diff --git a/.github/workflows/format.yml b/.github/workflows/format.yml index ed1bd5e290..65254dcc63 100644 --- a/.github/workflows/format.yml +++ b/.github/workflows/format.yml @@ -54,7 +54,7 @@ jobs: ## Environments - YOLO may be run in any of the following up-to-date verified environments (with all dependencies including [CUDA](https://developer.nvidia.com/cuda-zone)/[CUDNN](https://developer.nvidia.com/cudnn), [Python](https://www.python.org/) and [PyTorch](https://pytorch.org/) preinstalled): + YOLO may be run in any of the following up-to-date verified environments (with all dependencies including [CUDA](https://developer.nvidia.com/cuda)/[CUDNN](https://developer.nvidia.com/cudnn), [Python](https://www.python.org/) and [PyTorch](https://pytorch.org/) preinstalled): - **Notebooks** with free GPU: Run on Gradient Open In Colab Open In Kaggle - **Google Cloud** Deep Learning VM. See [GCP Quickstart Guide](https://docs.ultralytics.com/yolov5/environments/google_cloud_quickstart_tutorial/) diff --git a/docs/en/guides/coral-edge-tpu-on-raspberry-pi.md b/docs/en/guides/coral-edge-tpu-on-raspberry-pi.md index d70a5e70da..1da6996a5a 100644 --- a/docs/en/guides/coral-edge-tpu-on-raspberry-pi.md +++ b/docs/en/guides/coral-edge-tpu-on-raspberry-pi.md @@ -175,6 +175,7 @@ Find comprehensive information on the [Predict](../modes/predict.md) page for fu Tested with Raspberry Pi OS Bookworm 64-bit and a USB Coral Edge TPU. !!! note + Shown is the inference time, pre-/postprocessing is not included. === "Raspberry Pi 4B 2GB" diff --git a/docs/en/integrations/dvc.md b/docs/en/integrations/dvc.md index 6e7327beff..b2819395c7 100644 --- a/docs/en/integrations/dvc.md +++ b/docs/en/integrations/dvc.md @@ -16,7 +16,7 @@ Integrating DVCLive with [Ultralytics YOLO11](https://www.ultralytics.com/) tran DVCLive Overview

-[DVCLive](https://dvc.org/doc/dvclive), developed by DVC, is an innovative open-source tool for experiment tracking in machine learning. Integrating seamlessly with Git and DVC, it automates the logging of crucial experiment data like model parameters and training metrics. Designed for simplicity, DVCLive enables effortless comparison and analysis of multiple runs, enhancing the efficiency of machine learning projects with intuitive [data visualization](https://www.ultralytics.com/glossary/data-visualization) and analysis tools. +[DVCLive](https://doc.dvc.org/dvclive), developed by DVC, is an innovative open-source tool for experiment tracking in machine learning. Integrating seamlessly with Git and DVC, it automates the logging of crucial experiment data like model parameters and training metrics. Designed for simplicity, DVCLive enables effortless comparison and analysis of multiple runs, enhancing the efficiency of machine learning projects with intuitive [data visualization](https://www.ultralytics.com/glossary/data-visualization) and analysis tools. ## YOLO11 Training with DVCLive @@ -166,7 +166,7 @@ Based on your analysis, iterate on your experiments. Adjust model configurations This guide has led you through the process of integrating DVCLive with Ultralytics' YOLO11. You have learned how to harness the power of DVCLive for detailed experiment monitoring, effective visualization, and insightful analysis in your machine learning endeavors. -For further details on usage, visit [DVCLive's official documentation](https://dvc.org/doc/dvclive/ml-frameworks/yolo). +For further details on usage, visit [DVCLive's official documentation](https://doc.dvc.org/dvclive/ml-frameworks/yolo). Additionally, explore more integrations and capabilities of Ultralytics by visiting the [Ultralytics integration guide page](../integrations/index.md), which is a collection of great resources and insights. diff --git a/docs/en/integrations/tensorrt.md b/docs/en/integrations/tensorrt.md index f77f7c0b64..2a0e12fb1c 100644 --- a/docs/en/integrations/tensorrt.md +++ b/docs/en/integrations/tensorrt.md @@ -240,6 +240,7 @@ Experimentation by NVIDIA led them to recommend using at least 500 calibration i See [Detection Docs](../tasks/detect.md) for usage examples with these models trained on [COCO](../datasets/detect/coco.md), which include 80 pre-trained classes. !!! note + Inference times shown for `mean`, `min` (fastest), and `max` (slowest) for each test using pre-trained weights `yolov8n.engine` | Precision | Eval test | mean
