ultralytics-opencv-headless 8.3.242__tar.gz → 8.3.245__tar.gz

{ultralytics_opencv_headless-8.3.242 → ultralytics_opencv_headless-8.3.245}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: ultralytics-opencv-headless
-Version: 8.3.242
+Version: 8.3.245
 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>
@@ -50,7 +50,7 @@ Requires-Dist: ipython; extra == "dev"
 Requires-Dist: pytest; extra == "dev"
 Requires-Dist: pytest-cov; extra == "dev"
 Requires-Dist: coverage[toml]; extra == "dev"
-Requires-Dist: zensical>=0.0.9; python_version >= "3.10" and extra == "dev"
+Requires-Dist: zensical>=0.0.15; python_version >= "3.10" and extra == "dev"
 Requires-Dist: mkdocs-ultralytics-plugin>=0.2.4; extra == "dev"
 Requires-Dist: minijinja>=2.0.0; extra == "dev"
 Provides-Extra: export

{ultralytics_opencv_headless-8.3.242 → ultralytics_opencv_headless-8.3.245}/pyproject.toml

@@ -83,7 +83,7 @@ dev = [
     "pytest",
     "pytest-cov",
     "coverage[toml]",
-    "zensical>=0.0.9; python_version >= '3.10'",
+    "zensical>=0.0.15; python_version >= '3.10'",
     "mkdocs-ultralytics-plugin>=0.2.4", # for meta descriptions and images, dates and authors
     "minijinja>=2.0.0", # render docs macros without mkdocs-macros-plugin
 ]

{ultralytics_opencv_headless-8.3.242 → ultralytics_opencv_headless-8.3.245}/tests/test_engine.py

@@ -13,7 +13,7 @@ from ultralytics.models.yolo import classify, detect, segment
 from ultralytics.utils import ASSETS, DEFAULT_CFG, WEIGHTS_DIR
 
 
-def test_func(*args):
+def test_func(*args, **kwargs):
     """Test function callback for evaluating YOLO model performance metrics."""
     print("callback test passed")
 

{ultralytics_opencv_headless-8.3.242 → ultralytics_opencv_headless-8.3.245}/ultralytics/__init__.py

@@ -1,6 +1,6 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-__version__ = "8.3.242"
+__version__ = "8.3.245"
 
 import importlib
 import os

{ultralytics_opencv_headless-8.3.242 → ultralytics_opencv_headless-8.3.245}/ultralytics/cfg/models/rt-detr/rtdetr-l.yaml

@@ -6,7 +6,7 @@
 
 # Parameters
 nc: 80 # number of classes
-scales: # model compound scaling constants, i.e. 'model=yolov8n-cls.yaml' will call yolov8-cls.yaml with scale 'n'
+scales: # model compound scaling constants, i.e. 'model=rtdetr-l.yaml' will call rtdetr-l.yaml with scale 'l'
   # [depth, width, max_channels]
   l: [1.00, 1.00, 1024]
 

{ultralytics_opencv_headless-8.3.242 → ultralytics_opencv_headless-8.3.245}/ultralytics/cfg/models/rt-detr/rtdetr-resnet101.yaml

@@ -6,7 +6,7 @@
 
 # Parameters
 nc: 80 # number of classes
-scales: # model compound scaling constants, i.e. 'model=yolov8n-cls.yaml' will call yolov8-cls.yaml with scale 'n'
+scales: # model compound scaling constants, i.e. 'model=rtdetr-resnet101.yaml' will call rtdetr-resnet101.yaml with scale 'l'
   # [depth, width, max_channels]
   l: [1.00, 1.00, 1024]
 

{ultralytics_opencv_headless-8.3.242 → ultralytics_opencv_headless-8.3.245}/ultralytics/cfg/models/rt-detr/rtdetr-resnet50.yaml

