From f6005a916694dbe45657abbb84b13162a6a2b5cf Mon Sep 17 00:00:00 2001 From: Laughing <61612323+Laughing-q@users.noreply.github.com> Date: Fri, 6 Dec 2024 18:46:48 +0800 Subject: [PATCH 1/8] Set `task` for Triton inferenceTriton (#18064) --- ultralytics/engine/model.py | 1 + 1 file changed, 1 insertion(+) diff --git a/ultralytics/engine/model.py b/ultralytics/engine/model.py index 874613d2f1..db8d87ebc2 100644 --- a/ultralytics/engine/model.py +++ b/ultralytics/engine/model.py @@ -136,6 +136,7 @@ class Model(nn.Module): # Check if Triton Server model elif self.is_triton_model(model): self.model_name = self.model = model + self.overrides["task"] = task or "detect" # set `task=detect` if not explicitly set return # Load or create new YOLO model From 7ba48cc078c38b4bfe7c3645c668dec03045febb Mon Sep 17 00:00:00 2001 From: yeyangshuo <115603502+ye-yangshuo@users.noreply.github.com> Date: Fri, 6 Dec 2024 18:58:59 +0800 Subject: [PATCH 2/8] Modified the parameter description of 'weights' in the AutoBackend class (#18059) Signed-off-by: Glenn Jocher Co-authored-by: Glenn Jocher --- ultralytics/nn/autobackend.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/ultralytics/nn/autobackend.py b/ultralytics/nn/autobackend.py index 17504b823a..8e9b74ebc5 100644 --- a/ultralytics/nn/autobackend.py +++ b/ultralytics/nn/autobackend.py @@ -96,7 +96,7 @@ class AutoBackend(nn.Module): Initialize the AutoBackend for inference. Args: - weights (str): Path to the model weights file. Defaults to 'yolov8n.pt'. + weights (str | torch.nn.Module): Path to the model weights file or a module instance. Defaults to 'yolo11n.pt'. device (torch.device): Device to run the model on. Defaults to CPU. dnn (bool): Use OpenCV DNN module for ONNX inference. Defaults to False. data (str | Path | optional): Path to the additional data.yaml file containing class names. Optional. From 530e6b934256017b518fe312d57f5700f7438f3f Mon Sep 17 00:00:00 2001 From: Laughing <61612323+Laughing-q@users.noreply.github.com> Date: Fri, 6 Dec 2024 19:59:19 +0800 Subject: [PATCH 3/8] Fix `np.empty_like` and `torch.empty_like` input type (#18062) Co-authored-by: Glenn Jocher Co-authored-by: UltralyticsAssistant --- docs/en/reference/utils/ops.md | 4 ++++ ultralytics/utils/ops.py | 15 +++++++++++---- 2 files changed, 15 insertions(+), 4 deletions(-) diff --git a/docs/en/reference/utils/ops.md b/docs/en/reference/utils/ops.md index b62ba7b4eb..ab6cafbca8 100644 --- a/docs/en/reference/utils/ops.md +++ b/docs/en/reference/utils/ops.md @@ -129,4 +129,8 @@ keywords: Ultralytics, utility operations, non-max suppression, bounding box tra ## ::: ultralytics.utils.ops.clean_str +


+ +## ::: ultralytics.utils.ops.empty_like +

diff --git a/ultralytics/utils/ops.py b/ultralytics/utils/ops.py index 50c861de1e..9a05b3a8b5 100644 --- a/ultralytics/utils/ops.py +++ b/ultralytics/utils/ops.py @@ -400,7 +400,7 @@ def xyxy2xywh(x): y (np.ndarray | torch.Tensor): The bounding box coordinates in (x, y, width, height) format. """ assert x.shape[-1] == 4, f"input shape last dimension expected 4 but input shape is {x.shape}" - y = torch.empty_like(x) if isinstance(x, torch.Tensor) else np.empty_like(x) # faster than clone/copy + y = empty_like(x) # faster than clone/copy y[..., 0] = (x[..., 0] + x[..., 2]) / 2 # x center y[..., 1] = (x[..., 1] + x[..., 3]) / 2 # y center y[..., 2] = x[..., 2] - x[..., 0] # width @@ -420,7 +420,7 @@ def xywh2xyxy(x): y (np.ndarray | torch.Tensor): The bounding box coordinates in (x1, y1, x2, y2) format. """ assert x.shape[-1] == 4, f"input shape last dimension expected 4 but input shape is {x.shape}" - y = torch.empty_like(x) if isinstance(x, torch.Tensor) else np.empty_like(x) # faster than clone/copy + y = empty_like(x) # faster than clone/copy xy = x[..., :2] # centers wh = x[..., 2:] / 2 # half width-height y[..., :2] = xy - wh # top left xy @@ -443,7 +443,7 @@ def xywhn2xyxy(x, w=640, h=640, padw=0, padh=0): x1,y1 is the top-left corner, x2,y2 is the bottom-right corner of the bounding box. """ assert x.shape[-1] == 4, f"input shape last dimension expected 4 but input shape is {x.shape}" - y = torch.empty_like(x) if isinstance(x, torch.Tensor) else np.empty_like(x) # faster than clone/copy + y = empty_like(x) # faster than clone/copy y[..., 0] = w * (x[..., 0] - x[..., 2] / 2) + padw # top left x y[..., 1] = h * (x[..., 1] - x[..., 3] / 2) + padh # top left y y[..., 2] = w * (x[..., 0] + x[..., 2] / 2) + padw # bottom right x @@ -469,7 +469,7 @@ def xyxy2xywhn(x, w=640, h=640, clip=False, eps=0.0): if clip: x = clip_boxes(x, (h - eps, w - eps)) assert x.shape[-1] == 4, f"input shape last dimension expected 4 but input shape is {x.shape}" - y = torch.empty_like(x) if isinstance(x, torch.Tensor) else np.empty_like(x, dtype=float) # faster than clone/copy + y = empty_like(x) # faster than clone/copy y[..., 0] = ((x[..., 0] + x[..., 2]) / 2) / w # x center y[..., 1] = ((x[..., 1] + x[..., 3]) / 2) / h # y center y[..., 2] = (x[..., 2] - x[..., 0]) / w # width @@ -838,3 +838,10 @@ def clean_str(s): (str): a string with special characters replaced by an underscore _ """ return re.sub(pattern="[|@#!¡·$€%&()=?¿^*;:,¨´><+]", repl="_", string=s) + + +def empty_like(x): + """Creates empty torch.Tensor or np.ndarray with same shape as input and float32 dtype.""" + return ( + torch.empty_like(x, dtype=torch.float32) if isinstance(x, torch.Tensor) else np.empty_like(x, dtype=np.float32) + ) From c284a9e9744afb867c1acb6518d65cb21b7a1e75 Mon Sep 17 00:00:00 2001 From: Mohammed Yasin <32206511+Y-T-G@users.noreply.github.com> Date: Fri, 6 Dec 2024 20:10:26 +0800 Subject: [PATCH 4/8] `ultralytics 8.3.44` improve Triton Inference Server metadata (#17921) Signed-off-by: Glenn Jocher Co-authored-by: Glenn Jocher --- docs/en/guides/triton-inference-server.md | 18 +++++++++++++++++- ultralytics/__init__.py | 2 +- ultralytics/nn/autobackend.py | 1 + ultralytics/utils/triton.py | 1 + 4 files changed, 20 insertions(+), 2 deletions(-) diff --git a/docs/en/guides/triton-inference-server.md b/docs/en/guides/triton-inference-server.md index 0151cc078d..67d419bf52 100644 --- a/docs/en/guides/triton-inference-server.md +++ b/docs/en/guides/triton-inference-server.md @@ -48,6 +48,16 @@ from ultralytics import YOLO # Load a model model = YOLO("yolo11n.pt") # load an official model +# Retreive metadata during export +metadata = [] + + +def export_cb(exporter): + metadata.append(exporter.metadata) + + +model.add_callback("on_export_end", export_cb) + # Export the model onnx_file = model.export(format="onnx", dynamic=True) ``` @@ -107,7 +117,13 @@ The Triton Model Repository is a storage location where Triton can access and lo } } } - """ + parameters { + key: "metadata" + value: { + string_value: "%s" + } + } + """ % metadata[0] with open(triton_model_path / "config.pbtxt", "w") as f: f.write(data) diff --git a/ultralytics/__init__.py b/ultralytics/__init__.py index 790bb406d4..9d19f6abfd 100644 --- a/ultralytics/__init__.py +++ b/ultralytics/__init__.py @@ -1,6 +1,6 @@ # Ultralytics YOLO 🚀, AGPL-3.0 license -__version__ = "8.3.43" +__version__ = "8.3.44" import os diff --git a/ultralytics/nn/autobackend.py b/ultralytics/nn/autobackend.py index 8e9b74ebc5..b6df3753ec 100644 --- a/ultralytics/nn/autobackend.py +++ b/ultralytics/nn/autobackend.py @@ -462,6 +462,7 @@ class AutoBackend(nn.Module): from ultralytics.utils.triton import TritonRemoteModel model = TritonRemoteModel(w) + metadata = model.metadata # Any other format (unsupported) else: diff --git a/ultralytics/utils/triton.py b/ultralytics/utils/triton.py index 3f873a6faf..cc53ed5714 100644 --- a/ultralytics/utils/triton.py +++ b/ultralytics/utils/triton.py @@ -66,6 +66,7 @@ class TritonRemoteModel: self.np_input_formats = [type_map[x] for x in self.input_formats] self.input_names = [x["name"] for x in config["input"]] self.output_names = [x["name"] for x in config["output"]] + self.metadata = eval(config.get("parameters", {}).get("metadata", {}).get("string_value", "None")) def __call__(self, *inputs: np.ndarray) -> List[np.ndarray]: """ From 89a3de1ba831d3b9f382999b950be697d9bc07c5 Mon Sep 17 00:00:00 2001 From: Glenn Jocher Date: Fri, 6 Dec 2024 16:40:32 +0100 Subject: [PATCH 5/8] Fix Docs YAML boolean (#18072) Signed-off-by: Glenn Jocher Signed-off-by: UltralyticsAssistant Co-authored-by: UltralyticsAssistant --- .github/workflows/docs.yml | 2 +- ultralytics/models/sam/predict.py | 2 +- 2 files changed, 2 insertions(+), 2 deletions(-) diff --git a/.github/workflows/docs.yml b/.github/workflows/docs.yml index dfb6a34631..40b7efc186 100644 --- a/.github/workflows/docs.yml +++ b/.github/workflows/docs.yml @@ -23,7 +23,7 @@ on: inputs: publish_docs: description: "Publish live to https://docs.ultralytics.com" - default: "true" + default: true type: boolean jobs: diff --git a/ultralytics/models/sam/predict.py b/ultralytics/models/sam/predict.py index 540d1007a3..b657ef7051 100644 --- a/ultralytics/models/sam/predict.py +++ b/ultralytics/models/sam/predict.py @@ -1105,7 +1105,7 @@ class SAM2VideoPredictor(SAM2Predictor): for obj_temp_output_dict in temp_output_dict_per_obj.values(): temp_frame_inds.update(obj_temp_output_dict[storage_key].keys()) consolidated_frame_inds[storage_key].update(temp_frame_inds) - # consolidate the temprary output across all objects on this frame + # consolidate the temporary output across all objects on this frame for frame_idx in temp_frame_inds: consolidated_out = self._consolidate_temp_output_across_obj( frame_idx, is_cond=is_cond, run_mem_encoder=True From eb3783763dae921ada76bbb4d01a96ec5d412334 Mon Sep 17 00:00:00 2001 From: Muhammad Rizwan Munawar Date: Fri, 6 Dec 2024 20:41:17 +0500 Subject: [PATCH 6/8] Eliminate duplicate bullet points in docs (#18074) --- docs/en/solutions/index.md | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/docs/en/solutions/index.md b/docs/en/solutions/index.md index 243fbf2757..dd7b61d252 100644 --- a/docs/en/solutions/index.md +++ b/docs/en/solutions/index.md @@ -29,7 +29,6 @@ Here's our curated list of Ultralytics solutions that can be used to create awes - [Parking Management](../guides/parking-management.md) 🚀: Organize and direct vehicle flow in parking areas with YOLO11, optimizing space utilization and user experience. - [Analytics](../guides/analytics.md) 📊: Conduct comprehensive data analysis to discover patterns and make informed decisions, leveraging YOLO11 for descriptive, predictive, and prescriptive analytics. - [Live Inference with Streamlit](../guides/streamlit-live-inference.md) 🚀: Leverage the power of YOLO11 for real-time [object detection](https://www.ultralytics.com/glossary/object-detection) directly through your web browser with a user-friendly Streamlit interface. -- [Live Inference with Streamlit](../guides/streamlit-live-inference.md) 🚀: Leverage the power of YOLO11 for real-time [object detection](https://www.ultralytics.com/glossary/object-detection) directly through your web browser with a user-friendly Streamlit interface. - [Track Objects in Zone](../guides/trackzone.md) 🎯 NEW: Learn how to track objects within specific zones of video frames using YOLO11 for precise and efficient monitoring. ## Solutions Usage @@ -39,7 +38,7 @@ Here's our curated list of Ultralytics solutions that can be used to create awes `yolo SOLUTIONS SOLUTION_NAME ARGS` - **SOLUTIONS** is a required keyword. - - **SOLUTION_NAME** (optional) is one of: `['count', 'heatmap', 'queue', 'speed', 'workout', 'analytics']`. + - **SOLUTION_NAME** (optional) is one of: `['count', 'heatmap', 'queue', 'speed', 'workout', 'analytics', 'trackzone']`. - **ARGS** (optional) are custom `arg=value` pairs, such as `show_in=True`, to override default settings. === "CLI" From 95a9796fee5a110fdd861e12b476b1dfa237b910 Mon Sep 17 00:00:00 2001 From: Mohammed Yasin <32206511+Y-T-G@users.noreply.github.com> Date: Sat, 7 Dec 2024 01:25:52 +0800 Subject: [PATCH 7/8] Mention `copy_paste` applies only when using segmentation labels (#18077) Signed-off-by: Mohammed Yasin <32206511+Y-T-G@users.noreply.github.com> Co-authored-by: UltralyticsAssistant Co-authored-by: Ultralytics Assistant <135830346+UltralyticsAssistant@users.noreply.github.com> --- docs/en/macros/augmentation-args.md | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/docs/en/macros/augmentation-args.md b/docs/en/macros/augmentation-args.md index b4d6c9df6d..bee27ddd0d 100644 --- a/docs/en/macros/augmentation-args.md +++ b/docs/en/macros/augmentation-args.md @@ -13,7 +13,7 @@ | `bgr` | `float` | `0.0` | `0.0 - 1.0` | Flips the image channels from RGB to BGR with the specified probability, useful for increasing robustness to incorrect channel ordering. | | `mosaic` | `float` | `1.0` | `0.0 - 1.0` | Combines four training images into one, simulating different scene compositions and object interactions. Highly effective for complex scene understanding. | | `mixup` | `float` | `0.0` | `0.0 - 1.0` | Blends two images and their labels, creating a composite image. Enhances the model's ability to generalize by introducing label noise and visual variability. | -| `copy_paste` | `float` | `0.0` | `0.0 - 1.0` | Copies objects from one image and pastes them onto another, useful for increasing object instances and learning object occlusion. | +| `copy_paste` | `float` | `0.0` | `0.0 - 1.0` | Copies and pastes objects across images, useful for increasing object instances and learning object occlusion. Requires segmentation labels. | | `copy_paste_mode` | `str` | `flip` | - | Copy-Paste augmentation method selection among the options of (`"flip"`, `"mixup"`). | | `auto_augment` | `str` | `randaugment` | - | Automatically applies a predefined augmentation policy (`randaugment`, `autoaugment`, `augmix`), optimizing for classification tasks by diversifying the visual features. | | `erasing` | `float` | `0.4` | `0.0 - 0.9` | Randomly erases a portion of the image during classification training, encouraging the model to focus on less obvious features for recognition. | From 3d52c4fa106dfe3da037dea0d2e370f984ca367f Mon Sep 17 00:00:00 2001 From: Laughing <61612323+Laughing-q@users.noreply.github.com> Date: Sat, 7 Dec 2024 20:55:59 +0800 Subject: [PATCH 8/8] `ultralytics 8.3.47` fix `softmax` and `Classify` head commonality (#18085) Signed-off-by: Glenn Jocher Co-authored-by: UltralyticsAssistant Co-authored-by: Glenn Jocher --- ultralytics/__init__.py | 2 +- ultralytics/engine/exporter.py | 4 +++- ultralytics/models/yolo/classify/predict.py | 3 ++- ultralytics/models/yolo/classify/val.py | 4 ++++ ultralytics/nn/modules/head.py | 7 ++++++- ultralytics/utils/loss.py | 1 + 6 files changed, 17 insertions(+), 4 deletions(-) diff --git a/ultralytics/__init__.py b/ultralytics/__init__.py index 9d19f6abfd..bd608b1d66 100644 --- a/ultralytics/__init__.py +++ b/ultralytics/__init__.py @@ -1,6 +1,6 @@ # Ultralytics YOLO 🚀, AGPL-3.0 license -__version__ = "8.3.44" +__version__ = "8.3.47" import