lichen/detecttracking
1
0
Fork 0
Code Issues Pull Requests Actions Packages Projects Releases Wiki Activity

add yolo v10 and modify pipeline

Browse Source
This commit is contained in:
王庆刚
2025-03-28 13:19:54 +08:00
parent 183299c06b
commit 798c596acc
471 changed files with 19109 additions and 7342 deletions
Download Patch File Download Diff File Expand all files Collapse all files

38
ultralytics/models/sam/modules/sam.py
View File

@ -16,8 +16,23 @@ from .encoders import ImageEncoderViT, PromptEncoder
class Sam(nn.Module):
"""
Sam (Segment Anything Model) is designed for object segmentation tasks. It uses image encoders to generate image
embeddings, and prompt encoders to encode various types of input prompts. These embeddings are then used by the mask
decoder to predict object masks.
Attributes:
mask_threshold (float): Threshold value for mask prediction.
image_format (str): Format of the input image, default is 'RGB'.
image_encoder (ImageEncoderViT): The backbone used to encode the image into embeddings.
prompt_encoder (PromptEncoder): Encodes various types of input prompts.
mask_decoder (MaskDecoder): Predicts object masks from the image and prompt embeddings.
pixel_mean (List[float]): Mean pixel values for image normalization.
pixel_std (List[float]): Standard deviation values for image normalization.
"""
mask_threshold: float = 0.0
image_format: str = 'RGB'
image_format: str = "RGB"
def __init__(
self,
@ -25,25 +40,26 @@ class Sam(nn.Module):
prompt_encoder: PromptEncoder,
mask_decoder: MaskDecoder,
pixel_mean: List[float] = (123.675, 116.28, 103.53),
pixel_std: List[float] = (58.395, 57.12, 57.375)
pixel_std: List[float] = (58.395, 57.12, 57.375),
) -> None:
"""
SAM predicts object masks from an image and input prompts.
Initialize the Sam class to predict object masks from an image and input prompts.
Note:
All forward() operations moved to SAMPredictor.
Args:
image_encoder (ImageEncoderViT): The backbone used to encode the image into image embeddings that allow for
efficient mask prediction.
prompt_encoder (PromptEncoder): Encodes various types of input prompts.
mask_decoder (MaskDecoder): Predicts masks from the image embeddings and encoded prompts.
pixel_mean (list(float)): Mean values for normalizing pixels in the input image.
pixel_std (list(float)): Std values for normalizing pixels in the input image.
image_encoder (ImageEncoderViT): The backbone used to encode the image into image embeddings.
prompt_encoder (PromptEncoder): Encodes various types of input prompts.
mask_decoder (MaskDecoder): Predicts masks from the image embeddings and encoded prompts.
pixel_mean (List[float], optional): Mean values for normalizing pixels in the input image. Defaults to
(123.675, 116.28, 103.53).
pixel_std (List[float], optional): Std values for normalizing pixels in the input image. Defaults to
(58.395, 57.12, 57.375).
"""
super().__init__()
self.image_encoder = image_encoder
self.prompt_encoder = prompt_encoder
self.mask_decoder = mask_decoder
self.register_buffer('pixel_mean', torch.Tensor(pixel_mean).view(-1, 1, 1), False)
self.register_buffer('pixel_std', torch.Tensor(pixel_std).view(-1, 1, 1), False)
self.register_buffer("pixel_mean", torch.Tensor(pixel_mean).view(-1, 1, 1), False)
self.register_buffer("pixel_std", torch.Tensor(pixel_std).view(-1, 1, 1), False)