Docs updates: Add Explorer to tab, YOLOv5 in Guides and Usage in Quickstart (#7438)

Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com> Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com> Co-authored-by: Haixuan Xavier Tao <tao.xavier@outlook.com>
10 months ago · a92adf8231
parent 53150a925b
commit a92adf8231
30 changed files with 227 additions and 105 deletions
--- a/docs/en/datasets/explorer/dashboard.md
+++ b/docs/en/datasets/explorer/dashboard.md
@ -6,7 +6,7 @@ keywords: Ultralytics, Explorer GUI, semantic search, vector similarity search,

 # Explorer GUI

-Explorer GUI is like a playground build using (Ultralytics Explorer API)[api.md]. It allows you to run semantic/vector similarity search, SQL queries and even search using natural language using our ask AI feature powered by LLMs.
+Explorer GUI is like a playground build using [Ultralytics Explorer API](api.md). It allows you to run semantic/vector similarity search, SQL queries and even search using natural language using our ask AI feature powered by LLMs.

 ### Installation

--- a/docs/en/datasets/explorer/index.md
+++ b/docs/en/datasets/explorer/index.md
@ -6,7 +6,13 @@ keywords: Ultralytics Explorer, CV Dataset Tools, Semantic Search, SQL Dataset Q

 # Ultralytics Explorer

-Ultralytics Explorer is a tool for exploring CV datasets using semantic search, SQL queries and vector similarity search. It is also a Python API for accessing the same functionality.
+<p>
+<img width="1709" alt="Screenshot 2024-01-08 at 7 19 48 PM (1)" src="https://github.com/AyushExel/assets/assets/15766192/e536b0eb-6bce-43fe-b800-3e79510d2e5b">
+</p>
+
+Ultralytics Explorer is a tool for exploring CV datasets using semantic search, SQL queries, vector similarity search and even using natural language. It is also a Python API for accessing the same functionality.
+
+

 ### Installation of optional dependencies

@ -33,8 +39,3 @@ yolo explorer
 !!! note "Note"
    Ask AI feature works using OpenAI, so you'll be prompted to set the api key for OpenAI when you first run the GUI.
    You can set it like this - `yolo settings openai_api_key="..."`
-
-Example
-<p>
-<img width="1709" alt="Screenshot 2024-01-08 at 7 19 48 PM (1)" src="https://github.com/AyushExel/assets/assets/15766192/e536b0eb-6bce-43fe-b800-3e79510d2e5b">
-</p>
--- a/docs/en/datasets/index.md
+++ b/docs/en/datasets/index.md
@ -10,7 +10,12 @@ Ultralytics provides support for various datasets to facilitate computer vision

 ## 🌟 New: Ultralytics Explorer 🌟

-Create embeddings for your dataset, search for similar images, run SQL queries and perform semantic search. You can get started with our GUI app or build your own using the API. Learn more [here](explorer/index.md).
+Create embeddings for your dataset, search for similar images, run SQL queries, perform semantic search and even search using natural language! You can get started with our GUI app or build your own using the API. Learn more [here](explorer/index.md).
+
+<p>
+<img width="1709" alt="Screenshot 2024-01-08 at 7 19 48 PM (1)" src="https://github.com/AyushExel/assets/assets/15766192/e536b0eb-6bce-43fe-b800-3e79510d2e5b">
+</p>
+

 - Try the [GUI Demo](explorer/index.md)
 - Learn more about the [Explorer API](explorer/index.md)
--- a/docs/en/guides/object-blurring.md
+++ b/docs/en/guides/object-blurring.md
@ -23,47 +23,47 @@ Object blurring with [Ultralytics YOLOv8](https://github.com/ultralytics/ultraly
        from ultralytics import YOLO
        from ultralytics.utils.plotting import Annotator, colors
        import cv2
-        
+
        model = YOLO("yolov8n.pt")
        names = model.names
-        
+
        cap = cv2.VideoCapture("path/to/video/file.mp4")
        assert cap.isOpened(), "Error reading video file"
        w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS))
-        
+
        # Blur ratio
        blur_ratio = 50
-        
+
        # Video writer
        video_writer = cv2.VideoWriter("object_blurring_output.avi",
                                       cv2.VideoWriter_fourcc(*'mp4v'),
                                       fps, (w, h))
-        
+
        while cap.isOpened():
            success, im0 = cap.read()
            if not success:
                print("Video frame is empty or video processing has been successfully completed.")
                break
-        
+
            results = model.predict(im0, show=False)
            boxes = results[0].boxes.xyxy.cpu().tolist()
            clss = results[0].boxes.cls.cpu().tolist()
            annotator = Annotator(im0, line_width=2, example=names)
-        
+
            if boxes is not None:
                for box, cls in zip(boxes, clss):
                    annotator.box_label(box, color=colors(int(cls), True), label=names[int(cls)])
-        
+
                    obj = im0[int(box[1]):int(box[3]), int(box[0]):int(box[2])]
                    blur_obj = cv2.blur(obj, (blur_ratio, blur_ratio))
-        
+
                    im0[int(box[1]):int(box[3]), int(box[0]):int(box[2])] = blur_obj
-        
+
            cv2.imshow("ultralytics", im0)
            video_writer.write(im0)
            if cv2.waitKey(1) & 0xFF == ord('q'):
                break
-        
+
        cap.release()
        video_writer.release()
        cv2.destroyAllWindows()
--- a/docs/en/guides/object-cropping.md
+++ b/docs/en/guides/object-cropping.md
@ -24,50 +24,50 @@ Object cropping with [Ultralytics YOLOv8](https://github.com/ultralytics/ultraly
        from ultralytics.utils.plotting import Annotator, colors
        import cv2
        import os
-        
+
        model = YOLO("yolov8n.pt")
        names = model.names
-        
+
        cap = cv2.VideoCapture("path/to/video/file.mp4")
        assert cap.isOpened(), "Error reading video file"
        w, h, fps = (int(cap.get(x)) for x in (cv2.CAP_PROP_FRAME_WIDTH, cv2.CAP_PROP_FRAME_HEIGHT, cv2.CAP_PROP_FPS))
-        
+
        crop_dir_name = "ultralytics_crop"
        if not os.path.exists(crop_dir_name):
            os.mkdir(crop_dir_name)
-        
+
        # Video writer
        video_writer = cv2.VideoWriter("object_cropping_output.avi",
                                       cv2.VideoWriter_fourcc(*'mp4v'),
                                       fps, (w, h))
-        
+
        idx = 0
        while cap.isOpened():
            success, im0 = cap.read()
            if not success:
                print("Video frame is empty or video processing has been successfully completed.")
                break
-        
+
            results = model.predict(im0, show=False)
            boxes = results[0].boxes.xyxy.cpu().tolist()
            clss = results[0].boxes.cls.cpu().tolist()
            annotator = Annotator(im0, line_width=2, example=names)
-        
+
            if boxes is not None:
                for box, cls in zip(boxes, clss):
                    idx += 1
                    annotator.box_label(box, color=colors(int(cls), True), label=names[int(cls)])
-        
+
                    crop_obj = im0[int(box[1]):int(box[3]), int(box[0]):int(box[2])]
-        
+
                    cv2.imwrite(os.path.join(crop_dir_name, str(idx)+".png"), crop_obj)
-        
+
            cv2.imshow("ultralytics", im0)
            video_writer.write(im0)
-        
+
            if cv2.waitKey(1) & 0xFF == ord('q'):
                break
-        
+
        cap.release()
        video_writer.release()
        cv2.destroyAllWindows()
--- a/docs/en/index.md
+++ b/docs/en/index.md
@ -39,17 +39,13 @@ Introducing [Ultralytics](https://ultralytics.com) [YOLOv8](https://github.com/u

