HongChuang/ultralytics-ascend
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity Actions 3

ultralytics 8.1.44 add IS_RASPBERRYPI and constants refactor (#9827)

Browse source 
Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Co-authored-by: UltralyticsAssistant <web@ultralytics.com>
This commit is contained in:
Glenn Jocher 2024-04-07 00:47:12 +02:00 • committed by GitHub
parent 3f34a7c3af
commit 7d891a4aa4
No known key found for this signature in database
GPG key ID: B5690EEEBB952194
43 changed files with 146 additions and 141 deletions
Download patch file Download diff file Expand all files Collapse all files

4
ultralytics/models/sam/modules/tiny_encoder.py
View file

@ -584,9 +584,9 @@ class TinyViT(nn.Module):
img_size (int, optional): The input image size. Defaults to 224.
in_chans (int, optional): Number of input channels. Defaults to 3.
num_classes (int, optional): Number of classification classes. Defaults to 1000.
embed_dims (List[int], optional): List of embedding dimensions for each layer. Defaults to [96, 192, 384, 768].
embed_dims (List[int], optional): List of embedding dimensions per layer. Defaults to [96, 192, 384, 768].
depths (List[int], optional): List of depths for each layer. Defaults to [2, 2, 6, 2].
num_heads (List[int], optional): List of number of attention heads for each layer. Defaults to [3, 6, 12, 24].
num_heads (List[int], optional): List of number of attention heads per layer. Defaults to [3, 6, 12, 24].
window_sizes (List[int], optional): List of window sizes for each layer. Defaults to [7, 7, 14, 7].
mlp_ratio (float, optional): Ratio of MLP hidden dimension to embedding dimension. Defaults to 4.
drop_rate (float, optional): Dropout rate. Defaults to 0.

2
ultralytics/models/sam/modules/transformer.py
View file

@ -222,7 +222,7 @@ class Attention(nn.Module):
downsample_rate (int, optional): The factor by which the internal dimensions are downsampled. Defaults to 1.
Raises:
AssertionError: If 'num_heads' does not evenly divide the internal dimension (embedding_dim / downsample_rate).
AssertionError: If 'num_heads' does not evenly divide the internal dim (embedding_dim / downsample_rate).
"""
super().__init__()
self.embedding_dim = embedding_dim

24
ultralytics/models/sam/predict.py
View file

@ -127,10 +127,10 @@ class Predictor(BasePredictor):
Args:
im (torch.Tensor): The preprocessed input image in tensor format, with shape (N, C, H, W).
bboxes (np.ndarray | List, optional): Bounding boxes with shape (N, 4), in XYXY format.
points (np.ndarray | List, optional): Points indicating object locations with shape (N, 2), in pixel coordinates.
labels (np.ndarray | List, optional): Labels for point prompts, shape (N, ). 1 for foreground and 0 for background.
masks (np.ndarray, optional): Low-resolution masks from previous predictions. Shape should be (N, H, W). For SAM, H=W=256.
multimask_output (bool, optional): Flag to return multiple masks. Helpful for ambiguous prompts. Defaults to False.
points (np.ndarray | List, optional): Points indicating object locations with shape (N, 2), in pixels.
labels (np.ndarray | List, optional): Labels for point prompts, shape (N, ). 1 = foreground, 0 = background.
masks (np.ndarray, optional): Low-resolution masks from previous predictions shape (N,H,W). For SAM H=W=256.
multimask_output (bool, optional): Flag to return multiple masks. Helpful for ambiguous prompts.
Returns:
(tuple): Contains the following three elements.
@ -156,10 +156,10 @@ class Predictor(BasePredictor):
Args:
im (torch.Tensor): The preprocessed input image in tensor format, with shape (N, C, H, W).
bboxes (np.ndarray | List, optional): Bounding boxes with shape (N, 4), in XYXY format.
points (np.ndarray | List, optional): Points indicating object locations with shape (N, 2), in pixel coordinates.
labels (np.ndarray | List, optional): Labels for point prompts, shape (N, ). 1 for foreground and 0 for background.
masks (np.ndarray, optional): Low-resolution masks from previous predictions. Shape should be (N, H, W). For SAM, H=W=256.
multimask_output (bool, optional): Flag to return multiple masks. Helpful for ambiguous prompts. Defaults to False.
points (np.ndarray | List, optional): Points indicating object locations with shape (N, 2), in pixels.
labels (np.ndarray | List, optional): Labels for point prompts, shape (N, ). 1 = foreground, 0 = background.
masks (np.ndarray, optional): Low-resolution masks from previous predictions shape (N,H,W). For SAM H=W=256.
multimask_output (bool, optional): Flag to return multiple masks. Helpful for ambiguous prompts.
Returns:
(tuple): Contains the following three elements.
@ -230,7 +230,7 @@ class Predictor(BasePredictor):
im (torch.Tensor): Input tensor representing the preprocessed image with dimensions (N, C, H, W).
crop_n_layers (int): Specifies the number of layers for additional mask predictions on image crops.
Each layer produces 2**i_layer number of image crops.
crop_overlap_ratio (float): Determines the extent of overlap between crops. Scaled down in subsequent layers.
crop_overlap_ratio (float): Determines the overlap between crops. Scaled down in subsequent layers.
crop_downscale_factor (int): Scaling factor for the number of sampled points-per-side in each layer.
point_grids (list[np.ndarray], optional): Custom grids for point sampling normalized to [0,1].
Used in the nth crop layer.
@ -240,7 +240,7 @@ class Predictor(BasePredictor):
conf_thres (float): Confidence threshold [0,1] for filtering based on the model's mask quality prediction.
stability_score_thresh (float): Stability threshold [0,1] for mask filtering based on mask stability.
stability_score_offset (float): Offset value for calculating stability score.
crop_nms_thresh (float): IoU cutoff for Non-Maximum Suppression (NMS) to remove duplicate masks between crops.
crop_nms_thresh (float): IoU cutoff for NMS to remove duplicate masks between crops.
Returns:
(tuple): A tuple containing segmented masks, confidence scores, and bounding boxes.
@ -351,8 +351,8 @@ class Predictor(BasePredictor):
"""
Post-processes SAM's inference outputs to generate object detection masks and bounding boxes.
The method scales masks and boxes to the original image size and applies a threshold to the mask predictions. The
SAM model uses advanced architecture and promptable segmentation tasks to achieve real-time performance.
The method scales masks and boxes to the original image size and applies a threshold to the mask predictions.
The SAM model uses advanced architecture and promptable segmentation tasks to achieve real-time performance.
Args:
preds (tuple): The output from SAM model inference, containing masks, scores, and optional bounding boxes.