From db4c43bafbed1e1298c4436b8c7e7c6e5b9f3eec Mon Sep 17 00:00:00 2001 From: Francesco Mattioli Date: Wed, 31 Jul 2024 15:13:27 +0200 Subject: [PATCH 01/10] Exported model batch size validation fix (#14845) Co-authored-by: Glenn Jocher --- ultralytics/engine/validator.py | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/ultralytics/engine/validator.py b/ultralytics/engine/validator.py index 8a2765c98f..4a40a88291 100644 --- a/ultralytics/engine/validator.py +++ b/ultralytics/engine/validator.py @@ -136,8 +136,8 @@ class BaseValidator: if engine: self.args.batch = model.batch_size elif not pt and not jit: - self.args.batch = 1 # export.py models default to batch-size 1 - LOGGER.info(f"Forcing batch=1 square inference (1,3,{imgsz},{imgsz}) for non-PyTorch models") + self.args.batch = model.metadata.get("batch", 1) # export.py models default to batch-size 1 + LOGGER.info(f"Setting batch={self.args.batch} input of shape ({self.args.batch}, 3, {imgsz}, {imgsz})") if str(self.args.data).split(".")[-1] in {"yaml", "yml"}: self.data = check_det_dataset(self.args.data) From bdc7176fe48d0f29206337de397b1a4dc6c40f69 Mon Sep 17 00:00:00 2001 From: Jan Knobloch <116908874+jk4e@users.noreply.github.com> Date: Thu, 1 Aug 2024 12:57:13 +0200 Subject: [PATCH 02/10] Fix `model` in Pose, Segment datasets train FAQ sections (#14877) --- docs/en/datasets/pose/coco.md | 2 +- docs/en/datasets/pose/coco8-pose.md | 2 +- docs/en/datasets/pose/tiger-pose.md | 2 +- docs/en/datasets/segment/coco.md | 2 +- docs/en/datasets/segment/coco8-seg.md | 2 +- 5 files changed, 5 insertions(+), 5 deletions(-) diff --git a/docs/en/datasets/pose/coco.md b/docs/en/datasets/pose/coco.md index 589614f8b3..11cde4dd63 100644 --- a/docs/en/datasets/pose/coco.md +++ b/docs/en/datasets/pose/coco.md @@ -133,7 +133,7 @@ Training a YOLOv8 model on the COCO-Pose dataset can be accomplished using eithe ```bash # Start training from a pretrained *.pt model - yolo detect train data=coco-pose.yaml model=yolov8n.pt epochs=100 imgsz=640 + yolo detect train data=coco-pose.yaml model=yolov8n-pose.pt epochs=100 imgsz=640 ``` For more details on the training process and available arguments, check the [training page](../../modes/train.md). diff --git a/docs/en/datasets/pose/coco8-pose.md b/docs/en/datasets/pose/coco8-pose.md index f8f4d46073..c8d4a37542 100644 --- a/docs/en/datasets/pose/coco8-pose.md +++ b/docs/en/datasets/pose/coco8-pose.md @@ -105,7 +105,7 @@ To train a YOLOv8n-pose model on the COCO8-Pose dataset for 100 epochs with an i === "CLI" ```bash - yolo detect train data=coco8-pose.yaml model=yolov8n.pt epochs=100 imgsz=640 + yolo detect train data=coco8-pose.yaml model=yolov8n-pose.pt epochs=100 imgsz=640 ``` For a comprehensive list of training arguments, refer to the model [Training](../../modes/train.md) page. diff --git a/docs/en/datasets/pose/tiger-pose.md b/docs/en/datasets/pose/tiger-pose.md index ec838b5ddb..d1e338ccac 100644 --- a/docs/en/datasets/pose/tiger-pose.md +++ b/docs/en/datasets/pose/tiger-pose.md @@ -126,7 +126,7 @@ To train a YOLOv8n-pose model on the Tiger-Pose dataset for 100 epochs with an i ```bash # Start training from a pretrained *.pt model - yolo task=pose mode=train data=tiger-pose.yaml model=yolov8n.pt epochs=100 imgsz=640 + yolo task=pose mode=train data=tiger-pose.yaml model=yolov8n-pose.pt epochs=100 imgsz=640 ``` ### What configurations does the `tiger-pose.yaml` file include? diff --git a/docs/en/datasets/segment/coco.md b/docs/en/datasets/segment/coco.md index dd77b2102c..862ee3882b 100644 --- a/docs/en/datasets/segment/coco.md +++ b/docs/en/datasets/segment/coco.md @@ -131,7 +131,7 @@ To train a YOLOv8n-seg model on the COCO-Seg dataset for 100 epochs with an imag ```bash # Start training from a pretrained *.pt model - yolo detect train data=coco-seg.yaml model=yolov8n.pt epochs=100 imgsz=640 + yolo detect train data=coco-seg.yaml model=yolov8n-seg.pt epochs=100 imgsz=640 ``` ### What are the key features of the COCO-Seg dataset? diff --git a/docs/en/datasets/segment/coco8-seg.md b/docs/en/datasets/segment/coco8-seg.md index 55006b1712..b781f8bede 100644 --- a/docs/en/datasets/segment/coco8-seg.md +++ b/docs/en/datasets/segment/coco8-seg.md @@ -106,7 +106,7 @@ To train a **YOLOv8n-seg** model on the COCO8-Seg dataset for 100 epochs with an ```bash # Start training from a pretrained *.pt model - yolo detect train data=coco8-seg.yaml model=yolov8n.pt epochs=100 imgsz=640 + yolo detect train data=coco8-seg.yaml model=yolov8n-seg.pt epochs=100 imgsz=640 ``` For a thorough explanation of available arguments and configuration options, you can check the [Training](../../modes/train.md) documentation. From 229ec678790a5c6d8913ad3b0675cc545cface29 Mon Sep 17 00:00:00 2001 From: Francesco Mattioli Date: Thu, 1 Aug 2024 12:59:40 +0200 Subject: [PATCH 03/10] Fixed `box_label` docstrings (#14866) Co-authored-by: dearMOMO <34231503+dearMOMO@users.noreply.github.com> --- ultralytics/utils/plotting.py | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/ultralytics/utils/plotting.py b/ultralytics/utils/plotting.py index f000a8c50a..74ca940cfd 100644 --- a/ultralytics/utils/plotting.py +++ b/ultralytics/utils/plotting.py @@ -280,7 +280,7 @@ class