open-cd
该开源库基于：
mmcv
mmseg
mmdet
mmengine
1.安装
在安装过程中遇到的问题：
1.pytorch版本问题，open-cd采用的mmcv版本比较低，建议安装2.3以下版本pytorch，太高了mmcv可能不太适配，先安装pytorch，在安装mmcv，我在安装时用的版本
pytorch 2.1.2 py3.9_cuda12.1_cudnn8_0 pytorch
mmcv 2.1.0 pypi_0 pypi
mmcv安装方式
该方式同样适用于解决：
note: This error originates from a subprocess, and is likely not a problem with pip.
ERROR: Failed building wheel for mmcv
Running setup.py clean for mmcv
Failed to build mmcv
ERROR: ERROR: Failed to build installable wheels for some pyproject.toml based projects (mmcv)
之后参照博主的的安装步骤安装opencd的开原文件即可(建议安装源文件，直接 opencd第三方包形式后期不方便调试)：
# Install OpenMMLab Toolkits as Python packages
pip install -U openmim
mim install mmengine
mim install "mmpretrain>=1.0.0rc7"
pip install "mmsegmentation>=1.2.2"
pip install "mmdet>=3.0.0"
# Install Opencd
git clone https://github.com/likyoo/open-cd.git
cd open-cd
pip install -v -e .
2.源码结构分析
该库主要的文件时1.config参数文件，2.opencd模型架构文件，3.训练推理分析工具，4.mmlab
这里主要介绍2.opencd模型框架文件,文件下包含：
其中，model文件夹下包含模型结构基础文件：
变化检测大致遵循语义分割的编码结构、neck结构、以及解码结构。
如果使用过mmsegmentation机会发现，backbone中存放着雨参数文件对应的主干网络，相应的是neck，decoder，这里changer_detector里面是主要的模型架构如Encoder-Decoder。
open-cd与mmseg这类参数化的文件非常适合进行模型复现或者进行工程化应用；但对一些科研小白，特别是非计算机专业的科研小白需要改进网络就不太友好；这里直观的作用下模型架构的组合使用，方便大家理解和魔改（~~别越看越迷糊就行）
这里以changerformer-mitb0为例：
前提是已完成open-cd的安装官方issue
下面内容摘自opencd/model/
删除每个类前面的注册表装饰器 @MODELS.register_module()，报错提示类已注册
主干网络
# Copyright (c) OpenMMLab. All rights reserved.
import math
import warnings
import torch
import torch.nn as nn
import torch.utils.checkpoint as cp
from mmcv.cnn import Conv2d, build_activation_layer, build_norm_layer
from mmcv.cnn.bricks.drop import build_dropout
from mmcv.cnn.bricks.transformer import MultiheadAttention
from mmengine.model import BaseModule, ModuleList, Sequential
from mmengine.model.weight_init import (constant_init, normal_init,
trunc_normal_init)
from mmseg.registry import MODELS
## 下面两个依赖在opencd/model/utils中可以找到
from .embed import PatchEmbed
from .shape_convert import nchw_to_nlc, nlc_to_nchw
class MixFFN(BaseModule):
"""An implementation of MixFFN of Segformer.
The differences between MixFFN & FFN:
1. Use 1X1 Conv to replace Linear layer.
2. Introduce 3X3 Conv to encode positional information.
Args:
embed_dims (int): The feature dimension. Same as
`MultiheadAttention`. Defaults: 256.
feedforward_channels (int): The hidden dimension of FFNs.
Defaults: 1024.
act_cfg (dict, optional): The activation config for FFNs.
Default: dict(type='ReLU')
ffn_drop (float, optional): Probability of an element to be
zeroed in FFN. Default 0.0.
dropout_layer (obj:`ConfigDict`): The dropout_layer used
when adding the shortcut.
init_cfg (obj:`mmcv.ConfigDict`): The Config for initialization.
Default: None.
"""
def __init__(self,
embed_dims,
feedforward_channels,
act_cfg=dict(type='GELU'),
ffn_drop=0.,
dropout_layer=None,
init_cfg=None):
super().__init__(init_cfg)
self.embed_dims = embed_dims
self.feedforward_channels = feedforward_channels
self.act_cfg = act_cfg
self.activate = build_activation_layer(act_cfg)
in_channels = embed_dims
fc1 = Conv2d(
in_channels=in_channels,
out_channels=feedforward_channels,
kernel_size=1,
stride=1,
bias=True)
# 3x3 depth wise conv to provide positional encode information
pe_conv = Conv2d(
in_channels=feedforward_channels,
out_channels=feedforward_channels,
kernel_size=3,
stride=1,
padding=(3 - 1) // 2,
bias=True,
groups=feedforward_channels)
fc2 = Conv2d(
in_channels=feedforward_channels,
out_channels=in_channels,
kernel_size=1,
stride=1,
bias=True)
drop = nn.Dropout(ffn_drop)
layers = [fc1, pe_conv, self.activate, drop, fc2, drop]
self.layers = Sequential(*layers)
self.dropout_layer = build_dropout(
dropout_layer) if dropout_layer else torch.nn.Identity()
def forward(self, x, hw_shape, identity=None):
out = nlc_to_nchw(x, hw_shape)
out = self.layers(out)
out = nchw_to_nlc(out)
if identity is None:
identity = x
return identity + self.dropout_layer(out)
class EfficientMultiheadAttention(MultiheadAttention):
"""An implementation of Efficient Multi-head Attention of Segformer.
This module is modified from MultiheadAttention which is a module from
mmcv.cnn.bricks.transformer.
