xclele/yolov10
1
0
Fork 0
mirror of https://github.com/THU-MIG/yolov10.git synced 2025-05-22 21:04:21 +08:00
Code Issues Actions Packages Projects Releases Wiki Activity

Add bgr hyperparameter (#9139)

Browse Source 
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
This commit is contained in:
Laughing 2024-03-24 06:17:00 +08:00 committed by GitHub
parent e706c7f625
commit 33607ca278
No known key found for this signature in database
GPG Key ID: B5690EEEBB952194
8 changed files with 13 additions and 2 deletions
Show Stats Download Patch File Download Diff File Expand all files Collapse all files

1
docs/en/modes/train.md
View File

@ -242,6 +242,7 @@ Augmentation techniques are essential for improving the robustness and performan
| `perspective` | `float` | `0.0` | `0.0 - 0.001` | Applies a random perspective transformation to the image, enhancing the model's ability to understand objects in 3D space. |
| `flipud` | `float` | `0.0` | `0.0 - 1.0` | Flips the image upside down with the specified probability, increasing the data variability without affecting the object's characteristics. |
| `fliplr` | `float` | `0.5` | `0.0 - 1.0` | Flips the image left to right with the specified probability, useful for learning symmetrical objects and increasing dataset diversity. |
| `bgr` | `float` | `0.0` | `0.0 - 1.0` | Flips the image channels from RGB to BGR with the specified probability, useful for increasing robustness to incorrect channel ordering. |
| `mosaic` | `float` | `1.0` | `0.0 - 1.0` | Combines four training images into one, simulating different scene compositions and object interactions. Highly effective for complex scene understanding. |
| `mixup` | `float` | `0.0` | `0.0 - 1.0` | Blends two images and their labels, creating a composite image. Enhances the model's ability to generalize by introducing label noise and visual variability. |
| `copy_paste` | `float` | `0.0` | `0.0 - 1.0` | Copies objects from one image and pastes them onto another, useful for increasing object instances and learning object occlusion. |

3
docs/en/usage/cfg.md
View File

@ -147,7 +147,7 @@ Inference arguments:
|-----------------|----------------|------------------------|--------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------------|
| `source` | `str` | `'ultralytics/assets'` | Specifies the data source for inference. Can be an image path, video file, directory, URL, or device ID for live feeds. Supports a wide range of formats and sources, enabling flexible application across different types of input. |
| `conf` | `float` | `0.25` | Sets the minimum confidence threshold for detections. Objects detected with confidence below this threshold will be disregarded. Adjusting this value can help reduce false positives. |
| `iou` | `float` | `0.7` | Intersection Over Union (IoU) threshold for Non-Maximum Suppression (NMS). Lower values result in fewer detections by eliminating overlapping boxes, useful for reducing duplicates. |
| `iou` | `float` | `0.7` | Intersection Over Union (IoU) threshold for Non-Maximum Suppression (NMS). Lower values result in fewer detections by eliminating overlapping boxes, useful for reducing duplicates. |
| `imgsz` | `int or tuple` | `640` | Defines the image size for inference. Can be a single integer `640` for square resizing or a (height, width) tuple. Proper sizing can improve detection accuracy and processing speed. |
| `half` | `bool` | `False` | Enables half-precision (FP16) inference, which can speed up model inference on supported GPUs with minimal impact on accuracy. |
| `device` | `str` | `None` | Specifies the device for inference (e.g., `cpu`, `cuda:0` or `0`). Allows users to select between CPU, a specific GPU, or other compute devices for model execution. |
@ -241,6 +241,7 @@ Augmentation techniques are essential for improving the robustness and performan
| `perspective` | `float` | `0.0` | `0.0 - 0.001` | Applies a random perspective transformation to the image, enhancing the model's ability to understand objects in 3D space. |
| `flipud` | `float` | `0.0` | `0.0 - 1.0` | Flips the image upside down with the specified probability, increasing the data variability without affecting the object's characteristics. |
| `fliplr` | `float` | `0.5` | `0.0 - 1.0` | Flips the image left to right with the specified probability, useful for learning symmetrical objects and increasing dataset diversity. |
| `bgr` | `float` | `0.0` | `0.0 - 1.0` | Flips the image channels from RGB to BGR with the specified probability, useful for increasing robustness to incorrect channel ordering. |
| `mosaic` | `float` | `1.0` | `0.0 - 1.0` | Combines four training images into one, simulating different scene compositions and object interactions. Highly effective for complex scene understanding. |
| `mixup` | `float` | `0.0` | `0.0 - 1.0` | Blends two images and their labels, creating a composite image. Enhances the model's ability to generalize by introducing label noise and visual variability. |
| `copy_paste` | `float` | `0.0` | `0.0 - 1.0` | Copies objects from one image and pastes them onto another, useful for increasing object instances and learning object occlusion. |

