 
 

ultralytics/utils/export/tensorflow.py

@@ -2,12 +2,13 @@
 
 from __future__ import annotations
 
+from functools import partial
 from pathlib import Path
 
 import numpy as np
 import torch
 
-from ultralytics.nn.modules import Detect, Pose
+from ultralytics.nn.modules import Detect, Pose, Pose26
 from ultralytics.utils import LOGGER
 from ultralytics.utils.downloads import attempt_download_asset
 from ultralytics.utils.files import spaces_in_path
@@ -15,43 +16,42 @@ from ultralytics.utils.tal import make_anchors
 
 
 def tf_wrapper(model: torch.nn.Module) -> torch.nn.Module:
-    """A wrapper to add TensorFlow compatible inference methods to Detect and Pose layers."""
+    """A wrapper for TensorFlow export compatibility (TF-specific handling is now in head modules)."""
     for m in model.modules():
         if not isinstance(m, Detect):
             continue
         import types
 
-        m._inference = types.MethodType(_tf_inference, m)
-        if type(m) is Pose:
-            m.kpts_decode = types.MethodType(tf_kpts_decode, m)
+        m._get_decode_boxes = types.MethodType(_tf_decode_boxes, m)
+        if isinstance(m, Pose):
+            m.kpts_decode = types.MethodType(partial(_tf_kpts_decode, is_pose26=type(m) is Pose26), m)
     return model
 
 
-def _tf_inference(self, x: list[torch.Tensor]) -> tuple[torch.Tensor]:
-    """Decode boxes and cls scores for tf object detection."""
-    shape = x[0].shape  # BCHW
-    x_cat = torch.cat([xi.view(x[0].shape[0], self.no, -1) for xi in x], 2)
-    box, cls = x_cat.split((self.reg_max * 4, self.nc), 1)
-    if self.dynamic or self.shape != shape:
-        self.anchors, self.strides = (x.transpose(0, 1) for x in make_anchors(x, self.stride, 0.5))
+def _tf_decode_boxes(self, x: dict[str, torch.Tensor]) -> torch.Tensor:
+    """Decode bounding boxes for TensorFlow export."""
+    shape = x["feats"][0].shape  # BCHW
+    boxes = x["boxes"]
+    if self.format != "imx" and (self.dynamic or self.shape != shape):
+        self.anchors, self.strides = (a.transpose(0, 1) for a in make_anchors(x["feats"], self.stride, 0.5))
         self.shape = shape
-    grid_h, grid_w = shape[2], shape[3]
-    grid_size = torch.tensor([grid_w, grid_h, grid_w, grid_h], device=box.device).reshape(1, 4, 1)
+    grid_h, grid_w = shape[2:4]
+    grid_size = torch.tensor([grid_w, grid_h, grid_w, grid_h], device=boxes.device).reshape(1, 4, 1)
     norm = self.strides / (self.stride[0] * grid_size)
-    dbox = self.decode_bboxes(self.dfl(box) * norm, self.anchors.unsqueeze(0) * norm[:, :2])
-    return torch.cat((dbox, cls.sigmoid()), 1)
+    dbox = self.decode_bboxes(self.dfl(boxes) * norm, self.anchors.unsqueeze(0) * norm[:, :2])
+    return dbox
 
 
-def tf_kpts_decode(self, bs: int, kpts: torch.Tensor) -> torch.Tensor:
-    """Decode keypoints for tf pose estimation."""
+def _tf_kpts_decode(self, kpts: torch.Tensor, is_pose26: bool = False) -> torch.Tensor:
+    """Decode keypoints for TensorFlow export."""
     ndim = self.kpt_shape[1]
-    # required for TFLite export to avoid 'PLACEHOLDER_FOR_GREATER_OP_CODES' bug
+    bs = kpts.shape[0]
     # Precompute normalization factor to increase numerical stability
     y = kpts.view(bs, *self.kpt_shape, -1)
-    grid_h, grid_w = self.shape[2], self.shape[3]
+    grid_h, grid_w = self.shape[2:4]
     grid_size = torch.tensor([grid_w, grid_h], device=y.device).reshape(1, 2, 1)
     norm = self.strides / (self.stride[0] * grid_size)
-    a = (y[:, :, :2] * 2.0 + (self.anchors - 0.5)) * norm
+    a = ((y[:, :, :2] + self.anchors) if is_pose26 else (y[:, :, :2] * 2.0 + (self.anchors - 0.5))) * norm
     if ndim == 3:
         a = torch.cat((a, y[:, :, 2:3].sigmoid()), 2)
     return a.view(bs, self.nk, -1)