ConvMAE模型源码
Posted AI浩
tags:
篇首语：本文由小常识网(cha138.com)小编为大家整理，主要介绍了ConvMAE模型源码相关的知识，希望对你有一定的参考价值。
vision_transformer.py
# Copyright (c) 2022 Alpha-VL
# --------------------------------------------------------
# References:
# timm: https://github.com/rwightman/pytorch-image-models/tree/master/timm
# DeiT: https://github.com/facebookresearch/deit
# --------------------------------------------------------
import torch
import torch.nn as nn
from functools import partial
from timm.data import IMAGENET_DEFAULT_MEAN, IMAGENET_DEFAULT_STD
from timm.models.helpers import load_pretrained
from timm.models.layers import DropPath, to_2tuple, trunc_normal_
from timm.models.resnet import resnet26d, resnet50d
from timm.models.registry import register_model
import pdb
def _cfg(url='', **kwargs):
return
'url': url,
'num_classes': 1000, 'input_size': (3, 224, 224), 'pool_size': None,
'crop_pct': .9, 'interpolation': 'bicubic',
'mean': IMAGENET_DEFAULT_MEAN, 'std': IMAGENET_DEFAULT_STD,
'first_conv': 'patch_embed.proj', 'classifier': 'head',
**kwargs
default_cfgs =
# patch models
'vit_small_patch16_224': _cfg(
url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-weights/vit_small_p16_224-15ec54c9.pth',
),
'vit_base_patch16_224': _cfg(
url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-vitjx/jx_vit_base_p16_224-80ecf9dd.pth',
mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5),
),
'vit_base_patch16_384': _cfg(
url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-vitjx/jx_vit_base_p16_384-83fb41ba.pth',
input_size=(3, 384, 384), mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5), crop_pct=1.0),
'vit_base_patch32_384': _cfg(
url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-vitjx/jx_vit_base_p32_384-830016f5.pth',
input_size=(3, 384, 384), mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5), crop_pct=1.0),
'vit_large_patch16_224': _cfg(
url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-vitjx/jx_vit_large_p16_224-4ee7a4dc.pth',
mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5)),
'vit_large_patch16_384': _cfg(
url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-vitjx/jx_vit_large_p16_384-b3be5167.pth',
input_size=(3, 384, 384), mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5), crop_pct=1.0),
'vit_large_patch32_384': _cfg(
url='https://github.com/rwightman/pytorch-image-models/releases/download/v0.1-vitjx/jx_vit_large_p32_384-9b920ba8.pth',
input_size=(3, 384, 384), mean=(0.5, 0.5, 0.5), std=(0.5, 0.5, 0.5), crop_pct=1.0),
'vit_huge_patch16_224': _cfg(),
'vit_huge_patch32_384': _cfg(input_size=(3, 384, 384)),
# hybrid models
'vit_small_resnet26d_224': _cfg(),
'vit_small_resnet50d_s3_224': _cfg(),
'vit_base_resnet26d_224': _cfg(),
'vit_base_resnet50d_224': _cfg(),
class CMlp(nn.Module):
# taken from https://github.com/rwightman/pytorch-image-models/blob/master/timm/models/vision_transformer.py
def __init__(self, in_features, hidden_features=None, out_features=None, act_layer=nn.GELU, drop=0.):
super().__init__()
out_features = out_features or in_features
hidden_features = hidden_features or in_features
self.fc1 = nn.Conv2d(in_features, hidden_features, 1)
self.act = act_layer()
self.fc2 = nn.Conv2d(hidden_features, out_features, 1)
self.drop = nn.Dropout(drop)
def forward(self, x):
x = self.fc1(x)
x = self.act(x)
x = self.drop(x)
x = self.fc2(x)
x = self.drop(x)
return x
class Mlp(nn.Module):
def __init__(self, in_features, hidden_features=None, out_features=None, act_layer=nn.GELU, drop=0.):
super().__init__()
out_features = out_features or in_features
hidden_features = hidden_features or in_features
self.fc1 = nn.Linear(in_features, hidden_features)
self.act = act_layer()
self.fc2 = nn.Linear(hidden_features, out_features)
self.drop = nn.Dropout(drop)
def forward(self, x):
x = self.fc1(x)
x = self.act(x)
x = self.drop(x)
x = self.fc2(x)
x = self.drop(x)
return x
class CBlock(nn.Module):
# taken from https://github.com/rwightman/pytorch-image-models/blob/master/timm/models/vision_transformer.py
def __init__(self, dim, num_heads, mlp_ratio=4., qkv_bias=False, qk_scale=None, drop=0., attn_drop=0.,
drop_path=0., act_layer=nn.GELU, norm_layer=nn.LayerNorm):
super().__init__()
self.norm1 = nn.LayerNorm(dim)
self.conv1 = nn.Conv2d(dim, dim, 1)
self.conv2 = nn.Conv2d(dim, dim, 1)
self.attn = nn.Conv2d(dim, dim, 5, padding=2, groups=dim)
# self.attn = nn.Conv2d(dim, dim, 13, padding=6, groups=dim)
# NOTE: drop path for stochastic depth, we shall see if this is better than dropout here
self.drop_path = DropPath(drop_path) if drop_path > 0. else nn.Identity()
self.norm2 = nn.LayerNorm(dim)
mlp_hidden_dim = int(dim * mlp_ratio)
self.mlp = CMlp(in_features=dim, hidden_features=mlp_hidden_dim, act_layer=act_layer, drop=drop)
