Spaces:
Running
Running
File size: 6,075 Bytes
a950ee6 |
1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 59 60 61 62 63 64 65 66 67 68 69 70 71 72 73 74 75 76 77 78 79 80 81 82 83 84 85 86 87 88 89 90 91 92 93 94 95 96 97 98 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 |
# Copyright (c) Meta Platforms, Inc. and affiliates.
# All rights reserved.
# This source code is licensed under the license found in the
# LICENSE file in the root directory of this source tree.
from functools import partial
from pathlib import Path
import urllib.request
import torch
from .modeling import (
ImageEncoderViT,
MaskDecoder,
PromptEncoder,
Sam,
TwoWayTransformer,
)
from .modeling.image_encoder_swin import SwinTransformer
from monai.utils import ensure_tuple_rep, optional_import
def build_sam_vit_h(checkpoint=None, image_size=1024):
return _build_sam(
encoder_embed_dim=1280,
encoder_depth=32,
encoder_num_heads=16,
encoder_global_attn_indexes=[7, 15, 23, 31],
checkpoint=checkpoint,
image_size=image_size,
)
build_sam = build_sam_vit_h
def build_sam_vit_l(checkpoint=None, image_size=1024):
return _build_sam(
encoder_embed_dim=1024,
encoder_depth=24,
encoder_num_heads=16,
encoder_global_attn_indexes=[5, 11, 17, 23],
checkpoint=checkpoint,
image_size=image_size,
)
def build_sam_vit_b(checkpoint=None, image_size=1024):
return _build_sam(
encoder_embed_dim=768,
encoder_depth=12,
encoder_num_heads=12,
encoder_global_attn_indexes=[2, 5, 8, 11],
checkpoint=checkpoint,
image_size=image_size,
)
"""
Examples::
# for 3D single channel input with size (96,96,96), 4-channel output and feature size of 48.
>>> net = SwinUNETR(img_size=(96,96,96), in_channels=1, out_channels=4, feature_size=48)
# for 3D 4-channel input with size (128,128,128), 3-channel output and (2,4,2,2) layers in each stage.
>>> net = SwinUNETR(img_size=(128,128,128), in_channels=4, out_channels=3, depths=(2,4,2,2))
# for 2D single channel input with size (96,96), 2-channel output and gradient checkpointing.
>>> net = SwinUNETR(img_size=(96,96), in_channels=3, out_channels=2, use_checkpoint=True, spatial_dims=2)
"""
def build_sam_vit_swin(checkpoint=None, image_size=96):
print('==> build_sam_vit_swin')
return _build_sam(
encoder_embed_dim=48,
encoder_depth=12,
encoder_num_heads=12,
encoder_global_attn_indexes=[2, 5, 8, 11],
checkpoint=checkpoint,
image_size=image_size,
)
sam_model_registry = {
"default": build_sam_vit_h,
"vit_h": build_sam_vit_h,
"vit_l": build_sam_vit_l,
"vit_b": build_sam_vit_b,
"swin_vit": build_sam_vit_swin,
}
def _build_sam(
encoder_embed_dim,
encoder_depth,
encoder_num_heads,
encoder_global_attn_indexes,
checkpoint=None,
image_size=None,
spatial_dims=3,
):
prompt_embed_dim = 768
patch_size = ensure_tuple_rep(2, spatial_dims)
window_size = ensure_tuple_rep(7, spatial_dims)
image_embedding_size = [size // 32 for size in image_size]
sam = Sam(
image_encoder=SwinTransformer(
in_chans=1,
embed_dim=encoder_embed_dim,
window_size=window_size,
patch_size=patch_size,
depths=(2, 2, 6, 2), #(2, 2, 6, 2),
num_heads=(3, 6, 12, 24),
mlp_ratio=4.0,
qkv_bias=True,
spatial_dims=spatial_dims,
),
prompt_encoder=PromptEncoder(
embed_dim=prompt_embed_dim,
image_embedding_size=image_embedding_size,
input_image_size=image_size,
mask_in_chans=16,
),
mask_decoder=MaskDecoder(
num_multimask_outputs=3,
transformer=TwoWayTransformer(
depth=2,
embedding_dim=prompt_embed_dim,
mlp_dim=2048,
num_heads=8,
),
transformer_dim=prompt_embed_dim,
iou_head_depth=3,
iou_head_hidden_dim=256,
),
pixel_mean=[123.675, 116.28, 103.53],
pixel_std=[58.395, 57.12, 57.375],
)
sam.eval()
if checkpoint is not None:
checkpoint = Path(checkpoint)
if checkpoint.name == "sam_vit_b_01ec64.pth" and not checkpoint.exists():
cmd = input("Download sam_vit_b_01ec64.pth from facebook AI? [y]/n: ")
if len(cmd) == 0 or cmd.lower() == 'y':
checkpoint.parent.mkdir(parents=True, exist_ok=True)
print("Downloading SAM ViT-B checkpoint...")
urllib.request.urlretrieve(
"https://dl.fbaipublicfiles.com/segment_anything/sam_vit_b_01ec64.pth",
checkpoint,
)
print(checkpoint.name, " is downloaded!")
elif checkpoint.name == "sam_vit_h_4b8939.pth" and not checkpoint.exists():
cmd = input("Download sam_vit_h_4b8939.pth from facebook AI? [y]/n: ")
if len(cmd) == 0 or cmd.lower() == 'y':
checkpoint.parent.mkdir(parents=True, exist_ok=True)
print("Downloading SAM ViT-H checkpoint...")
urllib.request.urlretrieve(
"https://dl.fbaipublicfiles.com/segment_anything/sam_vit_h_4b8939.pth",
checkpoint,
)
print(checkpoint.name, " is downloaded!")
elif checkpoint.name == "sam_vit_l_0b3195.pth" and not checkpoint.exists():
cmd = input("Download sam_vit_l_0b3195.pth from facebook AI? [y]/n: ")
if len(cmd) == 0 or cmd.lower() == 'y':
checkpoint.parent.mkdir(parents=True, exist_ok=True)
print("Downloading SAM ViT-L checkpoint...")
urllib.request.urlretrieve(
"https://dl.fbaipublicfiles.com/segment_anything/sam_vit_l_0b3195.pth",
checkpoint,
)
print(checkpoint.name, " is downloaded!")
if checkpoint is not None:
with open(checkpoint, "rb") as f:
state_dict = torch.load(f)
sam.load_state_dict(state_dict)
return sam
|