From 932c069b0273e97eea46745e3bc5bb73dcd9cecd Mon Sep 17 00:00:00 2001 From: Glenn Jocher Date: Fri, 2 Jan 2026 05:01:51 +0100 Subject: [PATCH] Fix plots logging (#23105) Co-authored-by: UltralyticsAssistant --- docs/en/reference/utils/callbacks/platform.md | 4 ++ ultralytics/engine/validator.py | 5 +- ultralytics/utils/callbacks/platform.py | 54 +++++++++++++++---- ultralytics/utils/logger.py | 9 +++- ultralytics/utils/metrics.py | 4 +- 5 files changed, 62 insertions(+), 14 deletions(-) diff --git a/docs/en/reference/utils/callbacks/platform.md b/docs/en/reference/utils/callbacks/platform.md index f3877a6e..b1733f42 100644 --- a/docs/en/reference/utils/callbacks/platform.md +++ b/docs/en/reference/utils/callbacks/platform.md @@ -11,6 +11,10 @@ keywords: platform callbacks, training callbacks, console logging, YOLO11 traini
+## ::: ultralytics.utils.callbacks.platform._interp_plot + +



+ ## ::: ultralytics.utils.callbacks.platform._send



diff --git a/ultralytics/engine/validator.py b/ultralytics/engine/validator.py index a7d1641d..ba0bc586 100644 --- a/ultralytics/engine/validator.py +++ b/ultralytics/engine/validator.py @@ -364,7 +364,10 @@ class BaseValidator: return [] def on_plot(self, name, data=None): - """Register plots for visualization.""" + """Register plots for visualization, deduplicating by type.""" + plot_type = data.get("type") if data else None + if plot_type and any((v.get("data") or {}).get("type") == plot_type for v in self.plots.values()): + return # Skip duplicate plot types self.plots[Path(name)] = {"data": data, "timestamp": time.time()} def plot_val_samples(self, batch, ni): diff --git a/ultralytics/utils/callbacks/platform.py b/ultralytics/utils/callbacks/platform.py index e37ce88c..90d30a45 100644 --- a/ultralytics/utils/callbacks/platform.py +++ b/ultralytics/utils/callbacks/platform.py @@ -8,8 +8,9 @@ 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 +from ultralytics.utils import ENVIRONMENT, GIT, LOGGER, PYTHON_VERSION, RANK, SETTINGS, TESTS_RUNNING, colorstr +PREFIX = colorstr("Platform: ") _last_upload = 0 # Rate limit model uploads _console_logger = None # Global console logger instance _system_logger = None # Cached system logger instance @@ -31,6 +32,34 @@ except (AssertionError, ImportError): _api_key = None +def _interp_plot(plot, n=101): + """Interpolate plot curve data from 1000 to n points to reduce storage size.""" + import numpy as np + + if not plot.get("x") or not plot.get("y"): + return plot # No interpolation needed (e.g., confusion_matrix) + + x, y = np.array(plot["x"]), np.array(plot["y"]) + if len(x) <= n: + return plot # Already small enough + + # New x values (101 points gives clean 0.01 increments: 0, 0.01, 0.02, ..., 1.0) + x_new = np.linspace(x[0], x[-1], n) + + # Interpolate y values (handle both 1D and 2D arrays) + if y.ndim == 1: + y_new = np.interp(x_new, x, y) + else: + y_new = np.array([np.interp(x_new, x, yi) for yi in y]) + + # Also interpolate ap if present (for PR curves) + result = {**plot, "x": x_new.tolist(), "y": y_new.tolist()} + if "ap" in plot: + result["ap"] = plot["ap"] # Keep AP values as-is (per-class scalars) + + return result + + def _send(event, data, project, name): """Send event to Platform endpoint.""" try: @@ -75,7 +104,8 @@ def _upload_model(model_path, project, name): timeout=600, # 10 min timeout for large models ).raise_for_status() - LOGGER.info(f"Platform: Model uploaded to '{project}'") + # url = f"https://alpha.ultralytics.com/{project}/{name}" + # LOGGER.info(f"{PREFIX}Model uploaded to {url}") return data.get("gcsPath") except Exception as e: @@ -150,7 +180,8 @@ def on_pretrain_routine_start(trainer): _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}'") + url = f"https://alpha.ultralytics.com/{project}/{name}" + LOGGER.info(f"{PREFIX}Streaming to {url}") # Create callback to send console output to Platform def send_console_output(content, line_count, chunk_id): @@ -272,11 +303,15 @@ def on_train_end(trainer): model_size = Path(trainer.best).stat().st_size model_path = _upload_model(trainer.best, project, name) - # Collect plots from trainer and validator - plots = [info["data"] for info in getattr(trainer, "plots", {}).values() if info.get("data")] - plots += [ - info["data"] for info in getattr(getattr(trainer, "validator", None), "plots", {}).values() if info.get("data") - ] + # Collect plots from trainer and validator, deduplicating by type + plots_by_type = {} + for info in getattr(trainer, "plots", {}).values(): + if info.get("data") and info["data"].get("type"): + plots_by_type[info["data"]["type"]] = info["data"] + for info in getattr(getattr(trainer, "validator", None), "plots", {}).values(): + if info.get("data") and info["data"].get("type"): + plots_by_type.setdefault(info["data"]["type"], info["data"]) # Don't overwrite trainer plots + plots = [_interp_plot(p) for p in plots_by_type.values()] # Interpolate curves to reduce size # Get class names names = getattr(getattr(trainer, "validator", None), "names", None) or (trainer.data or {}).get("names") @@ -298,7 +333,8 @@ def on_train_end(trainer): project, name, ) - LOGGER.info(f"Platform: Training complete, results uploaded to '{project}' ({len(plots)} plots)") + url = f"https://alpha.ultralytics.com/{project}/{name}" + LOGGER.info(f"{PREFIX}View results at {url}") callbacks = ( diff --git a/ultralytics/utils/logger.py b/ultralytics/utils/logger.py index 516f8448..32286566 100644 --- a/ultralytics/utils/logger.py +++ b/ultralytics/utils/logger.py @@ -330,14 +330,19 @@ class SystemLogger: def _init_nvidia(self): """Initialize NVIDIA GPU monitoring with pynvml.""" + if MACOS: + return False + try: - assert not MACOS check_requirements("nvidia-ml-py>=12.0.0") self.pynvml = __import__("pynvml") self.pynvml.nvmlInit() return True except Exception as e: - LOGGER.warning(f"SystemLogger NVML init failed: {e}") + import torch + + if torch.cuda.is_available(): + LOGGER.warning(f"SystemLogger NVML init failed: {e}") return False def get_metrics(self, rates=False): diff --git a/ultralytics/utils/metrics.py b/ultralytics/utils/metrics.py index 51795282..b819a942 100644 --- a/ultralytics/utils/metrics.py +++ b/ultralytics/utils/metrics.py @@ -568,7 +568,6 @@ class ConfusionMatrix(DataExportMixin): fig.savefig(plot_fname, dpi=250) plt.close(fig) if on_plot: - # Pass confusion matrix data for interactive plotting (raw counts only, normalization done on frontend) on_plot(plot_fname, {"type": "confusion_matrix", "matrix": self.matrix.tolist()}) def print(self): @@ -663,7 +662,8 @@ def plot_pr_curve( plt.close(fig) if on_plot: # Pass PR curve data for interactive plotting (class names stored at model level) - on_plot(save_dir, {"type": "pr_curve", "x": px.tolist(), "y": py.tolist(), "ap": ap.tolist()}) + # Transpose py to match other curves: y[class][point] format + on_plot(save_dir, {"type": "pr_curve", "x": px.tolist(), "y": py.T.tolist(), "ap": ap.tolist()}) @plt_settings()