@@ -6,7 +6,7 @@
 
 # Parameters
 nc: 80 # number of classes
-scales: # model compound scaling constants, i.e. 'model=yolov8n-cls.yaml' will call yolov8-cls.yaml with scale 'n'
+scales: # model compound scaling constants, i.e. 'model=rtdetr-resnet50.yaml' will call rtdetr-resnet50.yaml with scale 'l'
   # [depth, width, max_channels]
   l: [1.00, 1.00, 1024]
 

{ultralytics_opencv_headless-8.3.242 → ultralytics_opencv_headless-8.3.245}/ultralytics/cfg/models/rt-detr/rtdetr-x.yaml

@@ -6,7 +6,7 @@
 
 # Parameters
 nc: 80 # number of classes
-scales: # model compound scaling constants, i.e. 'model=yolov8n-cls.yaml' will call yolov8-cls.yaml with scale 'n'
+scales: # model compound scaling constants, i.e. 'model=rtdetr-x.yaml' will call rtdetr-x.yaml with scale 'x'
   # [depth, width, max_channels]
   x: [1.00, 1.00, 2048]
 

{ultralytics_opencv_headless-8.3.242 → ultralytics_opencv_headless-8.3.245}/ultralytics/cfg/models/v10/yolov10b.yaml

@@ -6,7 +6,7 @@
 
 # Parameters
 nc: 80 # number of classes
-scales: # model compound scaling constants, i.e. 'model=yolov10n.yaml' will call yolov10.yaml with scale 'n'
+scales: # model compound scaling constants, i.e. 'model=yolov10n.yaml' uses the 'n' scale
   # [depth, width, max_channels]
   b: [0.67, 1.00, 512]
 
@@ -24,7 +24,7 @@ backbone:
   - [-1, 1, SPPF, [1024, 5]] # 9
   - [-1, 1, PSA, [1024]] # 10
 
-# YOLOv10.0n head
+# YOLOv10 head
 head:
   - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
   - [[-1, 6], 1, Concat, [1]] # cat backbone P4

{ultralytics_opencv_headless-8.3.242 → ultralytics_opencv_headless-8.3.245}/ultralytics/cfg/models/v10/yolov10l.yaml

@@ -6,7 +6,7 @@
 
 # Parameters
 nc: 80 # number of classes
-scales: # model compound scaling constants, i.e. 'model=yolov10n.yaml' will call yolov10.yaml with scale 'n'
+scales: # model compound scaling constants, i.e. 'model=yolov10n.yaml' uses the 'n' scale
   # [depth, width, max_channels]
   l: [1.00, 1.00, 512]
 
@@ -24,7 +24,7 @@ backbone:
   - [-1, 1, SPPF, [1024, 5]] # 9
   - [-1, 1, PSA, [1024]] # 10
 
-# YOLOv10.0n head
+# YOLOv10 head
 head:
   - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
   - [[-1, 6], 1, Concat, [1]] # cat backbone P4

{ultralytics_opencv_headless-8.3.242 → ultralytics_opencv_headless-8.3.245}/ultralytics/cfg/models/v10/yolov10m.yaml

@@ -6,7 +6,7 @@
 
 # Parameters
 nc: 80 # number of classes
-scales: # model compound scaling constants, i.e. 'model=yolov10n.yaml' will call yolov10.yaml with scale 'n'
+scales: # model compound scaling constants, i.e. 'model=yolov10n.yaml' uses the 'n' scale
   # [depth, width, max_channels]
   m: [0.67, 0.75, 768]
 
@@ -24,7 +24,7 @@ backbone:
   - [-1, 1, SPPF, [1024, 5]] # 9
   - [-1, 1, PSA, [1024]] # 10
 
-# YOLOv10.0n head
+# YOLOv10 head
 head:
   - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
   - [[-1, 6], 1, Concat, [1]] # cat backbone P4

{ultralytics_opencv_headless-8.3.242 → ultralytics_opencv_headless-8.3.245}/ultralytics/cfg/models/v10/yolov10n.yaml