(ms) | min \| max
(ms) | mAPval
50(B) | mAPval
50-95(B) | `batch` | size
(pixels) | @@ -256,6 +257,7 @@ Experimentation by NVIDIA led them to recommend using at least 500 calibration i See [Segmentation Docs](../tasks/segment.md) for usage examples with these models trained on [COCO](../datasets/segment/coco.md), which include 80 pre-trained classes. !!! note + Inference times shown for `mean`, `min` (fastest), and `max` (slowest) for each test using pre-trained weights `yolov8n-seg.engine` | Precision | Eval test | mean
(ms) | min \| max
(ms) | mAPval
50(B) | mAPval
50-95(B) | mAPval
50(M) | mAPval
50-95(M) | `batch` | size
(pixels) | @@ -272,6 +274,7 @@ Experimentation by NVIDIA led them to recommend using at least 500 calibration i See [Classification Docs](../tasks/classify.md) for usage examples with these models trained on [ImageNet](../datasets/classify/imagenet.md), which include 1000 pre-trained classes. !!! note + Inference times shown for `mean`, `min` (fastest), and `max` (slowest) for each test using pre-trained weights `yolov8n-cls.engine` | Precision | Eval test | mean
(ms) | min \| max
(ms) | top-1 | top-5 | `batch` | size
(pixels) | @@ -288,6 +291,7 @@ Experimentation by NVIDIA led them to recommend using at least 500 calibration i See [Pose Estimation Docs](../tasks/pose.md) for usage examples with these models trained on [COCO](../datasets/pose/coco.md), which include 1 pre-trained class, "person". !!! note + Inference times shown for `mean`, `min` (fastest), and `max` (slowest) for each test using pre-trained weights `yolov8n-pose.engine` | Precision | Eval test | mean
(ms) | min \| max
(ms) | mAPval
50(B) | mAPval
50-95(B) | mAPval
50(P) | mAPval
50-95(P) | `batch` | size
(pixels) | @@ -304,6 +308,7 @@ Experimentation by NVIDIA led them to recommend using at least 500 calibration i See [Oriented Detection Docs](../tasks/obb.md) for usage examples with these models trained on [DOTAv1](../datasets/obb/dota-v2.md#dota-v10), which include 15 pre-trained classes. !!! note + Inference times shown for `mean`, `min` (fastest), and `max` (slowest) for each test using pre-trained weights `yolov8n-obb.engine` | Precision | Eval test | mean
(ms) | min \| max
(ms) | mAPval
50(B) | mAPval
50-95(B) | `batch` | size
(pixels) | @@ -324,6 +329,7 @@ Experimentation by NVIDIA led them to recommend using at least 500 calibration i Tested with Windows 10.0.19045, `python 3.10.9`, `ultralytics==8.2.4`, `tensorrt==10.0.0b6` !!! note + Inference times shown for `mean`, `min` (fastest), and `max` (slowest) for each test using pre-trained weights `yolov8n.engine` | Precision | Eval test | mean
(ms) | min \| max
(ms) | mAPval
50(B) | mAPval
50-95(B) | `batch` | size
(pixels) | @@ -340,6 +346,7 @@ Experimentation by NVIDIA led them to recommend using at least 500 calibration i Tested with Windows 10.0.22631, `python 3.11.9`, `ultralytics==8.2.4`, `tensorrt==10.0.1` !!! note + Inference times shown for `mean`, `min` (fastest), and `max` (slowest) for each test using pre-trained weights `yolov8n.engine` @@ -357,6 +364,7 @@ Experimentation by NVIDIA led them to recommend using at least 500 calibration i Tested with Pop!_OS 22.04 LTS, `python 3.10.12`, `ultralytics==8.2.4`, `tensorrt==8.6.1.post1` !!! note + Inference times shown for `mean`, `min` (fastest), and `max` (slowest) for each test using pre-trained weights `yolov8n.engine` | Precision | Eval test | mean