Annotator: Args: box (tuple): The bounding box coordinates (x1, y1, x2, y2). label (str): The text label to be displayed. - color (tuple, optional): The background color of the rectangle (R, G, B). + color (tuple, optional): The background color of the rectangle (B, G, R). txt_color (tuple, optional): The color of the text (R, G, B). rotated (bool, optional): Variable used to check if task is OBB """ From 8e3d6685ddfa6186df4f227309f7865c65c21f63 Mon Sep 17 00:00:00 2001 From: Jan Knobloch <116908874+jk4e@users.noreply.github.com> Date: Thu, 1 Aug 2024 16:41:13 +0200 Subject: [PATCH 04/10] Add missing CLI `yolo` commands for `TASK` and `MODE` in Docs - Quickstart and CLI Guide (#14882) Co-authored-by: Glenn Jocher --- docs/en/quickstart.md | 4 ++-- docs/en/usage/cli.md | 8 ++++---- ultralytics/utils/__init__.py | 18 +++++++++--------- 3 files changed, 15 insertions(+), 15 deletions(-) diff --git a/docs/en/quickstart.md b/docs/en/quickstart.md index 93ccaaa3e7..6a5a21dba4 100644 --- a/docs/en/quickstart.md +++ b/docs/en/quickstart.md @@ -162,8 +162,8 @@ The Ultralytics command line interface (CLI) allows for simple single-line comma yolo TASK MODE ARGS ``` - - `TASK` (optional) is one of ([detect](tasks/detect.md), [segment](tasks/segment.md), [classify](tasks/classify.md), [pose](tasks/pose.md)) - - `MODE` (required) is one of ([train](modes/train.md), [val](modes/val.md), [predict](modes/predict.md), [export](modes/export.md), [track](modes/track.md)) + - `TASK` (optional) is one of ([detect](tasks/detect.md), [segment](tasks/segment.md), [classify](tasks/classify.md), [pose](tasks/pose.md), [obb](tasks/obb.md)) + - `MODE` (required) is one of ([train](modes/train.md), [val](modes/val.md), [predict](modes/predict.md), [export](modes/export.md), [track](modes/track.md), [benchmark](modes/benchmark.md)) - `ARGS` (optional) are `arg=value` pairs like `imgsz=640` that override defaults. See all `ARGS` in the full [Configuration Guide](usage/cfg.md) or with the `yolo cfg` CLI command. diff --git a/docs/en/usage/cli.md b/docs/en/usage/cli.md index c1c221ffca..b78b031ab0 100644 --- a/docs/en/usage/cli.md +++ b/docs/en/usage/cli.md @@ -27,8 +27,8 @@ The YOLO command line interface (CLI) allows for simple single-line commands wit ```bash yolo TASK MODE ARGS - Where TASK (optional) is one of [detect, segment, classify] - MODE (required) is one of [train, val, predict, export, track] + Where TASK (optional) is one of [detect, segment, classify, pose, obb] + MODE (required) is one of [train, val, predict, export, track, benchmark] ARGS (optional) are any number of custom 'arg=value' pairs like 'imgsz=320' that override defaults. ``` See all ARGS in the full [Configuration Guide](cfg.md) or with `yolo cfg` @@ -75,8 +75,8 @@ The YOLO command line interface (CLI) allows for simple single-line commands wit Where: -- `TASK` (optional) is one of `[detect, segment, classify]`. If it is not passed explicitly YOLOv8 will try to guess the `TASK` from the model type. -- `MODE` (required) is one of `[train, val, predict, export, track]` +- `TASK` (optional) is one of `[detect, segment, classify, pose, obb]`. If it is not passed explicitly YOLOv8 will try to guess the `TASK` from the model type. +- `MODE` (required) is one of `[train, val, predict, export, track, benchmark]` - `ARGS` (optional) are any number of custom `arg=value` pairs like `imgsz=320` that override defaults. For a full list of available `ARGS` see the [Configuration](cfg.md) page and `defaults.yaml` !!! Warning "Warning" diff --git a/ultralytics/utils/__init__.py b/ultralytics/utils/__init__.py index 54cb175a16..9d0f562e76 100644 --- a/ultralytics/utils/__init__.py +++ b/ultralytics/utils/__init__.py @@ -47,7 +47,7 @@ PYTHON_VERSION = platform.python_version() TORCH_VERSION = torch.__version__ TORCHVISION_VERSION = importlib.metadata.version("torchvision") # faster than importing torchvision HELP_MSG = """ - Usage examples for running YOLOv8: + Usage examples for running Ultralytics YOLO: 1. Install the ultralytics package: @@ -58,25 +58,25 @@ HELP_MSG = """ from ultralytics import YOLO # Load a model - model = YOLO('yolov8n.yaml') # build a new model from scratch + model = YOLO("yolov8n.yaml") # build a new model from scratch model = YOLO("yolov8n.pt") # load a pretrained model (recommended for training) # Use the model results = model.train(data="coco8.yaml", epochs=3) # train the model results = model.val() # evaluate model performance on the validation set - results = model('https://ultralytics.com/images/bus.jpg') # predict on an image - success = model.export(format='onnx') # export the model to ONNX format + results = model("https://ultralytics.com/images/bus.jpg") # predict on an image + success = model.export(format="onnx") # export the model to ONNX format 3. Use the command line interface (CLI): - YOLOv8 'yolo' CLI commands use the following syntax: + Ultralytics 'yolo' CLI commands use the following syntax: yolo TASK MODE ARGS - Where TASK (optional) is one of [detect, segment, classify] - MODE (required) is one of [train, val, predict, export] - ARGS (optional) are any number of custom 'arg=value' pairs like 'imgsz=320' that override defaults. - See all ARGS at