| Label and export your custom datasets directly to YOLOv8 for training with [Roboflow](https://roboflow.com/?ref=ultralytics) | Automatically track, visualize and even remotely train YOLOv8 using [ClearML](https://cutt.ly/yolov5-readme-clearml) (open-source!) | Free forever, [Comet](https://bit.ly/yolov8-readme-comet) lets you save YOLOv8 models, resume training, and interactively visualize and debug predictions | Run YOLOv8 inference up to 6x faster with [Neural Magic DeepSparse](https://bit.ly/yolov5-neuralmagic) |
| Label and export your custom datasets directly to YOLOv8 for training with [Roboflow](https://roboflow.com/?ref=ultralytics) | Automatically track, visualize and even remotely train YOLOv8 using [ClearML](https://clear.ml/) (open-source!) | Free forever, [Comet](https://bit.ly/yolov8-readme-comet) lets you save YOLOv8 models, resume training, and interactively visualize and debug predictions | Run YOLOv8 inference up to 6x faster with [Neural Magic DeepSparse](https://bit.ly/yolov5-neuralmagic) |
Embeddings table for a given dataset and model pair is only created once and reused. These use [LanceDB](https://lancedb.github.io/lancedb/) under the hood, which scales on-disk, so you can create and reuse embeddings for large datasets like COCO without running out of memory.
In case you want to force update the embeddings table, you can pass `force=True` to `create_embeddings_table` method.
You can direclty access the LanceDB table object to perform advanced analysis. Learn more about it in [Working with table section](#4-advanced---working-with-embeddings-table)
You can directly access the LanceDB table object to perform advanced analysis. Learn more about it in [Working with table section](#4-advanced---working-with-embeddings-table)
| `cpu()` | Method | Move the object to CPU memory. |
| `numpy()` | Method | Convert the object to a numpy array. |
| `cuda()` | Method | Move the object to CUDA memory. |
| `to()` | Method | Move the object to the specified device. |
| `conf` | Property (`torch.Tensor`) | Return the confidence values of the boxes. |
| `cls` | Property (`torch.Tensor`) | Return the class values of the boxes. |
| `id` | Property (`torch.Tensor`) | Return the track IDs of the boxes (if available). |
| `xyxy` | Property (`torch.Tensor`) | Return the horizontal boxes in xyxy format. |
| `xywhr` | Property (`torch.Tensor`) | Return the rotated boxes in xywhr format. |
| `xyxyxyxy` | Property (`torch.Tensor`) | Return the rotated boxes in xyxyxyxy format. |
| `xyxyxyxyn` | Property (`torch.Tensor`) | Return the rotated boxes in xyxyxyxy format normalized by image size. |
For more details see the `OBB` class [documentation](../reference/engine/results.md#ultralytics.engine.results.OBB).
## Plotting Results
You can use the `plot()` method of a `Result` objects to visualize predictions. It plots all prediction types (boxes, masks, keypoints, probabilities, etc.) contained in the `Results` object onto a numpy array that can then be shown or saved.
description: Discover OBBPredictor for YOLO, specializing in Oriented Bounding Box predictions. Essential for advanced object detection with Ultralytics YOLO.
description: Master the Ultralytics YOLO OBB Trainer: A specialized tool for training YOLO models using Oriented Bounding Boxes. Features detailed usage, model initialization, and training processes.
keywords: Ultralytics, YOLO OBB Trainer, Oriented Bounding Box, OBB model training, YOLO model training, computer vision, deep learning, machine learning, YOLO object detection, model initialization, YOLO training process
---
# Reference for `ultralytics/models/yolo/obb/train.py`
@ -18,6 +18,11 @@ The output of an oriented object detector is a set of rotated bounding boxes tha
YOLOv8 OBB models use the `-obb` suffix, i.e. `yolov8n-obb.pt` and are pretrained on [DOTAv1](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/datasets/DOTAv1.yaml).
| Ships Detection using OBB | Vehicle Detection using OBB |
YOLOv8 pretrained OBB models are shown here, which are pretrained on the [DOTAv1](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/cfg/datasets/DOTAv1.yaml) dataset.