 Explore the YOLOv8 Docs, a comprehensive resource designed to help you understand and utilize its features and capabilities. Whether you are a seasoned machine learning practitioner or new to the field, this hub aims to maximize YOLOv8's potential in your projects

-# 🌟 New: Ultralytics Explorer 🌟
-
-Create embeddings for your dataset, search for similar images, run SQL queries and perform semantic search. You can get started with our GUI app or build your own using the API. Learn more [here](datasets/explorer/index.md).
-
 ## Where to Start

 - **Install** `ultralytics` with pip and get up and running in minutes &nbsp; [:material-clock-fast: Get Started](quickstart.md){ .md-button }
 - **Predict** new images and videos with YOLOv8 &nbsp; [:octicons-image-16: Predict on Images](modes/predict.md){ .md-button }
 - **Train** a new YOLOv8 model on your own custom dataset &nbsp; [:fontawesome-solid-brain: Train a Model](modes/train.md){ .md-button }
 - **Tasks** YOLOv8 tasks like segment, classify, pose and track &nbsp; [:material-magnify-expand: Explore Tasks](tasks/index.md){ .md-button }
- **Explore** datasets with advanced semantic and SQL search &nbsp; [:material-magnify-expand: Run Explorer](datasets/explorer/index.md){ .md-button }
+- **NEW 🚀 Explore** datasets with advanced semantic and SQL search &nbsp; [:material-magnify-expand: Explore a Dataset](datasets/explorer/index.md){ .md-button }

 <p align="center">
  <br>
--- a/docs/en/reference/cfg/init.md
+++ b/docs/en/reference/cfg/init.md
@ -43,6 +43,10 @@ keywords: Ultralytics, YOLO, Configuration, cfg2dict, handle_deprecation, merge_

 <br><br>

+## ::: ultralytics.cfg.handle_explorer
+
+<br><br>
+
 ## ::: ultralytics.cfg.parse_key_value_pair

 <br><br>
--- a/docs/en/reference/solutions/distance_calculation.md
+++ b/docs/en/reference/solutions/distance_calculation.md
@ -7,7 +7,7 @@ keywords: Ultralytics, YOLO, distance calculation, object tracking, data visuali

 !!! Note

-    This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/solutions/distance_calculation.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/solutions/distance_calculation.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/solutions/heatmap.py) 🛠️. Thank you 🙏!
+    This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/solutions/distance_calculation.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/solutions/distance_calculation.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/solutions/distance_calculation.py) 🛠️. Thank you 🙏!

 <br><br>

--- a/docs/en/reference/solutions/speed_estimation.md
+++ b/docs/en/reference/solutions/speed_estimation.md
@ -7,7 +7,7 @@ keywords: Ultralytics YOLO, speed estimation software, real-time vehicle trackin

 !!! Note

-    This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/solutions/speed_estimation.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/solutions/speed_estimation.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/solutions/object_counter.py) 🛠️. Thank you 🙏!
+    This file is available at [https://github.com/ultralytics/ultralytics/blob/main/ultralytics/solutions/speed_estimation.py](https://github.com/ultralytics/ultralytics/blob/main/ultralytics/solutions/speed_estimation.py). If you spot a problem please help fix it by [contributing](https://docs.ultralytics.com/help/contributing/) a [Pull Request](https://github.com/ultralytics/ultralytics/edit/main/ultralytics/solutions/speed_estimation.py) 🛠️. Thank you 🙏!

