File size: 8,431 Bytes
ca1ebdb | 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 |
# 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
import torch.nn.functional as F
from timm.models.layers import trunc_normal_, DropPath
class Block(nn.Module):
r""" ConvNeXt Block. There are two equivalent implementations:
(1) DwConv -> LayerNorm (channels_first) -> 1x1 Conv -> GELU -> 1x1 Conv; all in (N, C, H, W)
(2) DwConv -> Permute to (N, H, W, C); LayerNorm (channels_last) -> Linear -> GELU -> Linear; Permute back
We use (2) as we find it slightly faster in PyTorch
Args:
dim (int): Number of input channels.
drop_path (float): Stochastic depth rate. Default: 0.0
layer_scale_init_value (float): Init value for Layer Scale. Default: 1e-6.
"""
def __init__(self, dim, drop_path=0.0, layer_scale_init_value=1e-6):
super().__init__()
self.dwconv = nn.Conv2d(
dim, dim, kernel_size=7, padding=3, groups=dim
) # depthwise conv
self.norm = LayerNorm(dim, eps=1e-6)
self.pwconv1 = nn.Linear(
dim, 4 * dim
) # pointwise/1x1 convs, implemented with linear layers
self.act = nn.GELU()
self.pwconv2 = nn.Linear(4 * dim, dim)
self.gamma = (
nn.Parameter(layer_scale_init_value * torch.ones((dim)), requires_grad=True)
if layer_scale_init_value > 0
else None
)
self.drop_path = DropPath(drop_path) if drop_path > 0.0 else nn.Identity()
def forward(self, x):
input = x
x = self.dwconv(x)
x = x.permute(0, 2, 3, 1) # (N, C, H, W) -> (N, H, W, C)
x = self.norm(x)
x = self.pwconv1(x)
x = self.act(x)
x = self.pwconv2(x)
if self.gamma is not None:
x = self.gamma * x
x = x.permute(0, 3, 1, 2) # (N, H, W, C) -> (N, C, H, W)
x = input + self.drop_path(x)
return x
class ConvNeXt(nn.Module):
r""" ConvNeXt
A PyTorch impl of : `A ConvNet for the 2020s` -
https://arxiv.org/pdf/2201.03545.pdf
Args:
in_chans (int): Number of input image channels. Default: 3
num_classes (int): Number of classes for classification head. Default: 1000
depths (tuple(int)): Number of blocks at each stage. Default: [3, 3, 9, 3]
dims (int): Feature dimension at each stage. Default: [96, 192, 384, 768]
drop_path_rate (float): Stochastic depth rate. Default: 0.
layer_scale_init_value (float): Init value for Layer Scale. Default: 1e-6.
head_init_scale (float): Init scaling value for classifier weights and biases. Default: 1.
"""
def __init__(
self,
in_chans=3,
num_classes=1000,
depths=[3, 3, 9, 3],
dims=[96, 192, 384, 768],
drop_path_rate=0.1,
layer_scale_init_value=0.0,
head_init_scale=1.0,
):
super().__init__()
self.downsample_layers = (
nn.ModuleList()
) # stem and 3 intermediate downsampling conv layers
stem = nn.Sequential(
nn.Conv2d(in_chans, dims[0], kernel_size=4, stride=4),
LayerNorm(dims[0], eps=1e-6, data_format="channels_first"),
)
self.downsample_layers.append(stem)
for i in range(3):
downsample_layer = nn.Sequential(
LayerNorm(dims[i], eps=1e-6, data_format="channels_first"),
nn.Conv2d(dims[i], dims[i + 1], kernel_size=2, stride=2),
)
self.downsample_layers.append(downsample_layer)
self.stages = (
nn.ModuleList()
) # 4 feature resolution stages, each consisting of multiple residual blocks
dp_rates = [x.item() for x in torch.linspace(0, drop_path_rate, sum(depths))]
cur = 0
for i in range(4):
stage = nn.Sequential(
*[
Block(
dim=dims[i],
drop_path=dp_rates[cur + j],
layer_scale_init_value=layer_scale_init_value,
)
for j in range(depths[i])
]
)
self.stages.append(stage)
cur += depths[i]
self.norm = nn.LayerNorm(dims[-1], eps=1e-6) # final norm layer
self.avgpool = nn.AdaptiveAvgPool2d((1, 1))
self.apply(self._init_weights)
def _init_weights(self, m):
if isinstance(m, (nn.Conv2d, nn.Linear)):
trunc_normal_(m.weight, std=0.02)
nn.init.constant_(m.bias, 0)
def forward_features(self, x):
for i in range(4):
x = self.downsample_layers[i](x)
x = self.stages[i](x)
x = x.flatten(2, 3).permute(0, 2, 1)
x = self.norm(x)
x_avg = x.mean(dim=1)
return x, x_avg
def forward(self, x):
x = self.forward_features(x)
return x
class LayerNorm(nn.Module):
r""" LayerNorm that supports two data formats: channels_last (default) or channels_first.
