Spaces:
Running
Running
File size: 11,472 Bytes
b36de75 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289 290 291 292 293 294 295 296 297 298 299 300 301 302 303 304 305 306 307 308 309 310 311 312 313 |
"""
MambaOut models for image classification.
Some implementations are modified from:
timm (https://github.com/rwightman/pytorch-image-models),
MetaFormer (https://github.com/sail-sg/metaformer),
InceptionNeXt (https://github.com/sail-sg/inceptionnext)
"""
from functools import partial
import torch
import torch.nn as nn
import torch.nn.functional as F
from timm.models.layers import trunc_normal_, DropPath
from timm.models.registry import register_model
from timm.data import IMAGENET_DEFAULT_MEAN, IMAGENET_DEFAULT_STD
def _cfg(url='', **kwargs):
return {
'url': url,
'num_classes': 1000, 'input_size': (3, 224, 224), 'pool_size': None,
'crop_pct': 1.0, 'interpolation': 'bicubic',
'mean': IMAGENET_DEFAULT_MEAN, 'std': IMAGENET_DEFAULT_STD, 'classifier': 'head',
**kwargs
}
default_cfgs = {
'mambaout_femto': _cfg(
url='https://github.com/yuweihao/MambaOut/releases/download/model/mambaout_femto.pth'),
'mambaout_tiny': _cfg(
url='https://github.com/yuweihao/MambaOut/releases/download/model/mambaout_tiny.pth'),
'mambaout_small': _cfg(
url='https://github.com/yuweihao/MambaOut/releases/download/model/mambaout_small.pth'),
'mambaout_base': _cfg(
url='https://github.com/yuweihao/MambaOut/releases/download/model/mambaout_base.pth'),
}
class StemLayer(nn.Module):
r""" Code modified from InternImage:
https://github.com/OpenGVLab/InternImage
"""
def __init__(self,
in_channels=3,
out_channels=96,
act_layer=nn.GELU,
norm_layer=partial(nn.LayerNorm, eps=1e-6)):
super().__init__()
self.conv1 = nn.Conv2d(in_channels,
out_channels // 2,
kernel_size=3,
stride=2,
padding=1)
self.norm1 = norm_layer(out_channels // 2)
self.act = act_layer()
self.conv2 = nn.Conv2d(out_channels // 2,
out_channels,
kernel_size=3,
stride=2,
padding=1)
self.norm2 = norm_layer(out_channels)
def forward(self, x):
x = self.conv1(x)
x = x.permute(0, 2, 3, 1)
x = self.norm1(x)
x = x.permute(0, 3, 1, 2)
x = self.act(x)
x = self.conv2(x)
x = x.permute(0, 2, 3, 1)
x = self.norm2(x)
return x
class DownsampleLayer(nn.Module):
r""" Code modified from InternImage:
https://github.com/OpenGVLab/InternImage
"""
def __init__(self, in_channels=96, out_channels=198, norm_layer=partial(nn.LayerNorm, eps=1e-6)):
super().__init__()
self.conv = nn.Conv2d(in_channels,
out_channels,
kernel_size=3,
stride=2,
padding=1)
self.norm = norm_layer(out_channels)
def forward(self, x):
x = self.conv(x.permute(0, 3, 1, 2)).permute(0, 2, 3, 1)
x = self.norm(x)
return x
class MlpHead(nn.Module):
""" MLP classification head
"""
def __init__(self, dim, num_classes=1000, act_layer=nn.GELU, mlp_ratio=4,
norm_layer=partial(nn.LayerNorm, eps=1e-6), head_dropout=0., bias=True):
super().__init__()
hidden_features = int(mlp_ratio * dim)
self.fc1 = nn.Linear(dim, hidden_features, bias=bias)
self.act = act_layer()
self.norm = norm_layer(hidden_features)
self.fc2 = nn.Linear(hidden_features, num_classes, bias=bias)
self.head_dropout = nn.Dropout(head_dropout)
def forward(self, x):
x = self.fc1(x)
x = self.act(x)
x = self.norm(x)
x = self.head_dropout(x)
x = self.fc2(x)
return x
class GatedCNNBlock(nn.Module):
r""" Our implementation of Gated CNN Block: https://arxiv.org/pdf/1612.08083
Args:
conv_ratio: control the number of channels to conduct depthwise convolution.