 <br><br>

--- a/docs/en/usage/python.md
+++ b/docs/en/usage/python.md
@ -240,6 +240,53 @@ Benchmark mode is used to profile the speed and accuracy of various export forma

 [Benchmark Examples](../modes/benchmark.md){ .md-button }

+## Explorer
+
+Explorer API can be used to explore datasets with advanced semantic, vector-similarity and SQL search among other features. It also searching for images based on their content using natural language by utilizing the power of LLMs. The Explorer API allows you to write your own dataset exploration notebooks or scripts to get insights into your datasets.
+
+!!! Example "Semantic Search Using Explorer"
+
+    === "Using Images"
+
+        ```python
+        from ultralytics import Explorer
+
+        # create an Explorer object
+        exp = Explorer(data='coco128.yaml', model='yolov8n.pt')
+        exp.create_embeddings_table()
+
+        similar = exp.get_similar(img='https://ultralytics.com/images/bus.jpg', limit=10)
+        print(similar.head())
+
+        # Search using multiple indices
+        similar = exp.get_similar(
+                                img=['https://ultralytics.com/images/bus.jpg',
+                                     'https://ultralytics.com/images/bus.jpg'],
+                                limit=10
+                                )
+        print(similar.head())
+        ```
+
+    === "Using Dataset Indices"
+
+        ```python
+        from ultralytics import Explorer
+
+        # create an Explorer object
+        exp = Explorer(data='coco128.yaml', model='yolov8n.pt')
+        exp.create_embeddings_table()
+
+        similar = exp.get_similar(idx=1, limit=10)
+        print(similar.head())
+
+        # Search using multiple indices
+        similar = exp.get_similar(idx=[1,10], limit=10)
+        print(similar.head())
+        ```
+
+[Explorer](../datasets/explorer/index.md){ .md-button }
+
+
 ## Using Trainers