os diff --git a/ultralytics/engine/exporter.py b/ultralytics/engine/exporter.py index c0e29e7e1c..ae84cab9a1 100644 --- a/ultralytics/engine/exporter.py +++ b/ultralytics/engine/exporter.py @@ -73,7 +73,7 @@ from ultralytics.data import build_dataloader from ultralytics.data.dataset import YOLODataset from ultralytics.data.utils import check_cls_dataset, check_det_dataset from ultralytics.nn.autobackend import check_class_names, default_class_names -from ultralytics.nn.modules import C2f, Detect, RTDETRDecoder +from ultralytics.nn.modules import C2f, Classify, Detect, RTDETRDecoder from ultralytics.nn.tasks import DetectionModel, SegmentationModel, WorldModel from ultralytics.utils import ( ARM64, @@ -287,6 +287,8 @@ class Exporter: model = FXModel(model) for m in model.modules(): + if isinstance(m, Classify): + m.export = True if isinstance(m, (Detect, RTDETRDecoder)): # includes all Detect subclasses like Segment, Pose, OBB m.dynamic = self.args.dynamic m.export = True diff --git a/ultralytics/models/yolo/classify/predict.py b/ultralytics/models/yolo/classify/predict.py index b75a194984..385f75bc0d 100644 --- a/ultralytics/models/yolo/classify/predict.py +++ b/ultralytics/models/yolo/classify/predict.py @@ -53,7 +53,8 @@ class ClassificationPredictor(BasePredictor): if not isinstance(orig_imgs, list): # input images are a torch.Tensor, not a list orig_imgs = ops.convert_torch2numpy_batch(orig_imgs) + preds = preds[0] if isinstance(preds, (list, tuple)) else preds return [ - Results(orig_img, path=img_path, names=self.model.names, probs=pred.softmax(0)) + Results(orig_img, path=img_path, names=self.model.names, probs=pred) for pred, orig_img, img_path in zip(preds, orig_imgs, self.batch[0]) ] diff --git a/ultralytics/models/yolo/classify/val.py b/ultralytics/models/yolo/classify/val.py index e54f04118a..67333f2604 100644 --- a/ultralytics/models/yolo/classify/val.py +++ b/ultralytics/models/yolo/classify/val.py @@ -71,6 +71,10 @@ class ClassificationValidator(BaseValidator): self.metrics.confusion_matrix = self.confusion_matrix self.metrics.save_dir = self.save_dir + def postprocess(self, preds): + """Preprocesses the classification predictions.""" + return preds[0] if isinstance(preds, (list, tuple)) else preds + def get_stats(self): """Returns a dictionary of metrics obtained by processing targets and predictions.""" self.metrics.process(self.targets, self.pred) diff --git a/ultralytics/nn/modules/head.py b/ultralytics/nn/modules/head.py index 25964ac2e5..0afb5fd16f 100644 --- a/ultralytics/nn/modules/head.py +++ b/ultralytics/nn/modules/head.py @@ -282,6 +282,8 @@ class Pose(Detect): class Classify(nn.Module): """YOLO classification head, i.e. x(b,c1,20,20) to x(b,c2).""" + export = False # export mode + def __init__(self, c1, c2, k=1, s=1, p=None, g=1): """Initializes YOLO classification head to transform input tensor from (b,c1,20,20) to (b,c2) shape.""" super().__init__() @@ -296,7 +298,10 @@ class Classify(nn.Module): if isinstance(x, list): x = torch.cat(x, 1) x = self.linear(self.drop(self.pool(self.conv(x)).flatten(1))) - return x + if self.training: + return x + y = x.softmax(1) # get final output + return y if self.export else (y, x) class WorldDetect(Detect): diff --git a/ultralytics/utils/loss.py b/ultralytics/utils/loss.py index 7395286899..c6557df4c0 100644 --- a/ultralytics/utils/loss.py +++ b/ultralytics/utils/loss.py @@ -604,6 +604,7 @@ class v8ClassificationLoss: def __call__(self, preds, batch): """Compute the classification loss between predictions and true labels.""" + preds = preds[1] if isinstance(preds, (list, tuple)) else preds loss = F.cross_entropy(preds, batch["cls"], reduction="mean") loss_items = loss.detach() return loss, loss_items