Conduct convolution on partial channels can improve paraitcal efficiency.
The idea of partical channels is from ShuffleNet V2 (https://arxiv.org/abs/1807.11164) and
also used by InceptionNeXt (https://arxiv.org/abs/2303.16900) and FasterNet (https://arxiv.org/abs/2303.03667)
"""
def __init__(self, dim, expension_ratio=8/3, kernel_size=7, conv_ratio=1.0,
norm_layer=partial(nn.LayerNorm,eps=1e-6),
act_layer=nn.GELU,
drop_path=0.,
**kwargs):
super().__init__()
self.norm = norm_layer(dim)
hidden = int(expension_ratio * dim)
self.fc1 = nn.Linear(dim, hidden * 2)
self.act = act_layer()
conv_channels = int(conv_ratio * dim)
self.split_indices = (hidden, hidden - conv_channels, conv_channels)
self.conv = nn.Conv2d(conv_channels, conv_channels, kernel_size=kernel_size, padding=kernel_size//2, groups=conv_channels)
self.fc2 = nn.Linear(hidden, dim)
self.drop_path = DropPath(drop_path) if drop_path > 0. else nn.Identity()
def forward(self, x):
shortcut = x # [B, H, W, C]
x = self.norm(x)
g, i, c = torch.split(self.fc1(x), self.split_indices, dim=-1)
c = c.permute(0, 3, 1, 2) # [B, H, W, C] -> [B, C, H, W]
c = self.conv(c)
c = c.permute(0, 2, 3, 1) # [B, C, H, W] -> [B, H, W, C]
x = self.fc2(self.act(g) * torch.cat((i, c), dim=-1))
x = self.drop_path(x)
return x + shortcut
r"""
downsampling (stem) for the first stage is two layer of conv with k3, s2 and p1
downsamplings for the last 3 stages is a layer of conv with k3, s2 and p1
DOWNSAMPLE_LAYERS_FOUR_STAGES format: [Downsampling, Downsampling, Downsampling, Downsampling]
use `partial` to specify some arguments
"""
DOWNSAMPLE_LAYERS_FOUR_STAGES = [StemLayer] + [DownsampleLayer]*3
class MambaOut(nn.Module):
r""" MetaFormer
A PyTorch impl of : `MetaFormer Baselines for Vision` -
https://arxiv.org/abs/2210.13452
Args:
in_chans (int): Number of input image channels. Default: 3.
num_classes (int): Number of classes for classification head. Default: 1000.
depths (list or tuple): Number of blocks at each stage. Default: [3, 3, 9, 3].
dims (int): Feature dimension at each stage. Default: [96, 192, 384, 576].
downsample_layers: (list or tuple): Downsampling layers before each stage.
drop_path_rate (float): Stochastic depth rate. Default: 0.
output_norm: norm before classifier head. Default: partial(nn.LayerNorm, eps=1e-6).
head_fn: classification head. Default: nn.Linear.
head_dropout (float): dropout for MLP classifier. Default: 0.
