wehub-resource-sync
90 lines
2.4 KiB
Python
90 lines
2.4 KiB
Python
# 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.
|
|
|
|
import torch
|
|
|
|
from functools import partial
|
|
|
|
from segment_anything.modeling import ImageEncoderViT, MaskDecoder, PromptEncoder, Sam, TwoWayTransformer
|
|
from EdgeSAM.rep_vit import RepViT
|
|
|
|
|
|
prompt_embed_dim = 256
|
|
image_size = 1024
|
|
vit_patch_size = 16
|
|
image_embedding_size = image_size // vit_patch_size
|
|
|
|
|
|
def build_edge_sam(checkpoint=None, upsample_mode="bicubic"):
|
|
image_encoder = RepViT(
|
|
arch="m1",
|
|
img_size=image_size,
|
|
upsample_mode=upsample_mode
|
|
)
|
|
return _build_sam(image_encoder, checkpoint)
|
|
|
|
|
|
sam_model_registry = {
|
|
"default": build_edge_sam,
|
|
"edge_sam": build_edge_sam,
|
|
}
|
|
|
|
def _build_sam_encoder(
|
|
encoder_embed_dim,
|
|
encoder_depth,
|
|
encoder_num_heads,
|
|
encoder_global_attn_indexes,
|
|
):
|
|
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,
|
|
)
|
|
return image_encoder
|
|
|
|
|
|
def _build_sam(
|
|
image_encoder,
|
|
checkpoint=None,
|
|
):
|
|
sam = Sam(
|
|
image_encoder=image_encoder,
|
|
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],
|
|
)
|
|
sam.eval()
|
|
if checkpoint is not None:
|
|
with open(checkpoint, "rb") as f:
|
|
state_dict = torch.load(f, map_location="cpu")
|
|
sam.load_state_dict(state_dict)
|
|
return sam |