(ms) | min \| max
(ms) | mAPval
50(B) | mAPval
50-95(B) | `batch` | size
(pixels) | @@ -377,6 +385,7 @@ Experimentation by NVIDIA led them to recommend using at least 500 calibration i Tested with JetPack 6.0 (L4T 36.3) Ubuntu 22.04.4 LTS, `python 3.10.12`, `ultralytics==8.2.16`, `tensorrt==10.0.1` !!! note + Inference times shown for `mean`, `min` (fastest), and `max` (slowest) for each test using pre-trained weights `yolov8n.engine` | Precision | Eval test | mean
(ms) | min \| max
(ms) | mAPval
50(B) | mAPval
50-95(B) | `batch` | size
(pixels) | diff --git a/docs/en/models/fast-sam.md b/docs/en/models/fast-sam.md index 7d832dd774..7c059c13e1 100644 --- a/docs/en/models/fast-sam.md +++ b/docs/en/models/fast-sam.md @@ -220,7 +220,7 @@ To perform object tracking on an image, use the `track` method as shown below: ## FastSAM official Usage -FastSAM is also available directly from the [https://github.com/CASIA-IVA-Lab/FastSAM](https://github.com/CASIA-IVA-Lab/FastSAM) repository. Here is a brief overview of the typical steps you might take to use FastSAM: +FastSAM is also available directly from the [https://github.com/CASIA-IVA-Lab/FastSAM](https://github.com/CASIA-LMC-Lab/FastSAM) repository. Here is a brief overview of the typical steps you might take to use FastSAM: ### Installation @@ -298,7 +298,7 @@ We would like to acknowledge the FastSAM authors for their significant contribut } ``` -The original FastSAM paper can be found on [arXiv](https://arxiv.org/abs/2306.12156). The authors have made their work publicly available, and the codebase can be accessed on [GitHub](https://github.com/CASIA-IVA-Lab/FastSAM). We appreciate their efforts in advancing the field and making their work accessible to the broader community. +The original FastSAM paper can be found on [arXiv](https://arxiv.org/abs/2306.12156). The authors have made their work publicly available, and the codebase can be accessed on [GitHub](https://github.com/CASIA-LMC-Lab/FastSAM). We appreciate their efforts in advancing the field and making their work accessible to the broader community. ## FAQ diff --git a/docs/en/quickstart.md b/docs/en/quickstart.md index e809db0033..cbdcdad9b4 100644 --- a/docs/en/quickstart.md +++ b/docs/en/quickstart.md @@ -174,6 +174,7 @@ While the standard installation methods cover most use cases, you might need a m ``` !!! warning "Dependency Management" + This method gives full control but requires careful management of dependencies. Ensure all required packages are installed with compatible versions by referencing the `ultralytics` `pyproject.toml` file. === "Method 2: Install from a Custom Fork" diff --git a/docs/en/yolov5/index.md b/docs/en/yolov5/index.md index 6c6d9a9a71..f952455d4f 100644 --- a/docs/en/yolov5/index.md +++ b/docs/en/yolov5/index.md @@ -48,7 +48,7 @@ Here's a compilation of comprehensive tutorials that will guide you through diff ## Supported Environments -Ultralytics provides a range of ready-to-use environments, each pre-installed with essential dependencies such as [CUDA](https://developer.nvidia.com/cuda-zone), [CuDNN](https://developer.nvidia.com/cudnn), [Python](https://www.python.org/), and [PyTorch](https://pytorch.org/), to kickstart your projects. You can also manage your models and datasets using [Ultralytics HUB](https://www.ultralytics.com/hub). +Ultralytics provides a range of ready-to-use environments, each pre-installed with essential dependencies such as [CUDA](https://developer.nvidia.com/cuda), [CuDNN](https://developer.nvidia.com/cudnn), [Python](https://www.python.org/), and [PyTorch](https://pytorch.org/), to kickstart your projects. You can also manage your models and datasets using [Ultralytics HUB](https://www.ultralytics.com/hub). - **Free GPU Notebooks**: Run on Gradient Open In Colab Open In Kaggle - **Google Cloud**: [GCP Quickstart