@ -10,7 +10,7 @@ keywords: ClearML, YOLOv5, Ultralytics, AI toolbox, training data, remote traini
## About ClearML
[ClearML](https://cutt.ly/yolov5-tutorial-clearml) is an [open-source](https://github.com/allegroai/clearml) toolbox designed to save you time ⏱️.
[ClearML](https://clear.ml/) is an [open-source](https://github.com/allegroai/clearml) toolbox designed to save you time ⏱️.
🔨 Track every YOLOv5 training run in the <b>experiment manager</b>
@ -36,7 +36,7 @@ And so much more. It's up to you how many of these tools you want to use, you ca
To keep track of your experiments and/or data, ClearML needs to communicate to a server. You have 2 options to get one:
Either sign up for free to the [ClearML Hosted Service](https://cutt.ly/yolov5-tutorial-clearml) or you can set up your own server, see [here](https://clear.ml/docs/latest/docs/deploying_clearml/clearml_server). Even the server is open-source, so even if you're dealing with sensitive data, you should be good to go!
Either sign up for free to the [ClearML Hosted Service](https://clear.ml/) or you can set up your own server, see [here](https://clear.ml/docs/latest/docs/deploying_clearml/clearml_server). Even the server is open-source, so even if you're dealing with sensitive data, you should be good to go!
@ -34,12 +34,9 @@ Creating a custom model to detect your objects is an iterative process of collec
For more details see [Ultralytics Licensing](https://ultralytics.com/license).
### 1. Create Dataset
YOLOv5 models must be trained on labelled data in order to learn classes of objects in that data. There are two options for creating your dataset before you start training:
<detailsopen>
<summary>Use <ahref="https://roboflow.com/?ref=ultralytics">Roboflow</a> to create your dataset in YOLO format 🌟</summary>
## Option 1: Create a <ahref="https://roboflow.com/?ref=ultralytics">Roboflow</a> Dataset
### 1.1 Collect Images
@ -68,7 +65,7 @@ Note: YOLOv5 does online augmentation during training, so we do not recommend ap
- **Auto-Orient** - to strip EXIF orientation from your images.
- **Resize (Stretch)** - to the square input size of your model (640x640 is the YOLOv5 default).
Generating a version will give you a point in time snapshot of your dataset so you can always go back and compare your future model training runs against it, even if you add more images or change its configuration later.
Generating a version will give you a snapshot of your dataset, so you can always go back and compare your future model training runs against it, even if you add more images or change its configuration later.
<palign="center"><imgwidth="450"src="https://uploads-ssl.webflow.com/5f6bc60e665f54545a1e52a5/6152a2733fd1da943619934e_roboflow-export.png"alt="Export in YOLOv5 Format"></p>
@ -76,14 +73,9 @@ Export in `YOLOv5 Pytorch` format, then copy the snippet into your training scri
<summary>Or manually prepare your dataset</summary>
### 1.1 Create dataset.yaml
### 2.1 Create `dataset.yaml`
[COCO128](https://www.kaggle.com/ultralytics/coco128) is an example small tutorial dataset composed of the first 128 images in [COCO](http://cocodataset.org/#home) train2017. These same 128 images are used for both training and validation to verify our training pipeline is capable of overfitting. [data/coco128.yaml](https://github.com/ultralytics/yolov5/blob/master/data/coco128.yaml), shown below, is the dataset config file that defines 1) the dataset root directory `path` and relative paths to `train` / `val` / `test` image directories (or *.txt files with image paths) and 2) a class `names` dictionary:
@ -105,7 +97,7 @@ names:
79: toothbrush
```
### 1.2 Create Labels
### 2.2 Create Labels
After using an annotation tool to label your images, export your labels to **YOLO format**, with one `*.txt` file per image (if no objects in image, no `*.txt` file is required). The `*.txt` file specifications are:
@ -120,7 +112,7 @@ The label file corresponding to the above image contains 2 persons (class `0`) a
Organize your train and val images and labels according to the example below. YOLOv5 assumes `/coco128` is inside a `/datasets` directory **next to** the `/yolov5` directory. **YOLOv5 locates labels automatically for each image** by replacing the last instance of `/images/` in each image path with `/labels/`. For example:
@ -130,15 +122,14 @@ Organize your train and val images and labels according to the example below. YO
Select a pretrained model to start training from. Here we select [YOLOv5s](https://github.com/ultralytics/yolov5/blob/master/models/yolov5s.yaml), the second-smallest and fastest model available. See our README [table](https://github.com/ultralytics/yolov5#pretrained-checkpoints) for a full comparison of all models.
