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

Tests and docstrings improvements (#4475)

Browse source
This commit is contained in:
Glenn Jocher 2023-08-21 17:02:14 +02:00 • committed by GitHub
parent c659c0fa7b
commit 615ddc9d97
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
22 changed files with 107 additions and 186 deletions
Download patch file Download diff file Expand all files Collapse all files

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

@ -24,7 +24,7 @@ class MaskDecoder(nn.Module):
"""
Predicts masks given an image and prompt embeddings, using a transformer architecture.
Arguments:
Args:
transformer_dim (int): the channel dimension of the transformer module
transformer (nn.Module): the transformer used to predict masks
num_multimask_outputs (int): the number of masks to predict when disambiguating masks
@ -65,7 +65,7 @@ class MaskDecoder(nn.Module):
"""
Predict masks given image and prompt embeddings.
Arguments:
Args:
image_embeddings (torch.Tensor): the embeddings from the image encoder
image_pe (torch.Tensor): positional encoding with the shape of image_embeddings
sparse_prompt_embeddings (torch.Tensor): the embeddings of the points and boxes