Guide](environments/google_cloud_quickstart_tutorial.md) diff --git a/docs/en/yolov5/tutorials/hyperparameter_evolution.md b/docs/en/yolov5/tutorials/hyperparameter_evolution.md index b5d24cbce1..b7e32bd8fa 100644 --- a/docs/en/yolov5/tutorials/hyperparameter_evolution.md +++ b/docs/en/yolov5/tutorials/hyperparameter_evolution.md @@ -165,7 +165,7 @@ When evolution finishes, reuse the discovered settings by pointing training at t ## Supported Environments -Ultralytics provides a range of ready-to-use environments, each pre-installed with essential dependencies such as [CUDA](https://developer.nvidia.com/cuda-zone), [CUDNN](https://developer.nvidia.com/cudnn), [Python](https://www.python.org/), and [PyTorch](https://pytorch.org/), to kickstart your projects. +Ultralytics provides a range of ready-to-use environments, each pre-installed with essential dependencies such as [CUDA](https://developer.nvidia.com/cuda), [CUDNN](https://developer.nvidia.com/cudnn), [Python](https://www.python.org/), and [PyTorch](https://pytorch.org/), to kickstart your projects. - **Free GPU Notebooks**: Run on Gradient Open In Colab Open In Kaggle - **Google Cloud**: [GCP Quickstart Guide](../environments/google_cloud_quickstart_tutorial.md) diff --git a/docs/en/yolov5/tutorials/model_ensembling.md b/docs/en/yolov5/tutorials/model_ensembling.md index 0b1744e7be..84ce2291de 100644 --- a/docs/en/yolov5/tutorials/model_ensembling.md +++ b/docs/en/yolov5/tutorials/model_ensembling.md @@ -158,7 +158,7 @@ For real-time applications with strict latency requirements, single model infere ## Supported Environments -Ultralytics provides a range of ready-to-use environments, each pre-installed with essential dependencies such as [CUDA](https://developer.nvidia.com/cuda-zone), [CUDNN](https://developer.nvidia.com/cudnn), [Python](https://www.python.org/), and [PyTorch](https://pytorch.org/), to kickstart your projects. +Ultralytics provides a range of ready-to-use environments, each pre-installed with essential dependencies such as [CUDA](https://developer.nvidia.com/cuda), [CUDNN](https://developer.nvidia.com/cudnn), [Python](https://www.python.org/), and [PyTorch](https://pytorch.org/), to kickstart your projects. - **Free GPU Notebooks**: Run on Gradient Open In Colab Open In Kaggle - **Google Cloud**: [GCP Quickstart Guide](../environments/google_cloud_quickstart_tutorial.md) diff --git a/docs/en/yolov5/tutorials/model_export.md b/docs/en/yolov5/tutorials/model_export.md index 8476c8d67f..0b02661e08 100644 --- a/docs/en/yolov5/tutorials/model_export.md +++ b/docs/en/yolov5/tutorials/model_export.md @@ -237,7 +237,7 @@ YOLOv5 OpenVINO C++ inference examples: ## Supported Environments -Ultralytics provides a range of ready-to-use environments, each pre-installed with essential dependencies such as [CUDA](https://developer.nvidia.com/cuda-zone), [CUDNN](https://developer.nvidia.com/cudnn), [Python](https://www.python.org/), and [PyTorch](https://pytorch.org/), to kickstart your projects. +Ultralytics provides a range of ready-to-use environments, each pre-installed with essential dependencies such as [CUDA](https://developer.nvidia.com/cuda), [CUDNN](https://developer.nvidia.com/cudnn), [Python](https://www.python.org/), and [PyTorch](https://pytorch.org/), to kickstart your projects. - **Free GPU Notebooks**: Run on Gradient Open In Colab Open In Kaggle - **Google Cloud**: [GCP Quickstart Guide](../environments/google_cloud_quickstart_tutorial.md) diff --git a/docs/en/yolov5/tutorials/model_pruning_and_sparsity.md b/docs/en/yolov5/tutorials/model_pruning_and_sparsity.md index eb956578fa..bb60779618 100644 --- a/docs/en/yolov5/tutorials/model_pruning_and_sparsity.md +++ b/docs/en/yolov5/tutorials/model_pruning_and_sparsity.md @@ -127,7 +127,7 @@ This process helps the remaining parameters adapt to compensate for the removed ## Supported Environments -Ultralytics provides a range of ready-to-use environments, each pre-installed with essential dependencies such as [CUDA](https://developer.nvidia.com/cuda-zone), [CUDNN](https://developer.nvidia.com/cudnn), [Python](https://www.python.org/), and [PyTorch](https://pytorch.org/), to kickstart your projects. +Ultralytics provides a range of ready-to-use environments, each pre-installed with essential dependencies such as [CUDA](https://developer.nvidia.com/cuda), [CUDNN](https://developer.nvidia.com/cudnn), [Python](https://www.python.org/), and [PyTorch](https://pytorch.org/), to kickstart your projects. - **Free GPU Notebooks**: Run on Gradient Open In Colab Open In Kaggle - **Google Cloud**: [GCP Quickstart Guide](../environments/google_cloud_quickstart_tutorial.md) diff --git a/docs/en/yolov5/tutorials/multi_gpu_training.md b/docs/en/yolov5/tutorials/multi_gpu_training.md index db659a159d..b4237219a7 100644 --- a/docs/en/yolov5/tutorials/multi_gpu_training.md +++ b/docs/en/yolov5/tutorials/multi_gpu_training.md @@ -177,7 +177,7 @@ If you went through all the above, feel free to raise an Issue by giving as much ## Supported Environments -Ultralytics provides a range of ready-to-use environments, each pre-installed with essential dependencies such as [CUDA](https://developer.nvidia.com/cuda-zone), [CUDNN](https://developer.nvidia.com/cudnn), [Python](https://www.python.org/), and [PyTorch](https://pytorch.org/), to kickstart your projects. +Ultralytics provides a range of ready-to-use environments, each pre-installed with essential dependencies such as [CUDA](https://developer.nvidia.com/cuda), [CUDNN](https://developer.nvidia.com/cudnn), [Python](https://www.python.org/), and [PyTorch](https://pytorch.org/), to kickstart your projects. - **Free GPU Notebooks**: Run on Gradient Open In Colab Open In Kaggle - **Google Cloud**: [GCP Quickstart Guide](../environments/google_cloud_quickstart_tutorial.md) diff --git a/docs/en/yolov5/tutorials/pytorch_hub_model_loading.md b/docs/en/yolov5/tutorials/pytorch_hub_model_loading.md index 3c379bd006..aef9b28920 100644 --- a/docs/en/yolov5/tutorials/pytorch_hub_model_loading.md +++ b/docs/en/yolov5/tutorials/pytorch_hub_model_loading.md @@ -357,7 +357,7 @@ model = torch.hub.load("ultralytics/yolov5", "custom", path="yolov5s_paddle_mode ## Supported Environments -Ultralytics provides a range of ready-to-use environments, each pre-installed with essential dependencies such as [CUDA](https://developer.nvidia.com/cuda-zone), [CUDNN](https://developer.nvidia.com/cudnn), [Python](https://www.python.org/), and [PyTorch](https://pytorch.org/), to kickstart your projects. +Ultralytics provides a range of ready-to-use environments, each pre-installed with essential dependencies such as [CUDA](https://developer.nvidia.com/cuda), [CUDNN](https://developer.nvidia.com/cudnn), [Python](https://www.python.org/), and [PyTorch](https://pytorch.org/), to kickstart your projects. - **Free GPU Notebooks**: Run on Gradient Open In Colab Open In Kaggle - **Google Cloud**: [GCP Quickstart Guide](../environments/google_cloud_quickstart_tutorial.md) diff --git a/docs/en/yolov5/tutorials/test_time_augmentation.md b/docs/en/yolov5/tutorials/test_time_augmentation.md index 66061954df..d5ffb78964 100644 --- a/docs/en/yolov5/tutorials/test_time_augmentation.md +++ b/docs/en/yolov5/tutorials/test_time_augmentation.md @@ -160,7 +160,7 @@ The tradeoff is increased inference time, making TTA more suitable for applicati ## Supported Environments -Ultralytics provides a range of ready-to-use environments, each pre-installed with essential dependencies such as [CUDA](https://developer.nvidia.com/cuda-zone), [CUDNN](https://developer.nvidia.com/cudnn), [Python](https://www.python.org/), and [PyTorch](https://pytorch.org/), to kickstart your projects. +Ultralytics provides a range of ready-to-use environments, each