1
ultralytics/cfg/__init__.py
View File

@ -112,6 +112,7 @@ CFG_FRACTION_KEYS = {
"perspective",
"flipud",
"fliplr",
"bgr",
"mosaic",
"mixup",
"copy_paste",

1
ultralytics/cfg/default.yaml
View File

@ -111,6 +111,7 @@ shear: 0.0 # (float) image shear (+/- deg)
perspective: 0.0 # (float) image perspective (+/- fraction), range 0-0.001
flipud: 0.0 # (float) image flip up-down (probability)
fliplr: 0.5 # (float) image flip left-right (probability)
bgr: 0.0 # (float) image channel BGR (probability)
mosaic: 1.0 # (float) image mosaic (probability)
mixup: 0.0 # (float) image mixup (probability)
copy_paste: 0.0 # (float) segment copy-paste (probability)

6
ultralytics/data/augment.py
View File

@ -886,6 +886,7 @@ class Format:
mask_ratio (int): Downsample ratio for masks. Default is 4.
mask_overlap (bool): Whether to overlap masks. Default is True.
batch_idx (bool): Keep batch indexes. Default is True.
bgr (float): The probability to return BGR images. Default is 0.0.
"""
def __init__(
@ -898,6 +899,7 @@ class Format:
mask_ratio=4,
mask_overlap=True,
batch_idx=True,
bgr=0.0,
):
"""Initializes the Format class with given parameters."""
self.bbox_format = bbox_format
@ -908,6 +910,7 @@ class Format:
self.mask_ratio = mask_ratio
self.mask_overlap = mask_overlap
self.batch_idx = batch_idx # keep the batch indexes
self.bgr = bgr
def __call__(self, labels):
"""Return formatted image, classes, bounding boxes & keypoints to be used by 'collate_fn'."""
@ -948,7 +951,8 @@ class Format:
"""Format the image for YOLO from Numpy array to PyTorch tensor."""
if len(img.shape) < 3:
img = np.expand_dims(img, -1)
img = np.ascontiguousarray(img.transpose(2, 0, 1)[::-1])
img = img.transpose(2, 0, 1)
img = np.ascontiguousarray(img[::-1] if random.uniform(0, 1) > self.bgr else img)
img = torch.from_numpy(img)
return img

1
ultralytics/data/dataset.py
View File

@ -167,6 +167,7 @@ class YOLODataset(BaseDataset):
batch_idx=True,
mask_ratio=hyp.mask_ratio,
mask_overlap=hyp.overlap_mask,
bgr=hyp.bgr if self.augment else 0.0, # only affect training.
)
)
return transforms

1
ultralytics/engine/tuner.py
View File

@ -95,6 +95,7 @@ class Tuner:
"perspective": (0.0, 0.001), # image perspective (+/- fraction), range 0-0.001
"flipud": (0.0, 1.0), # image flip up-down (probability)
"fliplr": (0.0, 1.0), # image flip left-right (probability)
"bgr": (0.0, 1.0), # image channel bgr (probability)
"mosaic": (0.0, 1.0), # image mixup (probability)
"mixup": (0.0, 1.0), # image mixup (probability)
"copy_paste": (0.0, 1.0), # segment copy-paste (probability)

1
ultralytics/utils/tuner.py
View File

@ -78,6 +78,7 @@ def run_ray_tune(
"perspective": tune.uniform(0.0, 0.001), # image perspective (+/- fraction), range 0-0.001
"flipud": tune.uniform(0.0, 1.0), # image flip up-down (probability)
"fliplr": tune.uniform(0.0, 1.0), # image flip left-right (probability)
"bgr": tune.uniform(0.0, 1.0), # image channel BGR (probability)
"mosaic": tune.uniform(0.0, 1.0), # image mixup (probability)
"mixup": tune.uniform(0.0, 1.0), # image mixup (probability)
"copy_paste": tune.uniform(0.0, 1.0), # segment copy-paste (probability)