 `YOLO` model class is a high-level wrapper on the Trainer classes. Each YOLO task has its own trainer that inherits from `BaseTrainer`.
--- a/docs/mkdocs.yml
+++ b/docs/mkdocs.yml
@ -170,12 +170,14 @@ nav:
          - Classify: tasks/classify.md
          - Pose: tasks/pose.md
          - OBB: tasks/obb.md
-      - Guides:
-          - guides/index.md
      - Models:
          - models/index.md
      - Datasets:
          - datasets/index.md
+      - Guides:
+          - guides/index.md
+      - NEW 🚀 Explorer:
+          - datasets/explorer/index.md
      - Languages:
          - 🇬🇧&nbsp English: https://docs.ultralytics.com/
          - 🇨🇳&nbsp 简体中文: https://docs.ultralytics.com/zh/
@ -188,7 +190,14 @@ nav:
          - 🇵🇹&nbsp Português: https://docs.ultralytics.com/pt/
          - 🇮🇳&nbsp हिन्दी: https://docs.ultralytics.com/hi/
          - 🇸🇦&nbsp العربية: https://docs.ultralytics.com/ar/
-  - Quickstart: quickstart.md
+  - Quickstart:
+      - quickstart.md
+      - Usage:
+          - CLI: usage/cli.md
+          - Python: usage/python.md
+          - Callbacks: usage/callbacks.md
+          - Configuration: usage/cfg.md
+          - Advanced Customization: usage/engine.md
  - Modes:
      - modes/index.md
      - Train: modes/train.md
@ -219,7 +228,7 @@ nav:
      - RT-DETR (Realtime Detection Transformer): models/rtdetr.md
  - Datasets:
      - datasets/index.md
-      - Explorer:
+      - NEW 🚀 Explorer:
          - datasets/explorer/index.md
          - Explorer API: datasets/explorer/api.md
          - Explorer Dashboard: datasets/explorer/dashboard.md
@ -263,6 +272,11 @@ nav:
          - DOTA8: datasets/obb/dota8.md
      - Multi-Object Tracking:
          - datasets/track/index.md
+  - NEW 🚀 Explorer:
+      - datasets/explorer/index.md
+      - Explorer API: datasets/explorer/api.md
+      - Explorer Dashboard Demo: datasets/explorer/dashboard.md
+      - VOC Exploration Example: datasets/explorer/explorer.ipynb
  - Guides:
      - guides/index.md
      - YOLO Common Issues: guides/yolo-common-issues.md
@ -290,6 +304,31 @@ nav:
          - VisionEye Mapping: guides/vision-eye.md
          - Speed Estimation: guides/speed-estimation.md
          - Distance Calculation: guides/distance-calculation.md
+      - YOLOv5:
+          - yolov5/index.md
+          - Quickstart: yolov5/quickstart_tutorial.md
+          - Environments:
+              - Amazon Web Services (AWS): yolov5/environments/aws_quickstart_tutorial.md
+              - Google Cloud (GCP): yolov5/environments/google_cloud_quickstart_tutorial.md
+              - AzureML: yolov5/environments/azureml_quickstart_tutorial.md
+              - Docker Image: yolov5/environments/docker_image_quickstart_tutorial.md
+          - Tutorials:
+              - Train Custom Data: yolov5/tutorials/train_custom_data.md
+              - Tips for Best Training Results: yolov5/tutorials/tips_for_best_training_results.md
+              - Multi-GPU Training: yolov5/tutorials/multi_gpu_training.md
+              - PyTorch Hub: yolov5/tutorials/pytorch_hub_model_loading.md
+              - TFLite, ONNX, CoreML, TensorRT Export: yolov5/tutorials/model_export.md
+              - NVIDIA Jetson Nano Deployment: yolov5/tutorials/running_on_jetson_nano.md
+              - Test-Time Augmentation (TTA): yolov5/tutorials/test_time_augmentation.md
+              - Model Ensembling: yolov5/tutorials/model_ensembling.md
+              - Pruning/Sparsity Tutorial: yolov5/tutorials/model_pruning_and_sparsity.md
+              - Hyperparameter evolution: yolov5/tutorials/hyperparameter_evolution.md
+              - Transfer learning with frozen layers: yolov5/tutorials/transfer_learning_with_frozen_layers.md
+              - Architecture Summary: yolov5/tutorials/architecture_description.md
+              - Roboflow Datasets: yolov5/tutorials/roboflow_datasets_integration.md
+              - Neural Magic's DeepSparse: yolov5/tutorials/neural_magic_pruning_quantization.md
+              - Comet Logging: yolov5/tutorials/comet_logging_integration.md
+              - Clearml Logging: yolov5/tutorials/clearml_logging_integration.md
  - Integrations:
      - integrations/index.md
      - Comet ML: integrations/comet.md
@ -303,37 +342,6 @@ nav:
      - Neural Magic: integrations/neural-magic.md
      - TensorBoard: integrations/tensorboard.md
      - Amazon SageMaker: integrations/amazon-sagemaker.md
-  - Usage:
-      - CLI: usage/cli.md
-      - Python: usage/python.md
-      - Callbacks: usage/callbacks.md
-      - Configuration: usage/cfg.md
-      - Advanced Customization: usage/engine.md
-  - YOLOv5:
-      - yolov5/index.md
-      - Quickstart: yolov5/quickstart_tutorial.md
-      - Environments:
-          - Amazon Web Services (AWS): yolov5/environments/aws_quickstart_tutorial.md
-          - Google Cloud (GCP): yolov5/environments/google_cloud_quickstart_tutorial.md
-          - AzureML: yolov5/environments/azureml_quickstart_tutorial.md
-          - Docker Image: yolov5/environments/docker_image_quickstart_tutorial.md
-      - Tutorials:
-          - Train Custom Data: yolov5/tutorials/train_custom_data.md
-          - Tips for Best Training Results: yolov5/tutorials/tips_for_best_training_results.md
-          - Multi-GPU Training: yolov5/tutorials/multi_gpu_training.md
-          - PyTorch Hub: yolov5/tutorials/pytorch_hub_model_loading.md
-          - TFLite, ONNX, CoreML, TensorRT Export: yolov5/tutorials/model_export.md
-          - NVIDIA Jetson Nano Deployment: yolov5/tutorials/running_on_jetson_nano.md
-          - Test-Time Augmentation (TTA): yolov5/tutorials/test_time_augmentation.md
-          - Model Ensembling: yolov5/tutorials/model_ensembling.md
-          - Pruning/Sparsity Tutorial: yolov5/tutorials/model_pruning_and_sparsity.md
-          - Hyperparameter evolution: yolov5/tutorials/hyperparameter_evolution.md
-          - Transfer learning with frozen layers: yolov5/tutorials/transfer_learning_with_frozen_layers.md
-          - Architecture Summary: yolov5/tutorials/architecture_description.md
-          - Roboflow Datasets: yolov5/tutorials/roboflow_datasets_integration.md
-          - Neural Magic's DeepSparse: yolov5/tutorials/neural_magic_pruning_quantization.md
-          - Comet Logging: yolov5/tutorials/comet_logging_integration.md
-          - Clearml Logging: yolov5/tutorials/clearml_logging_integration.md
  - HUB:
      - hub/index.md
      - Quickstart: hub/quickstart.md
@ -357,6 +365,11 @@ nav:
          - build: reference/data/build.md
          - converter: reference/data/converter.md
          - dataset: reference/data/dataset.md
+          - explorer:
+              - explorer: reference/data/explorer/explorer.md
+              - gui:
+                  - dash: reference/data/explorer/gui/dash.md
+              - utils: reference/data/explorer/utils.md
          - loaders: reference/data/loaders.md
          - split_dota: reference/data/split_dota.md
          - utils: reference/data/utils.md
@ -436,10 +449,10 @@ nav:
          - tasks: reference/nn/tasks.md
      - solutions:
          - ai_gym: reference/solutions/ai_gym.md
+          - distance_calculation: reference/solutions/distance_calculation.md
          - heatmap: reference/solutions/heatmap.md
          - object_counter: reference/solutions/object_counter.md
          - speed_estimation: reference/solutions/speed_estimation.md
-          - distance_calculation: reference/solutions/distance_calculation.md
      - trackers:
          - basetrack: reference/trackers/basetrack.md
          - bot_sort: reference/trackers/bot_sort.md
--- a/tests/test_explorer.py
+++ b/tests/test_explorer.py
@ -1,8 +1,11 @@
+import PIL
+
 from ultralytics import Explorer
 from ultralytics.utils import ASSETS


 def test_similarity():
+    """Test similarity calculations and SQL queries for correctness and response length."""
    exp = Explorer()
    exp.create_embeddings_table()
    similar = exp.get_similar(idx=1)
@ -18,6 +21,7 @@ def test_similarity():


 def test_det():
+    """Test detection functionalities and ensure the embedding table has bounding boxes."""
    exp = Explorer(data='coco8.yaml', model='yolov8n.pt')
    exp.create_embeddings_table(force=True)
    assert len(exp.table.head()['bboxes']) > 0
@ -25,27 +29,26 @@ def test_det():
    assert len(similar) > 0
    # This is a loose test, just checks errors not correctness
    similar = exp.plot_similar(idx=[1, 2], limit=10)
-    assert similar is not None
-    similar.show()
+    assert isinstance(similar, PIL.Image.Image)


 def test_seg():
+    """Test segmentation functionalities and verify the embedding table includes masks."""
    exp = Explorer(data='coco8-seg.yaml', model='yolov8n-seg.pt')
    exp.create_embeddings_table(force=True)
    assert len(exp.table.head()['masks']) > 0
    similar = exp.get_similar(idx=[1, 2], limit=10)
    assert len(similar) > 0
    similar = exp.plot_similar(idx=[1, 2], limit=10)
-    assert similar is not None
-    similar.show()
+    assert isinstance(similar, PIL.Image.Image)


 def test_pose():
+    """Test pose estimation functionalities and check the embedding table for keypoints."""
    exp = Explorer(data='coco8-pose.yaml', model='yolov8n-pose.pt')
    exp.create_embeddings_table(force=True)
    assert len(exp.table.head()['keypoints']) > 0
    similar = exp.get_similar(idx=[1, 2], limit=10)
    assert len(similar) > 0
    similar = exp.plot_similar(idx=[1, 2], limit=10)
-    assert similar is not None
-    similar.show()
+    assert isinstance(similar, PIL.Image.Image)
--- a/ultralytics/data/explorer/init.py
+++ b/ultralytics/data/explorer/init.py
@ -1,3 +1,5 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
+
 from .utils import plot_query_result