pre-installed with essential dependencies such as [CUDA](https://developer.nvidia.com/cuda), [CUDNN](https://developer.nvidia.com/cudnn), [Python](https://www.python.org/), and [PyTorch](https://pytorch.org/), to kickstart your projects. - **Free GPU Notebooks**: Run on Gradient Open In Colab Open In Kaggle - **Google Cloud**: [GCP Quickstart Guide](../environments/google_cloud_quickstart_tutorial.md) diff --git a/docs/en/yolov5/tutorials/train_custom_data.md b/docs/en/yolov5/tutorials/train_custom_data.md index 5ffa1dcc8b..9b44dd3f88 100644 --- a/docs/en/yolov5/tutorials/train_custom_data.md +++ b/docs/en/yolov5/tutorials/train_custom_data.md @@ -239,7 +239,7 @@ Upon successful completion of training, the best performing model checkpoint (`b ## Supported Environments -Ultralytics provides ready-to-use environments equipped with essential dependencies like [CUDA](https://developer.nvidia.com/cuda-zone), [cuDNN](https://developer.nvidia.com/cudnn), [Python](https://www.python.org/), and [PyTorch](https://pytorch.org/), facilitating a smooth start. +Ultralytics provides ready-to-use environments equipped with essential dependencies like [CUDA](https://developer.nvidia.com/cuda), [cuDNN](https://developer.nvidia.com/cudnn), [Python](https://www.python.org/), and [PyTorch](https://pytorch.org/), facilitating a smooth start. - **Free GPU Notebooks**: - Run on Gradient diff --git a/docs/en/yolov5/tutorials/transfer_learning_with_frozen_layers.md b/docs/en/yolov5/tutorials/transfer_learning_with_frozen_layers.md index 85e43c19de..e755edd39b 100644 --- a/docs/en/yolov5/tutorials/transfer_learning_with_frozen_layers.md +++ b/docs/en/yolov5/tutorials/transfer_learning_with_frozen_layers.md @@ -152,7 +152,7 @@ Explore more about the nuances of transfer learning in our [glossary entry](http ## Supported Environments -Ultralytics offers various ready-to-use environments with essential dependencies like [CUDA](https://developer.nvidia.com/cuda-zone), [CuDNN](https://developer.nvidia.com/cudnn), [Python](https://www.python.org/), and [PyTorch](https://pytorch.org/) pre-installed. +Ultralytics offers various ready-to-use environments with essential dependencies like [CUDA](https://developer.nvidia.com/cuda), [CuDNN](https://developer.nvidia.com/cudnn), [Python](https://www.python.org/), and [PyTorch](https://pytorch.org/) pre-installed. - **Free GPU Notebooks**: Run on Gradient Open In Colab Open In Kaggle - **Google Cloud**: [GCP Quickstart Guide](../environments/google_cloud_quickstart_tutorial.md) diff --git a/examples/YOLO-Interactive-Tracking-UI/README.md b/examples/YOLO-Interactive-Tracking-UI/README.md index 3a7ea8eacb..9afe1b7d65 100644 --- a/examples/YOLO-Interactive-Tracking-UI/README.md +++ b/examples/YOLO-Interactive-Tracking-UI/README.md @@ -13,7 +13,7 @@ https://github.com/user-attachments/assets/723e919e-555b-4cca-8e60-18e711d4f3b2 - [Live terminal output](https://docs.ultralytics.com/guides/view-results-in-terminal/): object ID, label, [confidence](https://www.ultralytics.com/glossary/confidence), and center coordinates - Adjustable object tracking algorithms ([ByteTrack](https://docs.ultralytics.com/reference/trackers/byte_tracker/), [BoT-SORT](https://docs.ultralytics.com/reference/trackers/bot_sort/)) - Supports: - - [PyTorch](https://pytorch.org/) `.pt` models (for GPU devices like [NVIDIA Jetson](https://docs.ultralytics.com/guides/nvidia-jetson/) or [CUDA](https://developer.nvidia.com/cuda-zone)-enabled desktops) + - [PyTorch](https://pytorch.org/) `.pt` models (for GPU devices like [NVIDIA Jetson](https://docs.ultralytics.com/guides/nvidia-jetson/) or [CUDA](https://developer.nvidia.com/cuda)-enabled desktops) - [NCNN](https://docs.ultralytics.com/integrations/ncnn/) `.param + .bin` models (for CPU-only devices like [Raspberry Pi](https://www.raspberrypi.org/) or ARM boards) ## 🏗️ Project Structure