File size: 1,650 Bytes
2ac90ad |
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 |
# Copyright (c) Meta Platforms, Inc. and affiliates.
# All rights reserved.
# Partly revised by YZ @UCL&Moorfields
# --------------------------------------------------------
from functools import partial
import torch
import torch.nn as nn
import timm.models.vision_transformer
class VisionTransformer(timm.models.vision_transformer.VisionTransformer):
""" Vision Transformer with support for global average pooling
"""
def __init__(self, global_pool=False, **kwargs):
super(VisionTransformer, self).__init__(**kwargs)
self.global_pool = global_pool
if self.global_pool:
norm_layer = kwargs['norm_layer']
embed_dim = kwargs['embed_dim']
self.fc_norm = norm_layer(embed_dim)
del self.norm # remove the original norm
def forward_features(self, x):
B = x.shape[0]
x = self.patch_embed(x)
cls_tokens = self.cls_token.expand(B, -1, -1) # stole cls_tokens impl from Phil Wang, thanks
x = torch.cat((cls_tokens, x), dim=1)
x = x + self.pos_embed
x = self.pos_drop(x)
for blk in self.blocks:
x = blk(x)
if self.global_pool:
x = x[:, 1:, :].mean(dim=1) # global pool without cls token
outcome = self.fc_norm(x)
else:
x = self.norm(x)
outcome = x[:, 0]
return outcome
def vit_large_patch16(**kwargs):
model = VisionTransformer(
img_size=224,patch_size=16, embed_dim=1024, depth=24, num_heads=16, mlp_ratio=4, qkv_bias=True,
norm_layer=partial(nn.LayerNorm, eps=1e-6), **kwargs)
return model
|