Args:
embed_dims (int): The embedding dimension.
num_heads (int): Parallel attention heads.
attn_drop (float): A Dropout layer on attn_output_weights.
Default: 0.0.
proj_drop (float): A Dropout layer after `nn.MultiheadAttention`.
Default: 0.0.
dropout_layer (obj:`ConfigDict`): The dropout_layer used
when adding the shortcut. Default: None.
init_cfg (obj:`mmcv.ConfigDict`): The Config for initialization.
Default: None.
batch_first (bool): Key, Query and Value are shape of
(batch, n, embed_dim)
or (n, batch, embed_dim). Default: False.
qkv_bias (bool): enable bias for qkv if True. Default True.
norm_cfg (dict): Config dict for normalization layer.
Default: dict(type='LN').
sr_ratio (int): The ratio of spatial reduction of Efficient Multi-head
Attention of Segformer. Default: 1.
"""
def __init__(self,
embed_dims,
num_heads,
attn_drop=0.,
proj_drop=0.,
dropout_layer=None,
init_cfg=None,
batch_first=True,
qkv_bias=False,
norm_cfg=dict(type='LN'),
sr_ratio=1):
super().__init__(
embed_dims,
num_heads,
attn_drop,
proj_drop,
dropout_layer=dropout_layer,
init_cfg=init_cfg,
batch_first=batch_first,
bias=qkv_bias)
self.sr_ratio = sr_ratio
if sr_ratio > 1:
self.sr = Conv2d(
in_channels=embed_dims,
out_channels=embed_dims,
kernel_size=sr_ratio,
stride=sr_ratio)
# The ret[0] of build_norm_layer is norm name.
self.norm = build_norm_layer(norm_cfg, embed_dims)[1]
# handle the BC-breaking from https://github.com/open-mmlab/mmcv/pull/1418 # noqa
from mmseg import digit_version, mmcv_version
if mmcv_version < digit_version('1.3.17'):
warnings.warn('The legacy version of forward function in'
'EfficientMultiheadAttention is deprecated in'
'mmcv>=1.3.17 and will no longer support in the'
'future. Please upgrade your mmcv.')
self.forward = self.legacy_forward
def forward(self, x, hw_shape, identity=None):
x_q = x
if self.sr_ratio > 1:
x_kv = nlc_to_nchw(x, hw_shape)
x_kv = self.sr(x_kv)
x_kv = nchw_to_nlc(x_kv)
x_kv = self.norm(x_kv)
else:
x_kv = x
if identity is None:
identity = x_q
# Because the dataflow('key', 'query', 'value') of
# ``torch.nn.MultiheadAttention`` is (num_query, batch,
# embed_dims), We should adjust the shape of dataflow from
# batch_first (batch, num_query, embed_dims) to num_query_first
# (num_query ,batch, embed_dims), and recover ``attn_output``
# from num_query_first to batch_first.
if self.batch_first:
x_q = x_q.transpose(0, 1)
x_kv = x_kv.transpose(0, 1)
out = self.attn(query=x_q, key=x_kv, value=x_kv)[0]
if self.batch_first:
out = out.transpose(0, 1)
return identity + self.dropout_layer(self.proj_drop(out))
def legacy_forward(self, x, hw_shape, identity=None):
"""multi head attention forward in mmcv version < 1.3.17."""
x_q = x
if self.sr_ratio > 1:
x_kv = nlc_to_nchw(x, hw_shape)
x_kv = self.sr(x_kv)
x_kv = nchw_to_nlc(x_kv)
x_kv = self.norm(x_kv)
else:
x_kv = x
if identity is None:
identity = x_q
# `need_weights=True` will let nn.MultiHeadAttention
# `return attn_output, attn_output_weights.sum(dim=1) / num_heads`
# The `attn_output_weights.sum(dim=1)` may cause cuda error. So, we set
# `need_weights=False` to ignore `attn_output_weights.sum(dim=1)`.
# This issue - `https://github.com/pytorch/pytorch/issues/37583` report
# the error that large scale tensor sum operation may cause cuda error.
out = self.attn(query=x_q, key=x_kv, value=x_kv, need_weights=False)[0]
return identity + self.dropout_layer(self.proj_drop(out))
class TransformerEncoderLayer(BaseModule):
"""Implements one encoder layer in Segformer.
Args:
embed_dims (int): The feature dimension.
num_heads (int): Parallel attention heads.
feedforward_channels (int): The hidden dimension for FFNs.
drop_rate (float): Probability of an element to be zeroed.
after the feed forward layer. Default 0.0.
attn_drop_rate (float): The drop out rate for attention layer.
Default 0.0.
drop_path_rate (float): stochastic depth rate. Default 0.0.
qkv_bias (bool): enable bias for qkv if True.
Default: True.
act_cfg (dict): The activation config for FFNs.
Default: dict(type='GELU').
norm_cfg (dict): Config dict for normalization layer.
Default: dict(type='LN').
batch_first (bool): Key, Query and Value are shape of
(batch, n, embed_dim)
or (n, batch, embed_dim). Default: False.
init_cfg (dict, optional): Initialization config dict.
Default:None.
sr_ratio (int): The ratio of spatial reduction of Efficient Multi-head
Attention of Segformer. Default: 1.
with_cp (bool): Use checkpoint or not. Using checkpoint will save
some memory while slowing down the training speed. Default: False.
"""
def __init__(self,
embed_dims,
num_heads,
feedforward_channels,
drop_rate=0
最低0.47元/天 解锁文章
扫一扫
被折叠的 条评论
为什么被折叠?
到【灌水乐园】发言