def forward(self, x, mask=None):
if mask is not None:
x = x + self.drop_path(self.conv2(self.attn(mask * self.conv1(self.norm1(x.permute(0, 2, 3, 1)).permute(0, 3, 1, 2)))))
else:
x = x + self.drop_path(self.conv2(self.attn(self.conv1(self.norm1(x.permute(0, 2, 3, 1)).permute(0, 3, 1, 2)))))
x = x + self.drop_path(self.mlp(self.norm2(x.permute(0, 2, 3, 1)).permute(0, 3, 1, 2)))
return x
class Attention(nn.Module):
def __init__(self, dim, num_heads=8, qkv_bias=False, qk_scale=None, attn_drop=0., proj_drop=0.):
super().__init__()
self.num_heads = num_heads
head_dim = dim // num_heads
# NOTE scale factor was wrong in my original version, can set manually to be compat with prev weights
self.scale = qk_scale or head_dim ** -0.5
self.qkv = nn.Linear(dim, dim * 3, bias=qkv_bias)
self.attn_drop = nn.Dropout(attn_drop)
self.proj = nn.Linear(dim, dim)
self.proj_drop = nn.Dropout(proj_drop)
def forward(self, x):
B, N, C = x.shape
qkv = self.qkv(x).reshape(B, N, 3, self.num_heads, C // self.num_heads).permute(2, 0, 3, 1, 4)
q, k, v = qkv[0], qkv[1], qkv[2] # make torchscript happy (cannot use tensor as tuple)
attn = (q @ k.transpose(-2, -1)) * self.scale
attn = attn.softmax(dim=-1)
attn = self.attn_drop(attn)
x = (attn @ v).transpose(1, 2).reshape(B, N, C)
x = self.proj(x)
x = self.proj_drop(x)
return x
class Block(nn.Module):
def __init__(self, dim, num_heads, mlp_ratio=4., qkv_bias=False, qk_scale=None, drop=0., attn_drop=0.,
drop_path=0., act_layer=nn.GELU, norm_layer=nn.LayerNorm):
super().__init__()
self.norm1 = norm_layer(dim)
self.attn = Attention(
dim, num_heads=num_heads, qkv_bias=qkv_bias, qk_scale=qk_scale, attn_drop=attn_drop, proj_drop=drop)
# NOTE: drop path for stochastic depth, we shall see if this is better than dropout here
self.drop_path = DropPath(drop_path) if drop_path > 0. else nn.Identity()
self.norm2 = norm_layer(dim)
mlp_hidden_dim = int(dim * mlp_ratio)
self.mlp = Mlp(in_features=dim, hidden_features=mlp_hidden_dim, act_layer=act_layer, drop=drop)
def forward(self, x):
x = x + self.drop_path(self.attn(self.norm1(x)))
x = x + self.drop_path(self.mlp(self.norm2(x)))
return x
class PatchEmbed(nn.Module):
""" Image to Patch Embedding
"""
def __init__(self, img_size=224, patch_size=16, in_chans=3, embed_dim=768):
super().__init__()
img_size = to_2tuple(img_size)
patch_size = to_2tuple(patch_size)
num_patches = (img_size[1] // patch_size[1]) * (img_size[0] // patch_size[0])
self.img_size = img_size
self.patch_size = patch_size
self.num_patches = num_patches
self.proj = nn.Conv2d(in_chans, embed_dim, kernel_size=patch_size, stride=patch_size)
self.norm = nn.LayerNorm(embed_dim)
self.act = nn.GELU()
def forward(self, x):
B, C, H, W = x.shape
# FIXME look at relaxing size constraints
assert H == self.img_size[0] and W == self.img_size[1], \\
f"Input image size (H*W) doesn't match model (self.img_size[0]*self.img_size[1])."
x = self.proj(x)
x = self.norm(x.permute(0, 2, 3, 1)).permute(0, 3, 1, 2)
return self.act(x)
class HybridEmbed(nn.Module):
""" CNN Feature Map Embedding
Extract feature map from CNN, flatten, project to embedding dim.
"""
def __init__(self, backbone, img_size=224, feature_size=None, in_chans=3, embed_dim=768):
super().__init__()
assert isinstance(backbone, nn.Module)
img_size = to_2tuple(img_size)
self.img_size = img_size
self.backbone = backbone
if feature_size is None:
with torch.no_grad():
# FIXME this is hacky, but most reliable way of determining the exact dim of the output feature
# map for all networks, the feature metadata has reliable channel and stride info, but using
# stride to calc feature dim requires info about padding of each stage that isn't captured.
training = backbone.training
if training:
backbone.eval()
o = self.backbone(torch.zeros(1, in_chans, img_size[0], img_size[1]))[-1]
feature_size = o.shape[-2:]
feature_dim = o.shape[1]
backbone.train(training)
else:
feature_size = to_2tuple(feature_size)
feature_dim = self.backbone.feature_info.channels()[-1]
self.num_patches = feature_size[0] * feature_size[1]
self.proj = nn.Linear(feature_dim, embed_dim)
def forward(self, x):
x = self.backbone(x)[-1]
x = x.flatten(2).transpose(1, 2)
x = self.proj(x)
return x
class ConvViT(nn.Module):
""" Vision Transformer with support for patch or hybrid CNN input stage
"""
def __init__(self, img_size=224, patch_size=16, in_chans=3, num_classes=1000, embed_dim=768, depth=12,
num_heads=12, mlp_ratio=4., qkv_bias=False, qk_scale=None, drop_rate=0., attn_drop_rate=0.,
drop_path_rate=0., hybrid_backbone=None, norm_layer=nn.LayerNorm):
super().__init__()
self.num_classes =以上是关于ConvMAE模型源码的主要内容，如果未能解决你的问题，请参考以下文章
ConvMAE实战：使用ConvMAE实现对植物幼苗的分类（非官方）