https://docs.ultralytics.com/usage/cfg or with 'yolo cfg' + Where TASK (optional) is one of [detect, segment, classify, pose, obb] + MODE (required) is one of [train, val, predict, export, benchmark] + ARGS (optional) are any number of custom "arg=value" pairs like "imgsz=320" that override defaults. + See all ARGS at https://docs.ultralytics.com/usage/cfg or with "yolo cfg" - Train a detection model for 10 epochs with an initial learning_rate of 0.01 yolo detect train data=coco8.yaml model=yolov8n.pt epochs=10 lr0=0.01 From fa2e8fc71d315a04e10b29000778ed4302660fdf Mon Sep 17 00:00:00 2001 From: Laughing <61612323+Laughing-q@users.noreply.github.com> Date: Thu, 1 Aug 2024 23:07:08 +0800 Subject: [PATCH 05/10] Update SAM 2 docs (#14864) --- docs/en/models/sam-2.md | 8 -------- 1 file changed, 8 deletions(-) diff --git a/docs/en/models/sam-2.md b/docs/en/models/sam-2.md index 001bd89b60..ef76f8a3cf 100644 --- a/docs/en/models/sam-2.md +++ b/docs/en/models/sam-2.md @@ -6,10 +6,6 @@ keywords: SAM 2, Segment Anything, video segmentation, image segmentation, promp # SAM 2: Segment Anything Model 2 -!!! Note "🚧 SAM 2 Integration In Progress 🚧" - - The SAM 2 features described in this documentation are currently not enabled in the `ultralytics` package. The Ultralytics team is actively working on integrating SAM 2, and these capabilities should be available soon. We appreciate your patience as we work to implement this exciting new model. - SAM 2, the successor to Meta's [Segment Anything Model (SAM)](sam.md), is a cutting-edge tool designed for comprehensive object segmentation in both images and videos. It excels in handling complex visual data through a unified, promptable model architecture that supports real-time processing and zero-shot generalization. ![SAM 2 Example Results](https://github.com/facebookresearch/segment-anything-2/raw/main/assets/sa_v_dataset.jpg?raw=true) @@ -105,10 +101,6 @@ pip install ultralytics ## How to Use SAM 2: Versatility in Image and Video Segmentation -!!! Note "🚧 SAM 2 Integration In Progress 🚧" - - The SAM 2 features described in this documentation are currently not enabled in the `ultralytics` package. The Ultralytics team is actively working on integrating SAM 2, and these capabilities should be available soon. We appreciate your patience as we work to implement this exciting new model. - The following table details the available SAM 2 models, their pre-trained weights, supported tasks, and compatibility with different operating modes like [Inference](../modes/predict.md), [Validation](../modes/val.md), [Training](../modes/train.md), and [Export](../modes/export.md). | Model Type | Pre-trained Weights | Tasks Supported | Inference | Validation | Training | Export | From eb184a6c07b4af83cf1be2984350ca2190af7425 Mon Sep 17 00:00:00 2001 From: Glenn Jocher Date: Thu, 1 Aug 2024 17:17:09 +0200 Subject: [PATCH 06/10] Increase Dockerfile build `max-parallel` (#14892) --- .github/workflows/docker.yaml | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/.github/workflows/docker.yaml b/.github/workflows/docker.yaml index d798cbec18..bae9221dd4 100644 --- a/.github/workflows/docker.yaml +++ b/.github/workflows/docker.yaml @@ -54,7 +54,7 @@ jobs: runs-on: ubuntu-latest strategy: fail-fast: false - max-parallel: 6 + max-parallel: 10 matrix: include: - dockerfile: "Dockerfile" @@ -133,7 +133,7 @@ jobs: uses: nick-invision/retry@v3 with: timeout_minutes: 120 - retry_wait_seconds: 30 + retry_wait_seconds: 60 max_attempts: 2 # retry once command: | docker build \ From 9ff33d67b6aba970cb675ba9e219ae75907d109f Mon Sep 17 00:00:00 2001 From: Jan Knobloch <116908874+jk4e@users.noreply.github.com> Date: Thu, 1 Aug 2024 17:18:31 +0200 Subject: [PATCH 07/10] Fix incorrect CLI commands in Datasets Docs (#14889) --- docs/en/datasets/classify/caltech101.md | 4 ++-- docs/en/datasets/classify/caltech256.md | 4 ++-- docs/en/datasets/classify/cifar10.md | 4 ++-- docs/en/datasets/classify/cifar100.md | 4 ++-- docs/en/datasets/classify/fashion-mnist.md | 4 ++-- docs/en/datasets/classify/imagenet.md | 4 ++-- docs/en/datasets/classify/imagenet10.md | 4 ++-- docs/en/datasets/classify/imagenette.md | 8 ++++---- docs/en/datasets/classify/imagewoof.md | 4 ++-- docs/en/datasets/classify/mnist.md | 4 ++-- docs/en/datasets/obb/index.md | 4 ++-- docs/en/datasets/pose/coco.md | 4 ++-- docs/en/datasets/pose/coco8-pose.md | 4 ++-- docs/en/datasets/pose/index.md | 2 +- docs/en/datasets/segment/coco.md | 4 ++-- docs/en/datasets/segment/coco8-seg.md | 4 ++-- docs/en/datasets/segment/index.md | 2 +- 17 files changed, 34 insertions(+), 34 deletions(-) diff --git a/docs/en/datasets/classify/caltech101.md b/docs/en/datasets/classify/caltech101.md index 451c4cc97e..6a75f66ac8 100644 --- a/docs/en/datasets/classify/caltech101.md +++ b/docs/en/datasets/classify/caltech101.md @@ -46,7 +46,7 @@ To train a YOLO model on the Caltech-101 dataset for 100 epochs, you can use the ```bash # Start training from a pretrained *.pt model - yolo detect train data=caltech101 model=yolov8n-cls.pt epochs=100 imgsz=416 + yolo classify train data=caltech101 model=yolov8n-cls.pt epochs=100 imgsz=416 ``` ## Sample Images and Annotations @@ -108,7 +108,7 @@ To train an