@@ -6,7 +6,7 @@
 
 # Parameters
 nc: 80 # number of classes
-scales: # model compound scaling constants, i.e. 'model=yolov10n.yaml' will call yolov10.yaml with scale 'n'
+scales: # model compound scaling constants, i.e. 'model=yolov10n.yaml' uses the 'n' scale
   # [depth, width, max_channels]
   n: [0.33, 0.25, 1024]
 
@@ -24,7 +24,7 @@ backbone:
   - [-1, 1, SPPF, [1024, 5]] # 9
   - [-1, 1, PSA, [1024]] # 10
 
-# YOLOv10.0n head
+# YOLOv10 head
 head:
   - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
   - [[-1, 6], 1, Concat, [1]] # cat backbone P4

{ultralytics_opencv_headless-8.3.242 → ultralytics_opencv_headless-8.3.245}/ultralytics/cfg/models/v10/yolov10s.yaml

@@ -6,7 +6,7 @@
 
 # Parameters
 nc: 80 # number of classes
-scales: # model compound scaling constants, i.e. 'model=yolov10n.yaml' will call yolov10.yaml with scale 'n'
+scales: # model compound scaling constants, i.e. 'model=yolov10n.yaml' uses the 'n' scale
   # [depth, width, max_channels]
   s: [0.33, 0.50, 1024]
 
@@ -24,7 +24,7 @@ backbone:
   - [-1, 1, SPPF, [1024, 5]] # 9
   - [-1, 1, PSA, [1024]] # 10
 
-# YOLOv10.0n head
+# YOLOv10 head
 head:
   - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
   - [[-1, 6], 1, Concat, [1]] # cat backbone P4

{ultralytics_opencv_headless-8.3.242 → ultralytics_opencv_headless-8.3.245}/ultralytics/cfg/models/v10/yolov10x.yaml

@@ -6,7 +6,7 @@
 
 # Parameters
 nc: 80 # number of classes
-scales: # model compound scaling constants, i.e. 'model=yolov10n.yaml' will call yolov10.yaml with scale 'n'
+scales: # model compound scaling constants, i.e. 'model=yolov10n.yaml' uses the 'n' scale
   # [depth, width, max_channels]
   x: [1.00, 1.25, 512]
 
@@ -24,7 +24,7 @@ backbone:
   - [-1, 1, SPPF, [1024, 5]] # 9
   - [-1, 1, PSA, [1024]] # 10
 
-# YOLOv10.0n head
+# YOLOv10 head
 head:
   - [-1, 1, nn.Upsample, [None, 2, "nearest"]]
   - [[-1, 6], 1, Concat, [1]] # cat backbone P4

{ultralytics_opencv_headless-8.3.242 → ultralytics_opencv_headless-8.3.245}/ultralytics/cfg/models/v3/yolov3-tiny.yaml

@@ -1,6 +1,6 @@
 # Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
 
-# Ultralytics YOLOv3-tiiny object detection model with P4/16 - P5/32 outputs
+# Ultralytics YOLOv3-tiny object detection model with P4/16 - P5/32 outputs
 # Model docs: https://docs.ultralytics.com/models/yolov3
 # Task docs: https://docs.ultralytics.com/tasks/detect
 

{ultralytics_opencv_headless-8.3.242 → ultralytics_opencv_headless-8.3.245}/ultralytics/cfg/models/v6/yolov6.yaml

@@ -7,7 +7,7 @@
 # Parameters
 nc: 80 # number of classes
 activation: torch.nn.ReLU() # (optional) model default activation function
-scales: # model compound scaling constants, i.e. 'model=yolov6n.yaml' will call yolov8.yaml with scale 'n'
+scales: # model compound scaling constants, i.e. 'model=yolov6n.yaml' will call yolov6.yaml with scale 'n'
   # [depth, width, max_channels]
   n: [0.33, 0.25, 1024]
   s: [0.33, 0.50, 1024]

{ultralytics_opencv_headless-8.3.242 → ultralytics_opencv_headless-8.3.245}/ultralytics/cfg/models/v8/yolov8-seg-p6.yaml

