File size: 2,906 Bytes
be2715b |
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 |
# 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
import torch.nn as nn
from functools import partial
import torch.nn.functional as F
from typing import Optional, Tuple, Type
from .modeling import ImageEncoderViT
def vit_encoder_l():
prompt_embed_dim = 256
image_size = 1024
vit_patch_size = 16
image_embedding_size = image_size // vit_patch_size
encoder_embed_dim=1024
encoder_depth=24
encoder_num_heads=16
encoder_global_attn_indexes=[5, 11, 17, 23]
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,
use_abs_pos = False,
global_attn_indexes=encoder_global_attn_indexes,
window_size=14,
out_chans=prompt_embed_dim,
)
return image_encoder
def vit_encoder_b():
prompt_embed_dim = 256
image_size = 1024
vit_patch_size = 16
image_embedding_size = image_size // vit_patch_size
encoder_embed_dim=768
encoder_depth=12
encoder_num_heads=12
encoder_global_attn_indexes=[2, 5, 8, 11]
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,
use_abs_pos = False,
global_attn_indexes=encoder_global_attn_indexes,
window_size=14,
out_chans=prompt_embed_dim,
)
return image_encoder
def vit_encoder_h():
prompt_embed_dim = 256
image_size = 1024
vit_patch_size = 16
image_embedding_size = image_size // vit_patch_size
encoder_embed_dim=1280
encoder_depth=32
encoder_num_heads=16
encoder_global_attn_indexes=[7, 15, 23, 31]
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,
use_abs_pos = False,
global_attn_indexes=encoder_global_attn_indexes,
window_size=14,
out_chans=prompt_embed_dim,
)
return image_encoder
|