Ultralytics YOLO model on the Caltech-101 dataset, you can use the p ```bash # Start training from a pretrained *.pt model - yolo detect train data=caltech101 model=yolov8n-cls.pt epochs=100 imgsz=416 + yolo classify train data=caltech101 model=yolov8n-cls.pt epochs=100 imgsz=416 ``` For more detailed arguments and options, refer to the model [Training](../../modes/train.md) page. diff --git a/docs/en/datasets/classify/caltech256.md b/docs/en/datasets/classify/caltech256.md index 6c6cf4a65a..c7b367cc63 100644 --- a/docs/en/datasets/classify/caltech256.md +++ b/docs/en/datasets/classify/caltech256.md @@ -57,7 +57,7 @@ To train a YOLO model on the Caltech-256 dataset for 100 epochs, you can use the ```bash # Start training from a pretrained *.pt model - yolo detect train data=caltech256 model=yolov8n-cls.pt epochs=100 imgsz=416 + yolo classify train data=caltech256 model=yolov8n-cls.pt epochs=100 imgsz=416 ``` ## Sample Images and Annotations @@ -116,7 +116,7 @@ To train a YOLO model on the Caltech-256 dataset for 100 epochs, you can use the ```bash # Start training from a pretrained *.pt model - yolo detect train data=caltech256 model=yolov8n-cls.pt epochs=100 imgsz=416 + yolo classify train data=caltech256 model=yolov8n-cls.pt epochs=100 imgsz=416 ``` ### What are the most common use cases for the Caltech-256 dataset? diff --git a/docs/en/datasets/classify/cifar10.md b/docs/en/datasets/classify/cifar10.md index 513f838319..b4742cbcb7 100644 --- a/docs/en/datasets/classify/cifar10.md +++ b/docs/en/datasets/classify/cifar10.md @@ -60,7 +60,7 @@ To train a YOLO model on the CIFAR-10 dataset for 100 epochs with an image size ```bash # Start training from a pretrained *.pt model - yolo detect train data=cifar10 model=yolov8n-cls.pt epochs=100 imgsz=32 + yolo classify train data=cifar10 model=yolov8n-cls.pt epochs=100 imgsz=32 ``` ## Sample Images and Annotations @@ -114,7 +114,7 @@ To train a YOLO model on the CIFAR-10 dataset using Ultralytics, you can follow ```bash # Start training from a pretrained *.pt model - yolo detect train data=cifar10 model=yolov8n-cls.pt epochs=100 imgsz=32 + yolo classify train data=cifar10 model=yolov8n-cls.pt epochs=100 imgsz=32 ``` For more details, refer to the model [Training](../../modes/train.md) page. diff --git a/docs/en/datasets/classify/cifar100.md b/docs/en/datasets/classify/cifar100.md index 5110564ef0..4a8ba4bd8b 100644 --- a/docs/en/datasets/classify/cifar100.md +++ b/docs/en/datasets/classify/cifar100.md @@ -49,7 +49,7 @@ To train a YOLO model on the CIFAR-100 dataset for 100 epochs with an image size ```bash # Start training from a pretrained *.pt model - yolo detect train data=cifar100 model=yolov8n-cls.pt epochs=100 imgsz=32 + yolo classify train data=cifar100 model=yolov8n-cls.pt epochs=100 imgsz=32 ``` ## Sample Images and Annotations @@ -107,7 +107,7 @@ You can train a YOLO model on the CIFAR-100 dataset using either Python or CLI c ```bash # Start training from a pretrained *.pt model - yolo detect train data=cifar100 model=yolov8n-cls.pt epochs=100 imgsz=32 + yolo classify train data=cifar100 model=yolov8n-cls.pt epochs=100 imgsz=32 ``` For a comprehensive list of available arguments, please refer to the model [Training](../../modes/train.md) page. diff --git a/docs/en/datasets/classify/fashion-mnist.md b/docs/en/datasets/classify/fashion-mnist.md index 21373268e1..656473edf5 100644 --- a/docs/en/datasets/classify/fashion-mnist.md +++ b/docs/en/datasets/classify/fashion-mnist.md @@ -74,7 +74,7 @@ To train a CNN model on the Fashion-MNIST dataset for 100 epochs with an image s ```bash # Start training from a pretrained *.pt model - yolo detect train data=fashion-mnist model=yolov8n-cls.pt epochs=100 imgsz=28 + yolo classify train data=fashion-mnist model=yolov8n-cls.pt epochs=100 imgsz=28 ``` ## Sample Images and Annotations @@ -117,7 +117,7 @@ To train an Ultralytics YOLO model on the Fashion-MNIST dataset, you can use bot === "CLI" ```bash - yolo detect train data=fashion-mnist model=yolov8n-cls.pt epochs=100 imgsz=28 + yolo classify train data=fashion-mnist model=yolov8n-cls.pt epochs=100 imgsz=28 ``` For more detailed training parameters, refer to the [Training page](../../modes/train.md). diff --git a/docs/en/datasets/classify/imagenet.md b/docs/en/datasets/classify/imagenet.md index e563568026..53aabccef0 100644 --- a/docs/en/datasets/classify/imagenet.md +++ b/docs/en/datasets/classify/imagenet.md @@ -59,7 +59,7 @@ To train a deep learning model on the ImageNet dataset for 100 epochs with an im ```bash # Start training from a pretrained *.pt model - yolo train data=imagenet model=yolov8n-cls.pt epochs=100 imgsz=224 + yolo classify train data=imagenet model=yolov8n-cls.pt epochs=100 imgsz=224 ``` ## Sample Images and Annotations @@ -120,7 +120,7 @@ To use a pretrained Ultralytics YOLO model for image classification on the Image ```bash # Start training from a pretrained *.pt model - yolo train data=imagenet model=yolov8n-cls.pt epochs=100 imgsz=224 + yolo classify train data=imagenet model=yolov8n-cls.pt epochs=100 imgsz=224 ``` For more in-depth training instruction, refer to our [Training page](../../modes/train.md). diff --git a/docs/en/datasets/classify/imagenet10.md