@@ -56,4 +56,4 @@ head:
   - [[-1, 11], 1, Concat, [1]] # cat head P6
   - [-1, 3, C2, [1024, False]] # 29 (P6/64-xlarge)
 
-  - [[20, 23, 26, 29], 1, Segment, [nc, 32, 256]] # Pose(P3, P4, P5, P6)
+  - [[20, 23, 26, 29], 1, Segment, [nc, 32, 256]] # Segment(P3, P4, P5, P6)

{ultralytics_opencv_headless-8.3.242 → ultralytics_opencv_headless-8.3.245}/ultralytics/cfg/models/v9/yolov9s.yaml

@@ -38,4 +38,4 @@ head:
   - [[-1, 9], 1, Concat, [1]] # cat head P5
   - [-1, 1, RepNCSPELAN4, [256, 256, 128, 3]] # 21 (P5/32-large)
 
-  - [[15, 18, 21], 1, Detect, [nc]] # Detect(P3, P4 P5)
+  - [[15, 18, 21], 1, Detect, [nc]] # Detect(P3, P4, P5)

{ultralytics_opencv_headless-8.3.242 → ultralytics_opencv_headless-8.3.245}/ultralytics/engine/exporter.py

@@ -87,6 +87,7 @@ from ultralytics.utils import (
     IS_COLAB,
     IS_DEBIAN_BOOKWORM,
     IS_DEBIAN_TRIXIE,
+    IS_DOCKER,
     IS_JETSON,
     IS_RASPBERRYPI,
     IS_UBUNTU,
@@ -1187,10 +1188,11 @@ class Exporter:
         """
         LOGGER.info(f"\n{prefix} starting export with ExecuTorch...")
         assert TORCH_2_9, f"ExecuTorch export requires torch>=2.9.0 but torch=={TORCH_VERSION} is installed"
-        # TorchAO release compatibility table bug https://github.com/pytorch/ao/issues/2919
-        # Setuptools bug: https://github.com/pypa/setuptools/issues/4483
-        check_requirements("setuptools<71.0.0")  # Setuptools bug: https://github.com/pypa/setuptools/issues/4483
-        check_requirements(("executorch==1.0.1", "flatbuffers"))
+
+        # BUG executorch build on arm64 Docker requires packaging>=22.0 https://github.com/pypa/setuptools/issues/4483
+        if LINUX and ARM64 and IS_DOCKER:
+            check_requirements("packaging>=22.0")
+        check_requirements("executorch==1.0.1", "flatbuffers")
         # Pin numpy to avoid coremltools errors with numpy>=2.4.0, must be separate
         check_requirements("numpy<=2.3.5")
 

{ultralytics_opencv_headless-8.3.242 → ultralytics_opencv_headless-8.3.245}/ultralytics/engine/model.py

@@ -523,7 +523,7 @@ class Model(torch.nn.Module):
         args = {**self.overrides, **custom, **kwargs}  # highest priority args on the right
         prompts = args.pop("prompts", None)  # for SAM-type models
 
-        if not self.predictor:
+        if not self.predictor or self.predictor.args.device != args.get("device", self.predictor.args.device):
             self.predictor = (predictor or self._smart_load("predictor"))(overrides=args, _callbacks=self.callbacks)
             self.predictor.setup_model(model=self.model, verbose=is_cli)
         else:  # only update args if predictor is already setup

{ultralytics_opencv_headless-8.3.242 → ultralytics_opencv_headless-8.3.245}/ultralytics/nn/modules/head.py

@@ -1078,9 +1078,9 @@ class RTDETRDecoder(nn.Module):
         enc_outputs_scores = self.enc_score_head(features)  # (bs, h*w, nc)
 
         # Query selection
-        # (bs, num_queries)
+        # (bs*num_queries,)
         topk_ind = torch.topk(enc_outputs_scores.max(-1).values, self.num_queries, dim=1).indices.view(-1)
-        # (bs, num_queries)
+        # (bs*num_queries,)
         batch_ind = torch.arange(end=bs, dtype=topk_ind.dtype).unsqueeze(-1).repeat(1, self.num_queries).view(-1)
 