 __all__ = ['plot_query_result']
--- a/ultralytics/data/explorer/explorer.py
+++ b/ultralytics/data/explorer/explorer.py
@ -1,3 +1,5 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
+
 from io import BytesIO
 from pathlib import Path
 from typing import Any, List, Tuple, Union
@ -24,9 +26,8 @@ class ExplorerDataset(YOLODataset):
    def __init__(self, *args, data: dict = None, **kwargs) -> None:
        super().__init__(*args, data=data, **kwargs)

-    # NOTE: Load the image directly without any resize operations.
    def load_image(self, i: int) -> Union[Tuple[np.ndarray, Tuple[int, int], Tuple[int, int]], Tuple[None, None, None]]:
-        """Loads 1 image from dataset index 'i', returns (im, resized hw)."""
+        """Loads 1 image from dataset index 'i' without any resize ops."""
        im, f, fn = self.ims[i], self.im_files[i], self.npy_files[i]
        if im is None:  # not cached in RAM
            if fn.exists():  # load npy
@ -41,6 +42,7 @@ class ExplorerDataset(YOLODataset):
        return self.ims[i], self.im_hw0[i], self.im_hw[i]

    def build_transforms(self, hyp: IterableSimpleNamespace = None):
+        """Creates transforms for dataset images without resizing."""
        return Format(
            bbox_format='xyxy',
            normalize=False,
@ -122,7 +124,7 @@ class Explorer:
        self.table = table

    def _yield_batches(self, dataset: ExplorerDataset, data_info: dict, model: YOLO, exclude_keys: List[str]):
-        # Implement Batching
+        """Generates batches of data for embedding, excluding specified keys."""
        for i in tqdm(range(len(dataset))):
            self.progress = float(i + 1) / len(dataset)
            batch = dataset[i]
@ -143,7 +145,7 @@ class Explorer:
            limit (int): Number of results to return.

        Returns:
-            An arrow table containing the results. Supports converting to:
+            (pyarrow.Table): An arrow table containing the results. Supports converting to:
                - pandas dataframe: `result.to_pandas()`
                - dict of lists: `result.to_pydict()`

@ -175,7 +177,7 @@ class Explorer:
            return_type (str): Type of the result to return. Can be either 'pandas' or 'arrow'. Defaults to 'pandas'.

        Returns:
-            An arrow table containing the results.
+            (pyarrow.Table): An arrow table containing the results.

        Example:
            ```python
@ -216,7 +218,7 @@ class Explorer:
            labels (bool): Whether to plot the labels or not.

        Returns:
-            PIL Image containing the plot.
+            (PIL.Image): Image containing the plot.

        Example:
            ```python
@ -248,7 +250,7 @@ class Explorer:
            return_type (str): Type of the result to return. Can be either 'pandas' or 'arrow'. Defaults to 'pandas'.

        Returns:
-            A table or pandas dataframe containing the results.
+            (pandas.DataFrame): A dataframe containing the results.

        Example:
            ```python
@ -282,7 +284,7 @@ class Explorer:
            limit (int): Number of results to return. Defaults to 25.

        Returns:
-            PIL Image containing the plot.
+            (PIL.Image): Image containing the plot.

        Example:
            ```python
@ -306,11 +308,12 @@ class Explorer:
        Args:
            max_dist (float): maximum L2 distance between the embeddings to consider. Defaults to 0.2.
            top_k (float): Percentage of the closest data points to consider when counting. Used to apply limit when running
-                            vector search. Defaults: None.
+                           vector search. Defaults: None.
            force (bool): Whether to overwrite the existing similarity index or not. Defaults to True.

        Returns:
-            A pandas dataframe containing the similarity index.
+            (pandas.DataFrame): A dataframe containing the similarity index. Each row corresponds to an image, and columns
+                                include indices of similar images and their respective distances.

        Example:
            ```python
@ -340,6 +343,7 @@ class Explorer:
        sim_table = self.connection.create_table(sim_idx_table_name, schema=get_sim_index_schema(), mode='overwrite')

        def _yield_sim_idx():
+            """Generates a dataframe with similarity indices and distances for images."""
            for i in tqdm(range(len(embeddings))):
                sim_idx = self.table.search(embeddings[i]).limit(top_k).to_pandas().query(f'_distance <= {max_dist}')
                yield [{
@ -364,7 +368,7 @@ class Explorer:
            force (bool): Whether to overwrite the existing similarity index or not. Defaults to True.

        Returns:
-            PIL.PngImagePlugin.PngImageFile containing the plot.
+            (PIL.Image): Image containing the plot.

        Example:
            ```python
@ -416,7 +420,7 @@ class Explorer:
            query (str): Question to ask.

        Returns:
-            Answer from AI.
+            (pandas.DataFrame): A dataframe containing filtered results to the SQL query.

        Example:
            ```python
@ -436,14 +440,17 @@ class Explorer:

    def visualize(self, result):
        """
-        Visualize the results of a query.
+        Visualize the results of a query. TODO.