b/docs/en/datasets/classify/imagenet10.md index d7bf55e483..a079986cce 100644 --- a/docs/en/datasets/classify/imagenet10.md +++ b/docs/en/datasets/classify/imagenet10.md @@ -45,7 +45,7 @@ To test a deep learning model on the ImageNet10 dataset with an image size of 22 ```bash # Start training from a pretrained *.pt model - yolo train data=imagenet10 model=yolov8n-cls.pt epochs=5 imgsz=224 + yolo classify train data=imagenet10 model=yolov8n-cls.pt epochs=5 imgsz=224 ``` ## Sample Images and Annotations @@ -104,7 +104,7 @@ To test your deep learning model on the ImageNet10 dataset with an image size of ```bash # Start training from a pretrained *.pt model - yolo train data=imagenet10 model=yolov8n-cls.pt epochs=5 imgsz=224 + yolo classify train data=imagenet10 model=yolov8n-cls.pt epochs=5 imgsz=224 ``` Refer to the [Training](../../modes/train.md) page for a comprehensive list of available arguments. diff --git a/docs/en/datasets/classify/imagenette.md b/docs/en/datasets/classify/imagenette.md index b667192aec..9a2a128ff6 100644 --- a/docs/en/datasets/classify/imagenette.md +++ b/docs/en/datasets/classify/imagenette.md @@ -47,7 +47,7 @@ To train a model on the ImageNette dataset for 100 epochs with a standard image ```bash # Start training from a pretrained *.pt model - yolo detect train data=imagenette model=yolov8n-cls.pt epochs=100 imgsz=224 + yolo classify train data=imagenette model=yolov8n-cls.pt epochs=100 imgsz=224 ``` ## Sample Images and Annotations @@ -82,7 +82,7 @@ To use these datasets, simply replace 'imagenette' with 'imagenette160' or 'imag ```bash # Start training from a pretrained *.pt model with ImageNette160 - yolo detect train data=imagenette160 model=yolov8n-cls.pt epochs=100 imgsz=160 + yolo classify train data=imagenette160 model=yolov8n-cls.pt epochs=100 imgsz=160 ``` !!! Example "Train Example with ImageNette320" @@ -103,7 +103,7 @@ To use these datasets, simply replace 'imagenette' with 'imagenette160' or 'imag ```bash # Start training from a pretrained *.pt model with ImageNette320 - yolo detect train data=imagenette320 model=yolov8n-cls.pt epochs=100 imgsz=320 + yolo classify train data=imagenette320 model=yolov8n-cls.pt epochs=100 imgsz=320 ``` These smaller versions of the dataset allow for rapid iterations during the development process while still providing valuable and realistic image classification tasks. @@ -140,7 +140,7 @@ To train a YOLO model on the ImageNette dataset for 100 epochs, you can use the ```bash # Start training from a pretrained *.pt model - yolo detect train data=imagenette model=yolov8n-cls.pt epochs=100 imgsz=224 + yolo classify train data=imagenette model=yolov8n-cls.pt epochs=100 imgsz=224 ``` For more details, see the [Training](../../modes/train.md) documentation page. diff --git a/docs/en/datasets/classify/imagewoof.md b/docs/en/datasets/classify/imagewoof.md index 2a439425f8..5a76d97fc2 100644 --- a/docs/en/datasets/classify/imagewoof.md +++ b/docs/en/datasets/classify/imagewoof.md @@ -44,7 +44,7 @@ To train a CNN model on the ImageWoof dataset for 100 epochs with an image size ```bash # Start training from a pretrained *.pt model - yolo detect train data=imagewoof model=yolov8n-cls.pt epochs=100 imgsz=224 + yolo classify train data=imagewoof model=yolov8n-cls.pt epochs=100 imgsz=224 ``` ## Dataset Variants @@ -113,7 +113,7 @@ To train a Convolutional Neural Network (CNN) model on the ImageWoof dataset usi === "CLI" ```bash - yolo detect train data=imagewoof model=yolov8n-cls.pt epochs=100 imgsz=224 + yolo classify train data=imagewoof model=yolov8n-cls.pt epochs=100 imgsz=224 ``` For more details on available training arguments, refer to the [Training](../../modes/train.md) page. diff --git a/docs/en/datasets/classify/mnist.md b/docs/en/datasets/classify/mnist.md index 8f8ad1265d..ae9be2bceb 100644 --- a/docs/en/datasets/classify/mnist.md +++ b/docs/en/datasets/classify/mnist.md @@ -52,7 +52,7 @@ To train a CNN model on the MNIST dataset for 100 epochs with an image size of 3 ```bash # Start training from a pretrained *.pt model - cnn detect train data=mnist model=yolov8n-cls.pt epochs=100 imgsz=28 + yolo classify train data=mnist model=yolov8n-cls.pt epochs=100 imgsz=28 ``` ## Sample Images and Annotations @@ -113,7 +113,7 @@ To train a model on the MNIST dataset using Ultralytics YOLO, you can follow the ```bash # Start training from a pretrained *.pt model - cnn detect train data=mnist model=yolov8n-cls.pt epochs=100 imgsz=28 + yolo classify train data=mnist model=yolov8n-cls.pt epochs=100 imgsz=28 ``` For a detailed list of available training arguments, refer to the [Training](../../modes/train.md) page. diff --git a/docs/en/datasets/obb/index.md b/docs/en/datasets/obb/index.md index b0b548b0d5..f7708a10a0 100644 --- a/docs/en/datasets/obb/index.md +++ b/docs/en/datasets/obb/index.md @@ -50,7 +50,7 @@ To train a model using these OBB formats: ```bash # Train a new YOLOv8n-OBB model on the DOTAv2 dataset - yolo detect train data=DOTAv1.yaml model=yolov8n.pt epochs=100 imgsz=640 + yolo obb train data=DOTAv1.yaml model=yolov8n-obb.pt epochs=100 imgsz=640 ``` ## Supported Datasets @@ -125,7 +125,7 @@ Training a YOLOv8 model with OBBs involves ensuring your dataset