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

Add RTDETR Trainer (#2745)

Browse Source 
Co-authored-by: pre-commit-ci[bot] <66853113+pre-commit-ci[bot]@users.noreply.github.com>
Co-authored-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Co-authored-by: Laughing-q <1185102784@qq.com>
Co-authored-by: Kayzwer <68285002+Kayzwer@users.noreply.github.com>
Co-authored-by: Laughing <61612323+Laughing-q@users.noreply.github.com>
This commit is contained in:
Ayush Chaurasia
2023-06-17 17:16:18 +05:30
committed by GitHub
parent 03bce07848
commit a0ba8ef5f0
23 changed files with 989 additions and 314 deletions
Download Patch File Download Diff File Expand all files Collapse all files

4
ultralytics/vit/sam/amg.py
View File

@ -256,10 +256,8 @@ def remove_small_regions(mask: np.ndarray, area_thresh: float, mode: str) -> Tup
return mask, False
fill_labels = [0] + small_regions
if not correct_holes:
fill_labels = [i for i in range(n_labels) if i not in fill_labels]
# If every region is below threshold, keep largest
if not fill_labels:
fill_labels = [int(np.argmax(sizes)) + 1]
fill_labels = [i for i in range(n_labels) if i not in fill_labels] or [int(np.argmax(sizes)) + 1]
mask = np.isin(regions, fill_labels)
return mask, True

18
ultralytics/vit/sam/modules/sam.py
View File

@ -18,14 +18,12 @@ class Sam(nn.Module):
mask_threshold: float = 0.0
image_format: str = 'RGB'
def __init__(
self,
image_encoder: ImageEncoderViT,
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],
) -> None:
def __init__(self,
image_encoder: ImageEncoderViT,
prompt_encoder: PromptEncoder,
mask_decoder: MaskDecoder,
pixel_mean: List[float] = None,
pixel_std: List[float] = None) -> None:
"""
SAM predicts object masks from an image and input prompts.
@ -38,6 +36,10 @@ class Sam(nn.Module):
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.
"""
if pixel_mean is None:
pixel_mean = [123.675, 116.28, 103.53]
if pixel_std is None:
pixel_std = [58.395, 57.12, 57.375]
super().__init__()
self.image_encoder = image_encoder
self.prompt_encoder = prompt_encoder