The ordering of the dimensions in the inputs. channels_last corresponds to inputs with
shape (batch_size, height, width, channels) while channels_first corresponds to inputs
with shape (batch_size, channels, height, width).
"""
def __init__(self, normalized_shape, eps=1e-6, data_format="channels_last"):
super().__init__()
self.weight = nn.Parameter(torch.ones(normalized_shape))
self.bias = nn.Parameter(torch.zeros(normalized_shape))
self.eps = eps
self.data_format = data_format
if self.data_format not in ["channels_last", "channels_first"]:
raise NotImplementedError
self.normalized_shape = (normalized_shape,)
def forward(self, x):
if self.data_format == "channels_last":
return F.layer_norm(
x, self.normalized_shape, self.weight, self.bias, self.eps
)
elif self.data_format == "channels_first":
u = x.mean(1, keepdim=True)
s = (x - u).pow(2).mean(1, keepdim=True)
x = (x - u) / torch.sqrt(s + self.eps)
x = self.weight[:, None, None] * x + self.bias[:, None, None]
return x
def convnext_tiny(**kwargs):
model = ConvNeXt(depths=[3, 3, 9, 3], dims=[96, 192, 384, 768], **kwargs)
return model, 768
def convnext_small(**kwargs):
model = ConvNeXt(depths=[3, 3, 27, 3], dims=[96, 192, 384, 768], **kwargs)
return model, 768
def convnext_base(**kwargs):
model = ConvNeXt(depths=[3, 3, 27, 3], dims=[128, 256, 512, 1024], **kwargs)
return model, 1024
def convnext_large(**kwargs):
model = ConvNeXt(depths=[3, 3, 27, 3], dims=[192, 384, 768, 1536], **kwargs)
return model, 1536
def convnext_xlarge(**kwargs):
model = ConvNeXt(depths=[3, 3, 27, 3], dims=[256, 512, 1024, 2048], **kwargs)
return model, 2048
def MLP(mlp, embedding, norm_layer):
mlp_spec = f"{embedding}-{mlp}"
layers = []
f = list(map(int, mlp_spec.split("-")))
for i in range(len(f) - 2):
layers.append(nn.Linear(f[i], f[i + 1]))
if norm_layer == "batch_norm":
layers.append(nn.BatchNorm1d(f[i + 1]))
elif norm_layer == "layer_norm":
layers.append(nn.LayerNorm(f[i + 1]))
layers.append(nn.ReLU(True))
layers.append(nn.Linear(f[-2], f[-1], bias=False))
return nn.Sequential(*layers)
class ConvnextXL(torch.nn.Module):
def __init__(self, path):
super().__init__()
self.backbone, _ = convnext_xlarge()
self.maps_projector = MLP('512-512-512', 2048, 'layer_norm')
self.init_weights(path)
def init_weights(self, path):
sd = torch.load(path, map_location='cpu')['model']
for k in list(sd.keys()):
if 'module' in k:
sd[k.replace('module.', '')] = sd[k]
del sd[k]
try:
self.load_state_dict(sd, strict=False)
except:
pass
def forward(self, x):
p, _ = self.backbone(x) # b, hw, 2048
return p, self.maps_projector(p)
if __name__== "__main__":
m = ConvnextXL('../train_logs/models/convnext_xlarge_alpha0.75_fullckpt.pth')
preds = m(torch.randn(2, 3, 512, 512))
|