        Args:
-            result (arrow table): Arrow table containing the results of a query.
+            result (pyarrow.Table): Table containing the results of a query.
        """
-        # TODO:
        pass

    def generate_report(self, result):
-        """Generate a report of the dataset."""
+        """
+        Generate a report of the dataset.
+
+        TODO
+        """
        pass
--- a/ultralytics/data/explorer/gui/init.py
+++ b/ultralytics/data/explorer/gui/init.py
@ -0,0 +1 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
--- a/ultralytics/data/explorer/gui/dash.py
+++ b/ultralytics/data/explorer/gui/dash.py
@ -1,3 +1,5 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
+
 import time
 from threading import Thread

@ -7,13 +9,13 @@ from ultralytics import Explorer
 from ultralytics.utils import ROOT, SETTINGS
 from ultralytics.utils.checks import check_requirements

-check_requirements('streamlit>=1.29.0')
-check_requirements('streamlit-select>=0.2')
+check_requirements(('streamlit>=1.29.0', 'streamlit-select>=0.2'))
 import streamlit as st
 from streamlit_select import image_select


 def _get_explorer():
+    """Initializes and returns an instance of the Explorer class."""
    exp = Explorer(data=st.session_state.get('dataset'), model=st.session_state.get('model'))
    thread = Thread(target=exp.create_embeddings_table,
                    kwargs={'force': st.session_state.get('force_recreate_embeddings')})
@ -28,6 +30,7 @@ def _get_explorer():


 def init_explorer_form():
+    """Initializes an Explorer instance and creates embeddings table with progress tracking."""
    datasets = ROOT / 'cfg' / 'datasets'
    ds = [d.name for d in datasets.glob('*.yaml')]
    models = [
@ -46,6 +49,7 @@ def init_explorer_form():


 def query_form():
+    """Sets up a form in Streamlit to initialize Explorer with dataset and model selection."""
    with st.form('query_form'):
        col1, col2 = st.columns([0.8, 0.2])
        with col1:
@ -58,6 +62,7 @@ def query_form():


 def ai_query_form():
+    """Sets up a Streamlit form for user input to initialize Explorer with dataset and model selection."""
    with st.form('ai_query_form'):
        col1, col2 = st.columns([0.8, 0.2])
        with col1:
@ -67,6 +72,7 @@ def ai_query_form():


 def find_similar_imgs(imgs):
+    """Initializes a Streamlit form for AI-based image querying with custom input."""
    exp = st.session_state['explorer']
    similar = exp.get_similar(img=imgs, limit=st.session_state.get('limit'), return_type='arrow')
    paths = similar.to_pydict()['im_file']
@ -74,6 +80,7 @@ def find_similar_imgs(imgs):


 def similarity_form(selected_imgs):
+    """Initializes a form for AI-based image querying with custom input in Streamlit."""
    st.write('Similarity Search')
    with st.form('similarity_form'):
        subcol1, subcol2 = st.columns([1, 1])
@ -109,6 +116,7 @@ def similarity_form(selected_imgs):


 def run_sql_query():
+    """Executes an SQL query and returns the results."""
    st.session_state['error'] = None
    query = st.session_state.get('query')
    if query.rstrip().lstrip():
@ -118,6 +126,7 @@ def run_sql_query():


 def run_ai_query():
+    """Execute SQL query and update session state with query results."""
    if not SETTINGS['openai_api_key']:
        st.session_state[
            'error'] = 'OpenAI API key not found in settings. Please run yolo settings openai_api_key="..."'
@ -134,12 +143,14 @@ def run_ai_query():


 def reset_explorer():
+    """Resets the explorer to its initial state by clearing session variables."""
    st.session_state['explorer'] = None
    st.session_state['imgs'] = None
    st.session_state['error'] = None


 def utralytics_explorer_docs_callback():
+    """Resets the explorer to its initial state by clearing session variables."""
    with st.container(border=True):
        st.image('https://raw.githubusercontent.com/ultralytics/assets/main/logo/Ultralytics_Logotype_Original.svg',
                 width=100)
@ -151,6 +162,7 @@ def utralytics_explorer_docs_callback():


 def layout():
+    """Resets explorer session variables and provides documentation with a link to API docs."""
    st.set_page_config(layout='wide', initial_sidebar_state='collapsed')
    st.markdown("<h1 style='text-align: center;'>Ultralytics Explorer Demo</h1>", unsafe_allow_html=True)

--- a/ultralytics/data/explorer/utils.py
+++ b/ultralytics/data/explorer/utils.py
@ -1,3 +1,5 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
+
 import getpass
 from typing import List

@ -14,6 +16,7 @@ from ultralytics.utils.plotting import plot_images


 def get_table_schema(vector_size):
+    """Extracts and returns the schema of a database table."""
    from lancedb.pydantic import LanceModel, Vector

    class Schema(LanceModel):
@ -29,6 +32,7 @@ def get_table_schema(vector_size):


 def get_sim_index_schema():
+    """Returns a LanceModel schema for a database table with specified vector size."""
    from lancedb.pydantic import LanceModel

    class Schema(LanceModel):
@ -41,6 +45,7 @@ def get_sim_index_schema():


 def sanitize_batch(batch, dataset_info):
+    """Sanitizes input batch for inference, ensuring correct format and dimensions."""
    batch['cls'] = batch['cls'].flatten().int().tolist()
    box_cls_pair = sorted(zip(batch['bboxes'].tolist(), batch['cls']), key=lambda x: x[1])
    batch['bboxes'] = [box for box, _ in box_cls_pair]
@ -111,6 +116,7 @@ def plot_query_result(similar_set, plot_labels=True):


 def prompt_sql_query(query):
+    """Plots images with optional labels from a similar data set."""
    check_requirements('openai>=1.6.1')
    from openai import OpenAI

--- a/ultralytics/data/split_dota.py
+++ b/ultralytics/data/split_dota.py
@ -1,3 +1,5 @@
+# Ultralytics YOLO 🚀, AGPL-3.0 license
+
 import itertools
 import os
 from glob import glob
@ -53,10 +55,13 @@ def bbox_iof(polygon1, bbox2, eps=1e-6):


 def load_yolo_dota(data_root, split='train'):
-    """Load DOTA dataset.
+    """
+    Load DOTA dataset.
+
    Args:
        data_root (str): Data root.
        split (str): The split data set, could be train or val.
+
    Notes:
        The directory structure assumed for the DOTA dataset:
            - data_root
@ -133,7 +138,7 @@ def get_window_obj(anno, windows, iof_thr=0.7):
        label[:, 1::2] *= w
        label[:, 2::2] *= h
        iofs = bbox_iof(label[:, 1:], windows)
-        # unnormalized and misaligned coordinates
+        # Unnormalized and misaligned coordinates
        window_anns = [(label[iofs[:, i] >= iof_thr]) for i in range(len(windows))]
    else:
        window_anns = [np.zeros((0, 9), dtype=np.float32) for _ in range(len(windows))]
@ -141,13 +146,16 @@ def get_window_obj(anno, windows, iof_thr=0.7):


 def crop_and_save(anno, windows, window_objs, im_dir, lb_dir):
-    """Crop images and save new labels.
+    """
+    Crop images and save new labels.
+
    Args:
        anno (dict): Annotation dict, including `filepath`, `label`, `ori_size` as its keys.
        windows (list): A list of windows coordinates.
        window_objs (list): A list of labels inside each window.
        im_dir (str): The output directory path of images.
        lb_dir (str): The output directory path of labels.
+
    Notes:
        The directory structure assumed for the DOTA dataset:
            - data_root
@ -185,7 +193,7 @@ def split_images_and_labels(data_root, save_dir, split='train', crop_sizes=[1024
    """
    Split both images and labels.

-    NOTES:
+    Notes:
        The directory structure assumed for the DOTA dataset:
            - data_root
                - images
@ -215,7 +223,7 @@ def split_trainval(data_root, save_dir, crop_size=1024, gap=200, rates=[1.0]):
    """
    Split train and val set of DOTA.

-    NOTES:
+    Notes:
        The directory structure assumed for the DOTA dataset:
            - data_root
                - images
@ -245,7 +253,7 @@ def split_test(data_root, save_dir, crop_size=1024, gap=200, rates=[1.0]):
    """
    Split test set of DOTA, labels are not included within this set.

-    NOTES:
+    Notes:
        The directory structure assumed for the DOTA dataset:
            - data_root
                - images
--- a/ultralytics/models/rtdetr/val.py
+++ b/ultralytics/models/rtdetr/val.py
@ -107,6 +107,7 @@ class RTDETRValidator(DetectionValidator):
        return outputs

    def _prepare_batch(self, si, batch):
+        """Prepares a batch for training or inference by applying transformations."""
        idx = batch['batch_idx'] == si
        cls = batch['cls'][idx].squeeze(-1)
        bbox = batch['bboxes'][idx]
@ -121,6 +122,7 @@ class RTDETRValidator(DetectionValidator):
        return prepared_batch

    def _prepare_pred(self, pred, pbatch):
+        """Prepares and returns a batch with transformed bounding boxes and class labels."""
        predn = pred.clone()
        predn[..., [0, 2]] *= pbatch['ori_shape'][1] / self.args.imgsz  # native-space pred
        predn[..., [1, 3]] *= pbatch['ori_shape'][0] / self.args.imgsz  # native-space pred
--- a/ultralytics/models/yolo/detect/val.py
+++ b/ultralytics/models/yolo/detect/val.py
@ -87,6 +87,7 @@ class DetectionValidator(BaseValidator):
                                       max_det=self.args.max_det)

    def _prepare_batch(self, si, batch):
+        """Prepares a batch of images and annotations for validation."""
        idx = batch['batch_idx'] == si
        cls = batch['cls'][idx].squeeze(-1)
        bbox = batch['bboxes'][idx]
@ -100,6 +101,7 @@ class DetectionValidator(BaseValidator):
        return prepared_batch

    def _prepare_pred(self, pred, pbatch):
+        """Prepares a batch of images and annotations for validation."""
        predn = pred.clone()
        ops.scale_boxes(pbatch['imgsz'], predn[:, :4], pbatch['ori_shape'],
                        ratio_pad=pbatch['ratio_pad'])  # native-space pred
--- a/ultralytics/models/yolo/obb/predict.py
+++ b/ultralytics/models/yolo/obb/predict.py
@ -23,6 +23,7 @@ class OBBPredictor(DetectionPredictor):
    """

    def __init__(self, cfg=DEFAULT_CFG, overrides=None, _callbacks=None):
+        """Initializes OBBPredictor with optional model and data configuration overrides."""
        super().__init__(cfg, overrides, _callbacks)
        self.args.task = 'obb'