is in the YOLO ```bash # Train a new YOLOv8n-OBB model on the custom dataset - yolo detect train data=your_dataset.yaml model=yolov8n.pt epochs=100 imgsz=640 + yolo obb train data=your_dataset.yaml model=yolov8n-obb.yaml epochs=100 imgsz=640 ``` This ensures your model leverages the detailed OBB annotations for improved detection accuracy. diff --git a/docs/en/datasets/pose/coco.md b/docs/en/datasets/pose/coco.md index 11cde4dd63..52fce86c03 100644 --- a/docs/en/datasets/pose/coco.md +++ b/docs/en/datasets/pose/coco.md @@ -71,7 +71,7 @@ To train a YOLOv8n-pose model on the COCO-Pose dataset for 100 epochs with an im ```bash # Start training from a pretrained *.pt model - yolo detect train data=coco-pose.yaml model=yolov8n-pose.pt epochs=100 imgsz=640 + yolo pose train data=coco-pose.yaml model=yolov8n-pose.pt epochs=100 imgsz=640 ``` ## Sample Images and Annotations @@ -133,7 +133,7 @@ Training a YOLOv8 model on the COCO-Pose dataset can be accomplished using eithe ```bash # Start training from a pretrained *.pt model - yolo detect train data=coco-pose.yaml model=yolov8n-pose.pt epochs=100 imgsz=640 + yolo pose train data=coco-pose.yaml model=yolov8n-pose.pt epochs=100 imgsz=640 ``` For more details on the training process and available arguments, check the [training page](../../modes/train.md). diff --git a/docs/en/datasets/pose/coco8-pose.md b/docs/en/datasets/pose/coco8-pose.md index c8d4a37542..49295ac483 100644 --- a/docs/en/datasets/pose/coco8-pose.md +++ b/docs/en/datasets/pose/coco8-pose.md @@ -44,7 +44,7 @@ To train a YOLOv8n-pose model on the COCO8-Pose dataset for 100 epochs with an i ```bash # Start training from a pretrained *.pt model - yolo detect train data=coco8-pose.yaml model=yolov8n-pose.pt epochs=100 imgsz=640 + yolo pose train data=coco8-pose.yaml model=yolov8n-pose.pt epochs=100 imgsz=640 ``` ## Sample Images and Annotations @@ -105,7 +105,7 @@ To train a YOLOv8n-pose model on the COCO8-Pose dataset for 100 epochs with an i === "CLI" ```bash - yolo detect train data=coco8-pose.yaml model=yolov8n-pose.pt epochs=100 imgsz=640 + yolo pose train data=coco8-pose.yaml model=yolov8n-pose.pt epochs=100 imgsz=640 ``` For a comprehensive list of training arguments, refer to the model [Training](../../modes/train.md) page. diff --git a/docs/en/datasets/pose/index.md b/docs/en/datasets/pose/index.md index 29179d8c68..57c20dcb7c 100644 --- a/docs/en/datasets/pose/index.md +++ b/docs/en/datasets/pose/index.md @@ -82,7 +82,7 @@ The `train` and `val` fields specify the paths to the directories containing the ```bash # Start training from a pretrained *.pt model - yolo detect train data=coco8-pose.yaml model=yolov8n-pose.pt epochs=100 imgsz=640 + yolo pose train data=coco8-pose.yaml model=yolov8n-pose.pt epochs=100 imgsz=640 ``` ## Supported Datasets diff --git a/docs/en/datasets/segment/coco.md b/docs/en/datasets/segment/coco.md index 862ee3882b..e02b677115 100644 --- a/docs/en/datasets/segment/coco.md +++ b/docs/en/datasets/segment/coco.md @@ -69,7 +69,7 @@ To train a YOLOv8n-seg model on the COCO-Seg dataset for 100 epochs with an imag ```bash # Start training from a pretrained *.pt model - yolo detect train data=coco-seg.yaml model=yolov8n-seg.pt epochs=100 imgsz=640 + yolo segment train data=coco-seg.yaml model=yolov8n-seg.pt epochs=100 imgsz=640 ``` ## Sample Images and Annotations @@ -131,7 +131,7 @@ To train a YOLOv8n-seg model on the COCO-Seg dataset for 100 epochs with an imag ```bash # Start training from a pretrained *.pt model - yolo detect train data=coco-seg.yaml model=yolov8n-seg.pt epochs=100 imgsz=640 + yolo segment train data=coco-seg.yaml model=yolov8n-seg.pt epochs=100 imgsz=640 ``` ### What are the key features of the COCO-Seg dataset? diff --git a/docs/en/datasets/segment/coco8-seg.md b/docs/en/datasets/segment/coco8-seg.md index b781f8bede..bcca4a2641 100644 --- a/docs/en/datasets/segment/coco8-seg.md +++ b/docs/en/datasets/segment/coco8-seg.md @@ -44,7 +44,7 @@ To train a YOLOv8n-seg model on the COCO8-Seg dataset for 100 epochs with an ima ```bash # Start training from a pretrained *.pt model - yolo detect train data=coco8-seg.yaml model=yolov8n-seg.pt epochs=100 imgsz=640 + yolo segment train data=coco8-seg.yaml model=yolov8n-seg.pt epochs=100 imgsz=640 ``` ## Sample Images and Annotations @@ -106,7 +106,7 @@ To train a **YOLOv8n-seg** model on the COCO8-Seg dataset for 100 epochs with an ```bash # Start training from a pretrained *.pt model - yolo detect train data=coco8-seg.yaml model=yolov8n-seg.pt epochs=100 imgsz=640 + yolo segment train data=coco8-seg.yaml model=yolov8n-seg.pt epochs=100 imgsz=640 ``` For a thorough explanation of available arguments and configuration options, you can check the [Training](../../modes/train.md) documentation. diff --git a/docs/en/datasets/segment/index.md b/docs/en/datasets/segment/index.md index 27cb43741f..f9228c0812 100644 --- a/docs/en/datasets/segment/index.md +++ b/docs/en/datasets/segment/index.md @@ -84,7 +84,7 @@ The `train` and `val` fields specify the paths to the directories containing the ```bash # Start training from a pretrained *.pt model - yolo detect train data=coco8-seg.yaml model=yolov8n-seg.pt epochs=100 imgsz=640 + yolo segment