"""
def __init__(self, in_chans=3, num_classes=1000,
depths=[3, 3, 9, 3],
dims=[96, 192, 384, 576],
downsample_layers=DOWNSAMPLE_LAYERS_FOUR_STAGES,
norm_layer=partial(nn.LayerNorm, eps=1e-6),
act_layer=nn.GELU,
conv_ratio=1.0,
kernel_size=7,
drop_path_rate=0.,
output_norm=partial(nn.LayerNorm, eps=1e-6),
head_fn=MlpHead,
head_dropout=0.0,
**kwargs,
):
super().__init__()
self.num_classes = num_classes
if not isinstance(depths, (list, tuple)):
depths = [depths] # it means the model has only one stage
if not isinstance(dims, (list, tuple)):
dims = [dims]
num_stage = len(depths)
self.num_stage = num_stage
if not isinstance(downsample_layers, (list, tuple)):
downsample_layers = [downsample_layers] * num_stage
down_dims = [in_chans] + dims
self.downsample_layers = nn.ModuleList(
[downsample_layers[i](down_dims[i], down_dims[i+1]) for i in range(num_stage)]
)
dp_rates=[x.item() for x in torch.linspace(0, drop_path_rate, sum(depths))]
self.stages = nn.ModuleList()
cur = 0
for i in range(num_stage):
stage = nn.Sequential(
*[GatedCNNBlock(dim=dims[i],
norm_layer=norm_layer,
act_layer=act_layer,
kernel_size=kernel_size,
conv_ratio=conv_ratio,
drop_path=dp_rates[cur + j],
) for j in range(depths[i])]
)
self.stages.append(stage)
cur += depths[i]
self.norm = output_norm(dims[-1])
if head_dropout > 0.0:
self.head = head_fn(dims[-1], num_classes, head_dropout=head_dropout)
else:
self.head = head_fn(dims[-1], num_classes)
self.apply(self._init_weights)
def _init_weights(self, m):
if isinstance(m, (nn.Conv2d, nn.Linear)):
trunc_normal_(m.weight, std=.02)
if m.bias is not None:
nn.init.constant_(m.bias, 0)
@torch.jit.ignore
def no_weight_decay(self):
return {'norm'}
def forward_features(self, x):
for i in range(self.num_stage):
x = self.downsample_layers[i](x)
x = self.stages[i](x)
return self.norm(x.mean([1, 2])) # (B, H, W, C) -> (B, C)
def forward(self, x):
x = self.forward_features(x)
x = self.head(x)
return x
###############################################################################
# a series of MambaOut models
@register_model
def mambaout_femto(pretrained=False, **kwargs):
model = MambaOut(
depths=[3, 3, 9, 3],
dims=[48, 96, 192, 288],
**kwargs)
model.default_cfg = default_cfgs['mambaout_femto']
if pretrained:
state_dict = torch.hub.load_state_dict_from_url(
url= model.default_cfg['url'], map_location="cpu", check_hash=True)
model.load_state_dict(state_dict)
return model
@register_model
def mambaout_tiny(pretrained=False, **kwargs):
model = MambaOut(
depths=[3, 3, 9, 3],
dims=[96, 192, 384, 576],
**kwargs)
model.default_cfg = default_cfgs['mambaout_tiny']
if pretrained:
state_dict = torch.hub.load_state_dict_from_url(
url= model.default_cfg['url'], map_location="cpu", check_hash=True)
model.load_state_dict(state_dict)
return model
@register_model
def mambaout_small(pretrained=False, **kwargs):
model = MambaOut(
depths=[3, 4, 27, 3],
dims=[96, 192, 384, 576],
**kwargs)
model.default_cfg = default_cfgs['mambaout_small']
if pretrained:
state_dict = torch.hub.load_state_dict_from_url(
url= model.default_cfg['url'], map_location="cpu", check_hash=True)
model.load_state_dict(state_dict)
return model
@register_model
def mambaout_base(pretrained=False, **kwargs):
model = MambaOut(
depths=[3, 4, 27, 3],
dims=[128, 256, 512, 768],
**kwargs)
model.default_cfg = default_cfgs['mambaout_base']
if pretrained:
state_dict = torch.hub.load_state_dict_from_url(
url= model.default_cfg['url'], map_location="cpu", check_hash=True)
model.load_state_dict(state_dict)
return model |