--- a/ultralytics/models/yolo/obb/val.py
+++ b/ultralytics/models/yolo/obb/val.py
@ -65,6 +65,7 @@ class OBBValidator(DetectionValidator):
        return self.match_predictions(detections[:, 5], gt_cls, iou)

    def _prepare_batch(self, si, batch):
+        """Prepares and returns a batch for OBB validation."""
        idx = batch['batch_idx'] == si
        cls = batch['cls'][idx].squeeze(-1)
        bbox = batch['bboxes'][idx]
@ -78,6 +79,7 @@ class OBBValidator(DetectionValidator):
        return prepared_batch

    def _prepare_pred(self, pred, pbatch):
+        """Prepares and returns a batch for OBB validation with scaled and padded bounding boxes."""
        predn = pred.clone()
        ops.scale_boxes(pbatch['imgsz'], predn[:, :4], pbatch['ori_shape'], ratio_pad=pbatch['ratio_pad'],
                        xywh=True)  # native-space pred
--- a/ultralytics/models/yolo/pose/val.py
+++ b/ultralytics/models/yolo/pose/val.py
@ -69,6 +69,7 @@ class PoseValidator(DetectionValidator):
        self.stats = dict(tp_p=[], tp=[], conf=[], pred_cls=[], target_cls=[])

    def _prepare_batch(self, si, batch):
+        """Prepares a batch for processing by converting keypoints to float and moving to device."""
        pbatch = super()._prepare_batch(si, batch)
        kpts = batch['keypoints'][batch['batch_idx'] == si]
        h, w = pbatch['imgsz']
@ -80,6 +81,7 @@ class PoseValidator(DetectionValidator):
        return pbatch

    def _prepare_pred(self, pred, pbatch):
+        """Prepares and scales keypoints in a batch for pose processing."""
        predn = super()._prepare_pred(pred, pbatch)
        nk = pbatch['kpts'].shape[1]
        pred_kpts = predn[:, 6:].view(len(predn), nk, -1)
--- a/ultralytics/models/yolo/segment/val.py
+++ b/ultralytics/models/yolo/segment/val.py
@ -72,12 +72,14 @@ class SegmentationValidator(DetectionValidator):
        return p, proto

    def _prepare_batch(self, si, batch):
+        """Prepares a batch for training or inference by processing images and targets."""
        prepared_batch = super()._prepare_batch(si, batch)
        midx = [si] if self.args.overlap_mask else batch['batch_idx'] == si
        prepared_batch['masks'] = batch['masks'][midx]
        return prepared_batch

    def _prepare_pred(self, pred, pbatch, proto):
+        """Prepares a batch for training or inference by processing images and targets."""
        predn = super()._prepare_pred(pred, pbatch)
        pred_masks = self.process(proto, pred[:, 6:], pred[:, :4], shape=pbatch['imgsz'])
        return predn, pred_masks
--- a/ultralytics/nn/modules/head.py
+++ b/ultralytics/nn/modules/head.py
@ -116,6 +116,7 @@ class OBB(Detect):
    """YOLOv8 OBB detection head for detection with rotation models."""

    def __init__(self, nc=80, ne=1, ch=()):
+        """Initialize OBB with number of classes `nc` and layer channels `ch`."""
        super().__init__(nc, ch)
        self.ne = ne  # number of extra parameters
        self.detect = Detect.forward
@ -124,6 +125,7 @@ class OBB(Detect):
        self.cv4 = nn.ModuleList(nn.Sequential(Conv(x, c4, 3), Conv(c4, c4, 3), nn.Conv2d(c4, self.ne, 1)) for x in ch)

    def forward(self, x):
+        """Concatenates and returns predicted bounding boxes and class probabilities."""
        bs = x[0].shape[0]  # batch size
        angle = torch.cat([self.cv4[i](x[i]).view(bs, self.ne, -1) for i in range(self.nl)], 2)  # OBB theta logits
        # NOTE: set `angle` as an attribute so that `decode_bboxes` could use it.
--- a/ultralytics/nn/tasks.py
+++ b/ultralytics/nn/tasks.py
@ -306,6 +306,7 @@ class OBBModel(DetectionModel):
        super().__init__(cfg=cfg, ch=ch, nc=nc, verbose=verbose)

    def init_criterion(self):
+        """Initialize the loss criterion for the model."""
        return v8OBBLoss(self)


--- a/ultralytics/solutions/object_counter.py
+++ b/ultralytics/solutions/object_counter.py
@ -153,6 +153,7 @@ class ObjectCounter:
            self.selected_point = None

    def extract_and_process_tracks(self, tracks):
+        """Extracts and processes tracks for object counting in a video stream."""
        boxes = tracks[0].boxes.xyxy.cpu()
        clss = tracks[0].boxes.cls.cpu().tolist()
        track_ids = tracks[0].boxes.id.int().cpu().tolist()
--- a/ultralytics/trackers/basetrack.py
+++ b/ultralytics/trackers/basetrack.py
@ -55,6 +55,7 @@ class BaseTrack:
    _count = 0

    def __init__(self):
+        """Initializes a new track with unique ID and foundational tracking attributes."""
        self.track_id = 0
        self.is_activated = False
        self.state = TrackState.New
--- a/ultralytics/utils/init.py
+++ b/ultralytics/utils/init.py
@ -245,6 +245,7 @@ def set_logging(name=LOGGING_NAME, verbose=True):
            class CustomFormatter(logging.Formatter):

                def format(self, record):
+                    """Sets up logging with UTF-8 encoding and configurable verbosity."""
                    return emojis(super().format(record))

            formatter = CustomFormatter('%(message)s')  # Use CustomFormatter to eliminate UTF-8 output as last recourse
--- a/ultralytics/utils/downloads.py
+++ b/ultralytics/utils/downloads.py
@ -206,7 +206,7 @@ def check_disk_space(url='https://ultralytics.com/assets/coco128.zip', sf=1.5, h
    # Check file size
    gib = 1 << 30  # bytes per GiB
    data = int(r.headers.get('Content-Length', 0)) / gib  # file size (GB)
-    total, used, free = (x / gib for x in shutil.disk_usage('/'))  # bytes
+    total, used, free = (x / gib for x in shutil.disk_usage(Path.cwd()))  # bytes
    if data * sf < free:
        return True  # sufficient space