train data=coco8-seg.yaml model=yolov8n-seg.pt epochs=100 imgsz=640 ``` ## Supported Datasets From 16fc32530809b74961aabf26a39d8a6461948d17 Mon Sep 17 00:00:00 2001 From: Muhammad Rizwan Munawar Date: Thu, 1 Aug 2024 20:28:53 +0500 Subject: [PATCH 08/10] Add Segment masks to YOLO-Seg labels converter (#14557) Signed-off-by: Glenn Jocher Co-authored-by: UltralyticsAssistant Co-authored-by: Glenn Jocher --- docs/en/reference/data/converter.md | 4 ++ docs/en/usage/simple-utilities.md | 16 ++++++ docs/mkdocs_github_authors.yaml | 1 + ultralytics/data/converter.py | 81 +++++++++++++++++++++++++++++ 4 files changed, 102 insertions(+) diff --git a/docs/en/reference/data/converter.md b/docs/en/reference/data/converter.md index d1b63f2f0e..2854e7d228 100644 --- a/docs/en/reference/data/converter.md +++ b/docs/en/reference/data/converter.md @@ -23,6 +23,10 @@ keywords: Ultralytics, data conversion, YOLO models, COCO, DOTA, YOLO bbox2segme


+## ::: ultralytics.data.converter.convert_segment_masks_to_yolo_seg + +


+ ## ::: ultralytics.data.converter.convert_dota_to_yolo_obb


diff --git a/docs/en/usage/simple-utilities.md b/docs/en/usage/simple-utilities.md index 99206eb202..694ecf1dfe 100644 --- a/docs/en/usage/simple-utilities.md +++ b/docs/en/usage/simple-utilities.md @@ -51,6 +51,22 @@ auto_annotate( # (1)! - Use in combination with the [function `segments2boxes`](#convert-segments-to-bounding-boxes) to generate object detection bounding boxes as well +### Convert Segmentation Masks into YOLO Format + +![Segmentation Masks to YOLO Format](https://github.com/user-attachments/assets/1a823fc1-f3a1-4dd5-83e7-0b209df06fc3) + +Use to convert a dataset of segmentation mask images to the `YOLO` segmentation format. +This function takes the directory containing the binary format mask images and converts them into YOLO segmentation format. + +The converted masks will be saved in the specified output directory. + +```python +from ultralytics.data.converter import convert_segment_masks_to_yolo_seg + +# For COCO dataset we have 80 classes +convert_segment_masks_to_yolo_seg(masks_dir="path/to/masks_dir", output_dir="path/to/output_dir", classes=80) +``` + ### Convert COCO into YOLO Format Use to convert COCO JSON annotations into proper YOLO format. For object detection (bounding box) datasets, `use_segments` and `use_keypoints` should both be `False` diff --git a/docs/mkdocs_github_authors.yaml b/docs/mkdocs_github_authors.yaml index bfaddb3a7a..210c359506 100644 --- a/docs/mkdocs_github_authors.yaml +++ b/docs/mkdocs_github_authors.yaml @@ -1,3 +1,4 @@ +116908874+jk4e@users.noreply.github.com: jk4e 1185102784@qq.com: Laughing-q 130829914+IvorZhu331@users.noreply.github.com: IvorZhu331 135830346+UltralyticsAssistant@users.noreply.github.com: UltralyticsAssistant diff --git a/ultralytics/data/converter.py b/ultralytics/data/converter.py index 0ee390877d..34b359d61f 100644 --- a/ultralytics/data/converter.py +++ b/ultralytics/data/converter.py @@ -334,6 +334,87 @@ def convert_coco( LOGGER.info(f"{'LVIS' if lvis else 'COCO'} data converted successfully.\nResults saved to {save_dir.resolve()}") +def convert_segment_masks_to_yolo_seg(masks_dir, output_dir, classes): + """ + Converts a dataset of segmentation mask images to the YOLO segmentation format. + + This function takes the directory containing the binary format mask images and converts them into YOLO segmentation format. + The converted masks are saved in the specified output directory. + + Args: + masks_dir (str): The path to the directory where all mask images (png, jpg) are stored. + output_dir (str): The path to the directory where the converted YOLO segmentation masks will be stored. + classes (int): Total classes in the dataset i.e for COCO classes=80 + + Example: + ```python + from ultralytics.data.converter import convert_segment_masks_to_yolo_seg + + # for coco dataset, we have 80 classes + convert_segment_masks_to_yolo_seg('path/to/masks_directory', 'path/to/output/directory', classes=80) + ``` + + Notes: + The expected directory structure for the masks is: + + - masks + ├─ mask_image_01.png or mask_image_01.jpg + ├─ mask_image_02.png or mask_image_02.jpg + ├─ mask_image_03.png or mask_image_03.jpg + └─ mask_image_04.png or mask_image_04.jpg + + After execution, the labels will be organized in the following structure: + + - output_dir + ├─ mask_yolo_01.txt + ├─ mask_yolo_02.txt + ├─ mask_yolo_03.txt + └─ mask_yolo_04.txt + """ + import os + + pixel_to_class_mapping = {i + 1: i for i in range(80)} + for mask_filename in os.listdir(masks_dir): + if mask_filename.endswith(".png"): + mask_path = os.path.join(masks_dir, mask_filename) + mask = cv2.imread(mask_path, cv2.IMREAD_GRAYSCALE) # Read the mask image in grayscale + img_height, img_width = mask.shape # Get image dimensions + LOGGER.info(f"Processing {mask_path} imgsz = {img_height} x {img_width}") + + unique_values = np.unique(mask) # Get unique pixel values representing different classes + yolo_format_data = [] + + for value in unique_values: + if value == 0: + continue # Skip background + class_index = pixel_to_class_mapping.get(value, -1) + if class_index == -1: + LOGGER.warning(f"Unknown class for pixel value {value} in file {mask_filename}, skipping.") + continue + + # Create a binary mask for the current class and find contours + contours, _ = cv2.findContours( + (mask == value).astype(np.uint8), cv2.RETR_EXTERNAL, cv2.CHAIN_APPROX_SIMPLE + ) # Find contours + + for contour in contours: + if len(contour) >= 3: # YOLO requires at least 3 points for a valid segmentation + contour = contour.squeeze() # Remove single-dimensional entries + yolo_format = [class_index] + for point in contour: + # Normalize the coordinates + yolo_format.append(round(point[0] / img_width, 6)) # Rounding to 6 decimal places + yolo_format.append(round(point[1] / img_height, 6)) + yolo_format_data.append(yolo_format) + # Save Ultralytics YOLO format data to file + output_path = os.path.join(output_dir, os.path.splitext(mask_filename)[0] + ".txt") + with open(output_path, "w") as file: + for item in yolo_format_data: + line = " ".join(map(str, item)) + file.write(line + "\n") + LOGGER.info(f"Processed and stored at {output_path} imgsz = {img_height} x {img_width}") + + def convert_dota_to_yolo_obb(dota_root_path: str): """ Converts DOTA dataset annotations to YOLO OBB (Oriented Bounding Box) format. From 9c5d1a24511397d1d355eb3d759a49d2939e7123 Mon Sep 17 00:00:00 2001 From: Haris Rehman <115916265+Harri200191@users.noreply.github.com> Date: Thu, 1 Aug 2024 20:31:03 +0500 Subject: [PATCH 09/10] `ultralytics 8.2.71` Multinode DDP training (#14879) Co-authored-by: Haris Rehman Co-authored-by: Glenn Jocher Co-authored-by: UltralyticsAssistant --- .gitignore | 3 +++ ultralytics/__init__.py | 2 +- ultralytics/engine/trainer.py | 5 +++-- ultralytics/utils/torch_utils.py | 3 ++- 4 files changed, 9 insertions(+), 4 deletions(-) diff --git a/.gitignore b/.gitignore index 1b68ec6b2c..1c0c5fbea6 100644 --- a/.gitignore +++ b/.gitignore @@ -26,6 +26,9 @@ share/python-wheels/ .installed.cfg *.egg MANIFEST +requirements.txt +setup.py +ultralytics.egg-info # PyInstaller # Usually these files are written by a python script from a template diff --git a/ultralytics/__init__.py b/ultralytics/__init__.py index affb8e35c7..8eb9bc7812 100644 --- a/ultralytics/__init__.py +++ b/ultralytics/__init__.py @@ -1,6 +1,6 @@ # Ultralytics YOLO 🚀, AGPL-3.0 license -__version__ = "8.2.70" +__version__ = "8.2.71" import os diff --git a/ultralytics/engine/trainer.py b/ultralytics/engine/trainer.py index 48e95679cf..47063466ad 100644 --- a/ultralytics/engine/trainer.py +++ b/ultralytics/engine/trainer.py @@ -26,6 +26,7 @@ from ultralytics.data.utils import check_cls_dataset, check_det_dataset from ultralytics.nn.tasks import attempt_load_one_weight, attempt_load_weights from ultralytics.utils import ( DEFAULT_CFG, + LOCAL_RANK, LOGGER, RANK, TQDM, @@ -129,7 +130,7 @@ class BaseTrainer: # Model and Dataset self.model = check_model_file_from_stem(self.args.model) # add suffix, i.e. yolov8n -> yolov8n.pt - with torch_distributed_zero_first(RANK): # avoid auto-downloading dataset multiple times + with torch_distributed_zero_first(LOCAL_RANK): # avoid auto-downloading dataset multiple times self.trainset, self.testset = self.get_dataset() self.ema = None @@ -285,7 +286,7 @@ class BaseTrainer: # Dataloaders batch_size = self.batch_size // max(world_size, 1) - self.train_loader = self.get_dataloader(self.trainset, batch_size=batch_size, rank=RANK, mode="train") + self.train_loader = self.get_dataloader(self.trainset, batch_size=batch_size, rank=LOCAL_RANK, mode="train") if RANK in {-1, 0}: # Note: When training DOTA dataset, double batch size could get OOM on images with >2000 objects. self.test_loader = self.get_dataloader( diff --git a/ultralytics/utils/torch_utils.py b/ultralytics/utils/torch_utils.py index 624167694f..fd24403d5a 100644 --- a/ultralytics/utils/torch_utils.py +++ b/ultralytics/utils/torch_utils.py @@ -48,11 +48,12 @@ TORCHVISION_0_18 = check_version(TORCHVISION_VERSION, "0.18.0") def torch_distributed_zero_first(local_rank: int): """Ensures all processes in distributed training wait for the local master (rank 0) to complete a task first.""" initialized = dist.is_available() and dist.is_initialized() + if initialized and local_rank not in {-1, 0}: dist.barrier(device_ids=[local_rank]) yield if initialized and local_rank == 0: - dist.barrier(device_ids=[0]) + dist.barrier(device_ids=[local_rank]) def smart_inference_mode(): From 9f22f45189bd32efc14ddcb7b7b42a548b7aef6f Mon Sep 17 00:00:00 2001 From: Lakshantha Dissanayake Date: Thu, 1 Aug 2024 11:18:58 -0700 Subject: [PATCH 10/10] Delete Docker Cache before building Image (#14894) Co-authored-by: Glenn Jocher --- .github/workflows/docker.yaml | 9 +++++++++ 1 file changed, 9 insertions(+) diff --git a/.github/workflows/docker.yaml b/.github/workflows/docker.yaml index bae9221dd4..359db69ddb 100644 --- a/.github/workflows/docker.yaml +++ b/.github/workflows/docker.yaml @@ -82,6 +82,15 @@ jobs: # tags: "latest-conda" # platforms: "linux/amd64" steps: + - name: Cleanup toolcache + # Free up to 10GB of disk space per https://github.com/ultralytics/ultralytics/pull/14894 + run: | + echo "Free space before deletion:" + df -h / + rm -rf /opt/hostedtoolcache + echo "Free space after deletion:" + df -h / + - name: Checkout repo uses: actions/checkout@v4 with: