xdobro23/YOLOv8-16bit
1
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity

ultralytics 8.0.148 fix SettingsManager empty YAML bug (#4180)

Browse Source
This commit is contained in:
Glenn Jocher
2023-08-05 16:13:29 +02:00
committed by GitHub
parent a9fb8b239b
commit 038558cfab
7 changed files with 50 additions and 38 deletions
Download Patch File Download Diff File Expand all files Collapse all files

2
docs/integrations/openvino.md
View File

@ -4,7 +4,7 @@ description: Discover the power of deploying your Ultralytics YOLOv8 model using
keywords: ultralytics docs, YOLOv8, export YOLOv8, YOLOv8 model deployment, exporting YOLOv8, OpenVINO, OpenVINO format
---
<img width="1024" src="https://user-images.githubusercontent.com/26833433/252345644-0cf84257-4b34-404c-b7ce-eb73dfbcaff1.png">
<img width="1024" src="https://user-images.githubusercontent.com/26833433/252345644-0cf84257-4b34-404c-b7ce-eb73dfbcaff1.png" alt="OpenVINO Ecosystem">
**Export mode** is used for exporting a YOLOv8 model to a format that can be used for deployment. In this guide, we specifically cover exporting to OpenVINO, which can provide up to 3x [CPU](https://docs.openvino.ai/2023.0/openvino_docs_OV_UG_supported_plugins_CPU.html) speedup as well as accelerating on other Intel hardware ([iGPU](https://docs.openvino.ai/2023.0/openvino_docs_OV_UG_supported_plugins_GPU.html), [dGPU](https://docs.openvino.ai/2023.0/openvino_docs_OV_UG_supported_plugins_GPU.html), [VPU](https://docs.openvino.ai/2022.3/openvino_docs_OV_UG_supported_plugins_VPU.html), etc.).