         # (bs, num_queries, 256)

{ultralytics_opencv_headless-8.3.242 → ultralytics_opencv_headless-8.3.245}/ultralytics/nn/modules/utils.py

@@ -147,7 +147,7 @@ def multi_scale_deformable_attn_pytorch(
         sampling_value_list.append(sampling_value_l_)
     # (bs, num_queries, num_heads, num_levels, num_points) ->
     # (bs, num_heads, num_queries, num_levels, num_points) ->
-    # (bs, num_heads, 1, num_queries, num_levels*num_points)
+    # (bs*num_heads, 1, num_queries, num_levels*num_points)
     attention_weights = attention_weights.transpose(1, 2).reshape(
         bs * num_heads, 1, num_queries, num_levels * num_points
     )

ultralytics_opencv_headless-8.3.245/ultralytics/utils/callbacks/platform.py

@@ -0,0 +1,302 @@
+# Ultralytics 🚀 AGPL-3.0 License - https://ultralytics.com/license
+
+import os
+import platform
+import socket
+import sys
+from concurrent.futures import ThreadPoolExecutor
+from pathlib import Path
+from time import time
+
+from ultralytics.utils import ENVIRONMENT, GIT, LOGGER, PYTHON_VERSION, RANK, SETTINGS, TESTS_RUNNING
+
+_last_upload = 0  # Rate limit model uploads
+_console_logger = None  # Global console logger instance
+_system_logger = None  # Cached system logger instance
+
+try:
+    assert not TESTS_RUNNING  # do not log pytest
+    assert SETTINGS.get("platform", False) is True or os.getenv("ULTRALYTICS_API_KEY") or SETTINGS.get("api_key")
+    _api_key = os.getenv("ULTRALYTICS_API_KEY") or SETTINGS.get("api_key")
+    assert _api_key  # verify API key is present
+
+    import requests
+
+    from ultralytics.utils.logger import ConsoleLogger, SystemLogger
+    from ultralytics.utils.torch_utils import model_info_for_loggers
+
+    _executor = ThreadPoolExecutor(max_workers=10)  # Bounded thread pool for async operations
+
+except (AssertionError, ImportError):
+    _api_key = None
+
+
+def _send(event, data, project, name):
+    """Send event to Platform endpoint."""
+    try:
+        requests.post(
+            "https://alpha.ultralytics.com/api/webhooks/training/metrics",
+            json={"event": event, "project": project, "name": name, "data": data},
+            headers={"Authorization": f"Bearer {_api_key}"},
+            timeout=10,
+        ).raise_for_status()
+    except Exception as e:
+        LOGGER.debug(f"Platform: Failed to send {event}: {e}")
+
+
+def _send_async(event, data, project, name):
+    """Send event asynchronously using bounded thread pool."""
+    _executor.submit(_send, event, data, project, name)
+
+
+def _upload_model(model_path, project, name):
+    """Upload model checkpoint to Platform via signed URL."""
+    try:
+        model_path = Path(model_path)
+        if not model_path.exists():
+            return None
+
+        # Get signed upload URL
+        response = requests.post(
+            "https://alpha.ultralytics.com/api/webhooks/models/upload",
+            json={"project": project, "name": name, "filename": model_path.name},
+            headers={"Authorization": f"Bearer {_api_key}"},
+            timeout=10,
+        )
+        response.raise_for_status()
+        data = response.json()
+
+        # Upload to GCS
+        with open(model_path, "rb") as f:
+            requests.put(
+                data["uploadUrl"],
+                data=f,
+                headers={"Content-Type": "application/octet-stream"},
+                timeout=600,  # 10 min timeout for large models
+            ).raise_for_status()
+
+        LOGGER.info(f"Platform: Model uploaded to '{project}'")
+        return data.get("gcsPath")
+
+    except Exception as e:
+        LOGGER.debug(f"Platform: Failed to upload model: {e}")
+        return None
+
+
+def _upload_model_async(model_path, project, name):
+    """Upload model asynchronously using bounded thread pool."""
