Image Segmentation
kornia
segment-anything
ducha-aiki commited on
Commit
b6e8348
·
verified ·
1 Parent(s): faebcab

Card: list sam_vit_h_4b8939.safetensors with provenance

Browse files
Files changed (1) hide show
  1. README.md +2 -0
README.md CHANGED
@@ -21,6 +21,7 @@ encoder and mask decoder.
21
  |------|---------------|
22
  | `sam_vit_b_01ec64.safetensors` | ViT-B |
23
  | `sam_vit_l_0b3195.safetensors` | ViT-L |
 
24
 
25
  ## Provenance
26
 
@@ -32,6 +33,7 @@ from either file has a bitwise-identical `state_dict()` and gives bitwise-identi
32
  |------|-----------------|---------------|--------|
33
  | `sam_vit_b_01ec64.safetensors` | [`sam_vit_b_01ec64.pth`](https://dl.fbaipublicfiles.com/segment_anything/sam_vit_b_01ec64.pth) | `ec2df62732614e57411cdcf32a23ffdf28910380d03139ee0f4fcbe91eb8c912` | `fbf4c1ad844a2e9b867d89dc04a61f3ece19c57ebb7d8fcb6da92062a291d839` |
34
  | `sam_vit_l_0b3195.safetensors` | [`sam_vit_l_0b3195.pth`](https://dl.fbaipublicfiles.com/segment_anything/sam_vit_l_0b3195.pth) | `3adcc4315b642a4d2101128f611684e8734c41232a17c648ed1693702a49a622` | `8e087bc0db5cfac2676ae69bb1b846fa1f6cc193fc0beb6be8fb14fc7406be41` |
 
35
 
36
  The upstream ViT-B and ViT-L checkpoints store `mask_decoder.iou_token.weight` and `mask_decoder.mask_tokens.weight` as views
37
  of one shared storage. The safetensors format forbids shared storage, so each is stored as its own copy with identical
 
21
  |------|---------------|
22
  | `sam_vit_b_01ec64.safetensors` | ViT-B |
23
  | `sam_vit_l_0b3195.safetensors` | ViT-L |
24
+ | `sam_vit_h_4b8939.safetensors` | ViT-H |
25
 
26
  ## Provenance
27
 
 
33
  |------|-----------------|---------------|--------|
34
  | `sam_vit_b_01ec64.safetensors` | [`sam_vit_b_01ec64.pth`](https://dl.fbaipublicfiles.com/segment_anything/sam_vit_b_01ec64.pth) | `ec2df62732614e57411cdcf32a23ffdf28910380d03139ee0f4fcbe91eb8c912` | `fbf4c1ad844a2e9b867d89dc04a61f3ece19c57ebb7d8fcb6da92062a291d839` |
35
  | `sam_vit_l_0b3195.safetensors` | [`sam_vit_l_0b3195.pth`](https://dl.fbaipublicfiles.com/segment_anything/sam_vit_l_0b3195.pth) | `3adcc4315b642a4d2101128f611684e8734c41232a17c648ed1693702a49a622` | `8e087bc0db5cfac2676ae69bb1b846fa1f6cc193fc0beb6be8fb14fc7406be41` |
36
+ | `sam_vit_h_4b8939.safetensors` | [`sam_vit_h_4b8939.pth`](https://dl.fbaipublicfiles.com/segment_anything/sam_vit_h_4b8939.pth) | `a7bf3b02f3ebf1267aba913ff637d9a2d5c33d3173bb679e46d9f338c26f262e` | `1424ffbab6fa8218aeae5abb931549dcd2d68725220ed14a5d1b579aa503c3e7` |
37
 
38
  The upstream ViT-B and ViT-L checkpoints store `mask_decoder.iou_token.weight` and `mask_decoder.mask_tokens.weight` as views
39
  of one shared storage. The safetensors format forbids shared storage, so each is stored as its own copy with identical