69
docs/integrations/ray-tune.md
View File

@ -14,7 +14,9 @@ Hyperparameter tuning is vital in achieving peak model performance by discoverin
### Ray Tune
![Ray Tune Overview](https://docs.ray.io/en/latest/_images/tune_overview.png)
<p align="center">
<img width="640" src="https://docs.ray.io/en/latest/_images/tune_overview.png" alt="Ray Tune Overview">
</p>
[Ray Tune](https://docs.ray.io/en/latest/tune/index.html) is a hyperparameter tuning library designed for efficiency and flexibility. It supports various search strategies, parallelism, and early stopping strategies, and seamlessly integrates with popular machine learning frameworks, including Ultralytics YOLOv8.
@ -43,7 +45,10 @@ To install the required packages, run:
```python
from ultralytics import YOLO
# Load a YOLOv8n model
model = YOLO("yolov8n.pt")
# Start tuning hyperparameters for YOLOv8n training on the COCO128 dataset
result_grid = model.tune(data="coco128.yaml")
```
@ -51,14 +56,14 @@ To install the required packages, run:
The `tune()` method in YOLOv8 provides an easy-to-use interface for hyperparameter tuning with Ray Tune. It accepts several arguments that allow you to customize the tuning process. Below is a detailed explanation of each parameter:
| Parameter | Type | Description | Default Value |
|-----------------|----------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|---------------|
| `data` | str | The dataset configuration file (in YAML format) to run the tuner on. This file should specify the training and validation data paths, as well as other dataset-specific settings. | |
| `space` | dict, optional | A dictionary defining the hyperparameter search space for Ray Tune. Each key corresponds to a hyperparameter name, and the value specifies the range of values to explore during tuning. If not provided, YOLOv8 uses a default search space with various hyperparameters. | |
| `grace_period` | int, optional | The grace period in epochs for the [ASHA scheduler](https://docs.ray.io/en/latest/tune/api/schedulers.html) in Ray Tune. The scheduler will not terminate any trial before this number of epochs, allowing the model to have some minimum training before making a decision on early stopping. | 10 |
| `gpu_per_trial` | int, optional | The number of GPUs to allocate per trial during tuning. This helps manage GPU usage, particularly in multi-GPU environments. If not provided, the tuner will use all available GPUs. | None |
| `max_samples` | int, optional | The maximum number of trials to run during tuning. This parameter helps control the total number of hyperparameter combinations tested, ensuring the tuning process does not run indefinitely. | 10 |
| `**train_args` | dict, optional | Additional arguments to pass to the `train()` method during tuning. These arguments can include settings like the number of training epochs, batch size, and other training-specific configurations. | {} |
| Parameter | Type | Description | Default Value |
|-----------------|------------------|------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|---------------|
| `data` | `str` | The dataset configuration file (in YAML format) to run the tuner on. This file should specify the training and validation data paths, as well as other dataset-specific settings. | |
| `space` | `dict, optional` | A dictionary defining the hyperparameter search space for Ray Tune. Each key corresponds to a hyperparameter name, and the value specifies the range of values to explore during tuning. If not provided, YOLOv8 uses a default search space with various hyperparameters. | |
| `grace_period` | `int, optional` | The grace period in epochs for the [ASHA scheduler](https://docs.ray.io/en/latest/tune/api/schedulers.html) in Ray Tune. The scheduler will not terminate any trial before this number of epochs, allowing the model to have some minimum training before making a decision on early stopping. | 10 |
| `gpu_per_trial` | `int, optional` | The number of GPUs to allocate per trial during tuning. This helps manage GPU usage, particularly in multi-GPU environments. If not provided, the tuner will use all available GPUs. | None |
| `max_samples` | `int, optional` | The maximum number of trials to run during tuning. This parameter helps control the total number of hyperparameter combinations tested, ensuring the tuning process does not run indefinitely. | 10 |
| `**train_args` | `dict, optional` | Additional arguments to pass to the `train()` method during tuning. These arguments can include settings like the number of training epochs, batch size, and other training-specific configurations. | {} |
By customizing these parameters, you can fine-tune the hyperparameter optimization process to suit your specific needs and available computational resources.
@ -66,29 +71,29 @@ By customizing these parameters, you can fine-tune the hyperparameter optimizati
The following table lists the default search space parameters for hyperparameter tuning in YOLOv8 with Ray Tune. Each parameter has a specific value range defined by `tune.uniform()`.
| Parameter | Value Range | Description |
|-----------------|----------------------------|------------------------------------------|
| lr0 | `tune.uniform(1e-5, 1e-1)` | Initial learning rate |
| lrf | `tune.uniform(0.01, 1.0)` | Final learning rate factor |
| momentum | `tune.uniform(0.6, 0.98)` | Momentum |
| weight_decay | `tune.uniform(0.0, 0.001)` | Weight decay |
| warmup_epochs | `tune.uniform(0.0, 5.0)` | Warmup epochs |
| warmup_momentum | `tune.uniform(0.0, 0.95)` | Warmup momentum |
| box | `tune.uniform(0.02, 0.2)` | Box loss weight |
| cls | `tune.uniform(0.2, 4.0)` | Class loss weight |
| hsv_h | `tune.uniform(0.0, 0.1)` | Hue augmentation range |
| hsv_s | `tune.uniform(0.0, 0.9)` | Saturation augmentation range |
| hsv_v | `tune.uniform(0.0, 0.9)` | Value (brightness) augmentation range |
| degrees | `tune.uniform(0.0, 45.0)` | Rotation augmentation range (degrees) |
| translate | `tune.uniform(0.0, 0.9)` | Translation augmentation range |
| scale | `tune.uniform(0.0, 0.9)` | Scaling augmentation range |
| shear | `tune.uniform(0.0, 10.0)` | Shear augmentation range (degrees) |
| perspective | `tune.uniform(0.0, 0.001)` | Perspective augmentation range |
| flipud | `tune.uniform(0.0, 1.0)` | Vertical flip augmentation probability |
| fliplr | `tune.uniform(0.0, 1.0)` | Horizontal flip augmentation probability |
| mosaic | `tune.uniform(0.0, 1.0)` | Mosaic augmentation probability |
| mixup | `tune.uniform(0.0, 1.0)` | Mixup augmentation probability |
| copy_paste | `tune.uniform(0.0, 1.0)` | Copy-paste augmentation probability |
| Parameter | Value Range | Description |
|-------------------|----------------------------|------------------------------------------|
| `lr0` | `tune.uniform(1e-5, 1e-1)` | Initial learning rate |
| `lrf` | `tune.uniform(0.01, 1.0)` | Final learning rate factor |
| `momentum` | `tune.uniform(0.6, 0.98)` | Momentum |
| `weight_decay` | `tune.uniform(0.0, 0.001)` | Weight decay |
| `warmup_epochs` | `tune.uniform(0.0, 5.0)` | Warmup epochs |
| `warmup_momentum` | `tune.uniform(0.0, 0.95)` | Warmup momentum |
| `box` | `tune.uniform(0.02, 0.2)` | Box loss weight |
| `cls` | `tune.uniform(0.2, 4.0)` | Class loss weight |
| `hsv_h` | `tune.uniform(0.0, 0.1)` | Hue augmentation range |
| `hsv_s` | `tune.uniform(0.0, 0.9)` | Saturation augmentation range |
| `hsv_v` | `tune.uniform(0.0, 0.9)` | Value (brightness) augmentation range |
| `degrees` | `tune.uniform(0.0, 45.0)` | Rotation augmentation range (degrees) |
| `translate` | `tune.uniform(0.0, 0.9)` | Translation augmentation range |
| `scale` | `tune.uniform(0.0, 0.9)` | Scaling augmentation range |
| `shear` | `tune.uniform(0.0, 10.0)` | Shear augmentation range (degrees) |
| `perspective` | `tune.uniform(0.0, 0.001)` | Perspective augmentation range |
| `flipud` | `tune.uniform(0.0, 1.0)` | Vertical flip augmentation probability |
| `fliplr` | `tune.uniform(0.0, 1.0)` | Horizontal flip augmentation probability |
| `mosaic` | `tune.uniform(0.0, 1.0)` | Mosaic augmentation probability |
| `mixup` | `tune.uniform(0.0, 1.0)` | Mixup augmentation probability |
| `copy_paste` | `tune.uniform(0.0, 1.0)` | Copy-paste augmentation probability |
## Custom Search Space Example