+    _executor.submit(_upload_model, model_path, project, name)
+
+
+def _get_environment_info():
+    """Collect comprehensive environment info using existing ultralytics utilities."""
+    import shutil
+
+    import psutil
+    import torch
+
+    from ultralytics import __version__
+    from ultralytics.utils.torch_utils import get_cpu_info, get_gpu_info
+
+    # Get RAM and disk totals
+    memory = psutil.virtual_memory()
+    disk_usage = shutil.disk_usage("/")
+
+    env = {
+        "ultralyticsVersion": __version__,
+        "hostname": socket.gethostname(),
+        "os": platform.platform(),
+        "environment": ENVIRONMENT,
+        "pythonVersion": PYTHON_VERSION,
+        "pythonExecutable": sys.executable,
+        "cpuCount": os.cpu_count() or 0,
+        "cpu": get_cpu_info(),
+        "command": " ".join(sys.argv),
+        "totalRamGb": round(memory.total / (1 << 30), 1),  # Total RAM in GB
+        "totalDiskGb": round(disk_usage.total / (1 << 30), 1),  # Total disk in GB
+    }
+
+    # Git info using cached GIT singleton (no subprocess calls)
+    try:
+        if GIT.is_repo:
+            if GIT.origin:
+                env["gitRepository"] = GIT.origin
+            if GIT.branch:
+                env["gitBranch"] = GIT.branch
+            if GIT.commit:
+                env["gitCommit"] = GIT.commit[:12]  # Short hash
+    except Exception:
+        pass
+
+    # GPU info
+    try:
+        if torch.cuda.is_available():
+            env["gpuCount"] = torch.cuda.device_count()
+            env["gpuType"] = get_gpu_info(0) if torch.cuda.device_count() > 0 else None
+    except Exception:
+        pass
+
+    return env
+
+
+def on_pretrain_routine_start(trainer):
+    """Initialize Platform logging at training start."""
+    global _console_logger, _last_upload
+
+    if RANK not in {-1, 0} or not trainer.args.project:
+        return
+
+    # Initialize upload timer to now so first checkpoint waits 15 min from training start
+    _last_upload = time()
+
+    project, name = str(trainer.args.project), str(trainer.args.name or "train")
+    LOGGER.info(f"Platform: Streaming to project '{project}' as '{name}'")
+
+    # Create callback to send console output to Platform
+    def send_console_output(content, line_count, chunk_id):
+        """Send batched console output to Platform webhook."""
+        _send_async("console_output", {"chunkId": chunk_id, "content": content, "lineCount": line_count}, project, name)
+
+    # Start console capture with batching (5 lines or 5 seconds)
+    _console_logger = ConsoleLogger(batch_size=5, flush_interval=5.0, on_flush=send_console_output)
+    _console_logger.start_capture()
+
+    # Gather model info for richer metadata
+    model_info = {}
+    try:
+        info = model_info_for_loggers(trainer)
+        model_info = {
+            "parameters": info.get("model/parameters", 0),
+            "gflops": info.get("model/GFLOPs", 0),
+            "classes": getattr(trainer.model, "yaml", {}).get("nc", 0),  # number of classes
+        }
+    except Exception:
+        pass
+
+    # Collect environment info (W&B-style metadata)
+    environment = _get_environment_info()
+
+    _send_async(
+        "training_started",
+        {
+            "trainArgs": {k: str(v) for k, v in vars(trainer.args).items()},
+            "epochs": trainer.epochs,
+            "device": str(trainer.device),
+            "modelInfo": model_info,
+            "environment": environment,
+        },
+        project,
+        name,
+    )
+
+
+def on_fit_epoch_end(trainer):
+    """Log training and system metrics at epoch end."""
+    global _system_logger
+
+    if RANK not in {-1, 0} or not trainer.args.project:
+        return
+
+    project, name = str(trainer.args.project), str(trainer.args.name or "train")
