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

ultralytics 8.0.239 Ultralytics Actions and hub-sdk adoption (#7431)

Browse source 
Signed-off-by: Glenn Jocher <glenn.jocher@ultralytics.com>
Co-authored-by: UltralyticsAssistant <web@ultralytics.com>
Co-authored-by: Burhan <62214284+Burhan-Q@users.noreply.github.com>
Co-authored-by: Kayzwer <68285002+Kayzwer@users.noreply.github.com>
This commit is contained in:
Glenn Jocher 2024-01-10 03:16:08 +01:00 • committed by GitHub
parent e795277391
commit fe27db2f6e
No known key found for this signature in database
GPG key ID: 4AEE18F83AFDEB23
139 changed files with 6870 additions and 5125 deletions
Download patch file Download diff file Expand all files Collapse all files

10
ultralytics/models/sam/modules/decoders.py
View file

@ -64,8 +64,9 @@ class MaskDecoder(nn.Module):
nn.ConvTranspose2d(transformer_dim // 4, transformer_dim // 8, kernel_size=2, stride=2),
activation(),
)
self.output_hypernetworks_mlps = nn.ModuleList([
MLP(transformer_dim, transformer_dim, transformer_dim // 8, 3) for _ in range(self.num_mask_tokens)])
self.output_hypernetworks_mlps = nn.ModuleList(
[MLP(transformer_dim, transformer_dim, transformer_dim // 8, 3) for _ in range(self.num_mask_tokens)]
)
self.iou_prediction_head = MLP(transformer_dim, iou_head_hidden_dim, self.num_mask_tokens, iou_head_depth)
@ -132,13 +133,14 @@ class MaskDecoder(nn.Module):
# Run the transformer
hs, src = self.transformer(src, pos_src, tokens)
iou_token_out = hs[:, 0, :]
mask_tokens_out = hs[:, 1:(1 + self.num_mask_tokens), :]
mask_tokens_out = hs[:, 1 : (1 + self.num_mask_tokens), :]
# Upscale mask embeddings and predict masks using the mask tokens
src = src.transpose(1, 2).view(b, c, h, w)
upscaled_embedding = self.output_upscaling(src)
hyper_in_list: List[torch.Tensor] = [
self.output_hypernetworks_mlps[i](mask_tokens_out[:, i, :]) for i in range(self.num_mask_tokens)]
self.output_hypernetworks_mlps[i](mask_tokens_out[:, i, :]) for i in range(self.num_mask_tokens)
]
hyper_in = torch.stack(hyper_in_list, dim=1)
b, c, h, w = upscaled_embedding.shape
masks = (hyper_in @ upscaled_embedding.view(b, c, h * w)).view(b, -1, h, w)