Train a YOLOv5s model on COCO128 by specifying dataset, batch-size, image size and either pretrained `--weights yolov5s.pt` (recommended), or randomly initialized `--weights '' --cfg yolov5s.yaml` (not recommended). Pretrained weights are auto-downloaded from the [latest YOLOv5 release](https://github.com/ultralytics/yolov5/releases).
All training results are saved to `runs/train/` with incrementing run directories, i.e. `runs/train/exp2`, `runs/train/exp3` etc. For more details see the Training section of our tutorial notebook. <ahref="https://colab.research.google.com/github/ultralytics/yolov5/blob/master/tutorial.ipynb"><imgsrc="https://colab.research.google.com/assets/colab-badge.svg"alt="Open In Colab"></a><ahref="https://www.kaggle.com/ultralytics/yolov5"><imgsrc="https://kaggle.com/static/images/open-in-kaggle.svg"alt="Open In Kaggle"></a>
### 4. Visualize
## 5. Visualize
#### Comet Logging and Visualization 🌟 NEW
### Comet Logging and Visualization 🌟 NEW
[Comet](https://bit.ly/yolov5-readme-comet) is now fully integrated with YOLOv5. Track and visualize model metrics in real time, save your hyperparameters, datasets, and model checkpoints, and visualize your model predictions with [Comet Custom Panels](https://bit.ly/yolov5-colab-comet-panels)! Comet makes sure you never lose track of your work and makes it easy to share results and collaborate across teams of all sizes!
@ -174,21 +165,21 @@ To learn more about all the supported Comet features for this integration, check
[ClearML](https://cutt.ly/yolov5-notebook-clearml) is completely integrated into YOLOv5 to track your experimentation, manage dataset versions and even remotely execute training runs. To enable ClearML:
[ClearML](https://clear.ml/) is completely integrated into YOLOv5 to track your experimentation, manage dataset versions and even remotely execute training runs. To enable ClearML:
- `pip install clearml`
- run `clearml-init` to connect to a ClearML server (**deploy your own open-source server [here](https://github.com/allegroai/clearml-server)**, or use our free hosted server [here](https://cutt.ly/yolov5-notebook-clearml))
- run `clearml-init` to connect to a ClearML server
You'll get all the great expected features from an experiment manager: live updates, model upload, experiment comparison etc. but ClearML also tracks uncommitted changes and installed packages for example. Thanks to that ClearML Tasks (which is what we call experiments) are also reproducible on different machines! With only 1 extra line, we can schedule a YOLOv5 training task on a queue to be executed by any number of ClearML Agents (workers).
You can use ClearML Data to version your dataset and then pass it to YOLOv5 simply using its unique ID. This will help you keep track of your data without adding extra hassle. Explore the [ClearML Tutorial](https://docs.ultralytics.com/yolov5/tutorials/clearml_logging_integration) for details!
Training results are automatically logged with [Tensorboard](https://www.tensorflow.org/tensorboard) and [CSV](https://github.com/ultralytics/yolov5/pull/4148) loggers to `runs/train`, with a new experiment directory created for each new training as `runs/train/exp2`, `runs/train/exp3`, etc.
Glenn Jocher
11 months ago
committed by
GitHub