+    metrics = {**trainer.label_loss_items(trainer.tloss, prefix="train"), **trainer.metrics}
+
+    if trainer.optimizer and trainer.optimizer.param_groups:
+        metrics["lr"] = trainer.optimizer.param_groups[0]["lr"]
+    if trainer.epoch == 0:
+        try:
+            metrics.update(model_info_for_loggers(trainer))
+        except Exception:
+            pass
+
+    # Get system metrics (cache SystemLogger for efficiency)
+    system = {}
+    try:
+        if _system_logger is None:
+            _system_logger = SystemLogger()
+        system = _system_logger.get_metrics(rates=True)
+    except Exception:
+        pass
+
+    _send_async(
+        "epoch_end",
+        {
+            "epoch": trainer.epoch,
+            "metrics": metrics,
+            "system": system,
+            "fitness": trainer.fitness,
+            "best_fitness": trainer.best_fitness,
+        },
+        project,
+        name,
+    )
+
+
+def on_model_save(trainer):
+    """Upload model checkpoint (rate limited to every 15 min)."""
+    global _last_upload
+
+    if RANK not in {-1, 0} or not trainer.args.project:
+        return
+
+    # Rate limit to every 15 minutes (900 seconds)
+    if time() - _last_upload < 900:
+        return
+
+    model_path = trainer.best if trainer.best and Path(trainer.best).exists() else trainer.last
+    if not model_path:
+        return
+
+    project, name = str(trainer.args.project), str(trainer.args.name or "train")
+    _upload_model_async(model_path, project, name)
+    _last_upload = time()
+
+
+def on_train_end(trainer):
+    """Log final results and upload best model."""
+    global _console_logger
+
+    if RANK not in {-1, 0} or not trainer.args.project:
+        return
+
+    project, name = str(trainer.args.project), str(trainer.args.name or "train")
+
+    # Stop console capture and flush remaining output
+    if _console_logger:
+        _console_logger.stop_capture()
+        _console_logger = None
+
+    # Upload best model (blocking to ensure it completes)
+    model_path = None
+    model_size = None
+    if trainer.best and Path(trainer.best).exists():
+        model_size = Path(trainer.best).stat().st_size
+        model_path = _upload_model(trainer.best, project, name)
+
+    # Send training complete
+    _send(
+        "training_complete",
+        {
+            "results": {
+                "metrics": {**trainer.metrics, "fitness": trainer.fitness},
+                "bestEpoch": getattr(trainer, "best_epoch", trainer.epoch),
+                "bestFitness": trainer.best_fitness,
+                "modelPath": model_path or str(trainer.best) if trainer.best else None,
+                "modelSize": model_size,
+            }
+        },
+        project,
+        name,
+    )
+    LOGGER.info(f"Platform: Training complete, results uploaded to '{project}'")
+
+
+callbacks = (
+    {
+        "on_pretrain_routine_start": on_pretrain_routine_start,
+        "on_fit_epoch_end": on_fit_epoch_end,
+        "on_model_save": on_model_save,
+        "on_train_end": on_train_end,
+    }
+    if _api_key
+    else {}
+)

{ultralytics_opencv_headless-8.3.242 → ultralytics_opencv_headless-8.3.245}/ultralytics/utils/checks.py

@@ -418,6 +418,11 @@ def check_requirements(requirements=ROOT.parent / "requirements.txt", exclude=()
         >>> check_requirements([("onnxruntime", "onnxruntime-gpu"), "numpy"])
     """
     prefix = colorstr("red", "bold", "requirements:")
+
+    if os.environ.get("ULTRALYTICS_SKIP_REQUIREMENTS_CHECKS", "0") == "1":
+        LOGGER.info(f"{prefix} ULTRALYTICS_SKIP_REQUIREMENTS_CHECKS=1 detected, skipping requirements check.")
+        return True
+
     if isinstance(requirements, Path):  # requirements.txt file
         file = requirements.resolve()
         assert file.exists(), f"{prefix} {file} not found, check failed."