File size: 1,959 Bytes
d2a0a4e | 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 | # 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
import torch
from .modeling import ImageEncoderViT, MaskDecoder, PromptEncoder, Sam, TwoWayTransformer
def build_sam_vit_b():
image_size = 256
encoder_embed_dim = 768
encoder_depth = 12
encoder_num_heads = 12
encoder_global_attn_indexes = [2, 5, 8, 11]
encoder_adapter = True
prompt_embed_dim = 256
vit_patch_size = 16
image_embedding_size = image_size // vit_patch_size
sam = Sam(
image_encoder=ImageEncoderViT(
depth=encoder_depth,
embed_dim=encoder_embed_dim,
img_size=image_size,
mlp_ratio=4,
norm_layer=partial(torch.nn.LayerNorm, eps=1e-6),
num_heads=encoder_num_heads,
patch_size=vit_patch_size,
qkv_bias=True,
use_rel_pos = True,
global_attn_indexes=encoder_global_attn_indexes,
window_size=14,
out_chans=prompt_embed_dim,
adapter_train = encoder_adapter,
),
prompt_encoder=PromptEncoder(
embed_dim=prompt_embed_dim,
image_embedding_size=(image_embedding_size, image_embedding_size),
input_image_size=(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],
)
return sam
|