我在 ConvNext 小中添加了一个自定义层块。我想用预训练的权重来训练它，但出现错误
Traceback (most recent call last):
File "C:\Users\Ali\PycharmProjects\pythonProject1\ConvNext_Custom_FromGitHubCode.py", line 187, in <module>
model = convnext_small(pretrained=True, in_22k=False)
File "C:\Users\Ali\PycharmProjects\pythonProject1\ConvNext_Custom_FromGitHubCode.py", line 184, in convnext_small
model.load_state_dict(checkpoint["model"])
File "C:\Users\Ali\anaconda3\envs\py38\lib\site-packages\torch\nn\modules\module.py", line 1604, in load_state_dict
raise RuntimeError('Error(s) in loading state_dict for {}:\n\t{}'.format(
RuntimeError: Error(s) in loading state_dict for ConvNeXt:
Missing key(s) in state_dict: "custom_block.conv1.weight", "custom_block.conv1.bias", "custom_block.conv2.weight", "custom_block.conv2.bias", "custom_block.multihead_attention.in_proj_weight", "custom_block.multihead_attention.in_proj_bias", "custom_block.multihead_attention.out_proj.weight", "custom_block.multihead_attention.out_proj.bias", "custom_block.linear.weight", "custom_block.linear.bias".
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
# Define your custom block
class CustomBlock(nn.Module):
def __init__(self):
super(CustomBlock, self).__init__()
self.conv1 = nn.Conv2d(768, 512, kernel_size=1, padding=0)
self.conv2 = nn.Conv2d(512, 512, kernel_size=1)
self.identity = nn.Identity()
self.multihead_attention = nn.MultiheadAttention(embed_dim=512, num_heads=4)
self.linear = nn.Linear(512, 512)
self.dropout = nn.Dropout(0.2)
def forward(self, x):
x = self.conv1(x)
x = self.conv2(x)
x = self.identity(x)
x = self.multihead_attention(x, x, x)[0]
x = self.linear(x)
x = self.dropout(x)
return x
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., 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. 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.,
layer_scale_init_value=1e-6, head_init_scale=1.,
):
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.custom_block = CustomBlock() # Add your custom block
self.norm = nn.LayerNorm(dims[-1], eps=1e-6) # final norm layer
self.head = nn.Linear(dims[-1], num_classes)
self.apply(self._init_weights)
self.head.weight.data.mul_(head_init_scale)
self.head.bias.data.mul_(head_init_scale)
def _init_weights(self, m):
if isinstance(m, (nn.Conv2d, nn.Linear)):
trunc_normal_(m.weight, std=.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 = self.norm(x.mean([-2, -1])) # global average pooling, (N, C, H, W) -> (N, C)
# Add your custom block
x = self.custom_block(x)
return x
def forward(self, x):
x = self.forward_features(x)
x = self.head(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
model_urls = {
"convnext_small_1k": "https://dl.fbaipublicfiles.com/convnext/convnext_small_1k_224_ema.pth",
}
@register_model
def convnext_small(pretrained=False, in_22k=False, **kwargs):
model = ConvNeXt(depths=[3, 3, 27, 3], dims=[96, 192, 384, 768], **kwargs)
if pretrained:
url = model_urls['convnext_small_22k'] if in_22k else model_urls['convnext_small_1k']
checkpoint = torch.hub.load_state_dict_from_url(url=url, map_location="cpu")
model.load_state_dict(checkpoint["model"])
return model
model = convnext_small(pretrained=True, in_22k=False)
model.custom_block = CustomBlock()
print(model)
您可以使用
strict=Falsemodel.load_state_dict(checkpoint["model"], strict=False)
这将禁用在加载状态字典期间完成的不兼容和丢失键检查。