File size: 6,142 Bytes
c59c099 |
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 |
import os
import torch
from collections import OrderedDict
from torch import nn as nn
from torchvision.models import vgg as vgg
from basicsr.utils.registry import ARCH_REGISTRY
VGG_PRETRAIN_PATH = 'experiments/pretrained_models/vgg19-dcbb9e9d.pth'
NAMES = {
'vgg11': [
'conv1_1', 'relu1_1', 'pool1', 'conv2_1', 'relu2_1', 'pool2', 'conv3_1', 'relu3_1', 'conv3_2', 'relu3_2',
'pool3', 'conv4_1', 'relu4_1', 'conv4_2', 'relu4_2', 'pool4', 'conv5_1', 'relu5_1', 'conv5_2', 'relu5_2',
'pool5'
],
'vgg13': [
'conv1_1', 'relu1_1', 'conv1_2', 'relu1_2', 'pool1', 'conv2_1', 'relu2_1', 'conv2_2', 'relu2_2', 'pool2',
'conv3_1', 'relu3_1', 'conv3_2', 'relu3_2', 'pool3', 'conv4_1', 'relu4_1', 'conv4_2', 'relu4_2', 'pool4',
'conv5_1', 'relu5_1', 'conv5_2', 'relu5_2', 'pool5'
],
'vgg16': [
'conv1_1', 'relu1_1', 'conv1_2', 'relu1_2', 'pool1', 'conv2_1', 'relu2_1', 'conv2_2', 'relu2_2', 'pool2',
'conv3_1', 'relu3_1', 'conv3_2', 'relu3_2', 'conv3_3', 'relu3_3', 'pool3', 'conv4_1', 'relu4_1', 'conv4_2',
'relu4_2', 'conv4_3', 'relu4_3', 'pool4', 'conv5_1', 'relu5_1', 'conv5_2', 'relu5_2', 'conv5_3', 'relu5_3',
'pool5'
],
'vgg19': [
'conv1_1', 'relu1_1', 'conv1_2', 'relu1_2', 'pool1', 'conv2_1', 'relu2_1', 'conv2_2', 'relu2_2', 'pool2',
'conv3_1', 'relu3_1', 'conv3_2', 'relu3_2', 'conv3_3', 'relu3_3', 'conv3_4', 'relu3_4', 'pool3', 'conv4_1',
'relu4_1', 'conv4_2', 'relu4_2', 'conv4_3', 'relu4_3', 'conv4_4', 'relu4_4', 'pool4', 'conv5_1', 'relu5_1',
'conv5_2', 'relu5_2', 'conv5_3', 'relu5_3', 'conv5_4', 'relu5_4', 'pool5'
]
}
def insert_bn(names):
"""Insert bn layer after each conv.
Args:
names (list): The list of layer names.
Returns:
list: The list of layer names with bn layers.
"""
names_bn = []
for name in names:
names_bn.append(name)
if 'conv' in name:
position = name.replace('conv', '')
names_bn.append('bn' + position)
return names_bn
@ARCH_REGISTRY.register()
class VGGFeatureExtractor(nn.Module):
"""VGG network for feature extraction.
In this implementation, we allow users to choose whether use normalization
in the input feature and the type of vgg network. Note that the pretrained
path must fit the vgg type.
Args:
layer_name_list (list[str]): Forward function returns the corresponding
features according to the layer_name_list.
Example: {'relu1_1', 'relu2_1', 'relu3_1'}.
vgg_type (str): Set the type of vgg network. Default: 'vgg19'.
use_input_norm (bool): If True, normalize the input image. Importantly,
the input feature must in the range [0, 1]. Default: True.
range_norm (bool): If True, norm images with range [-1, 1] to [0, 1].
Default: False.
requires_grad (bool): If true, the parameters of VGG network will be
optimized. Default: False.
remove_pooling (bool): If true, the max pooling operations in VGG net
will be removed. Default: False.
pooling_stride (int): The stride of max pooling operation. Default: 2.
"""
def __init__(self,
layer_name_list,
vgg_type='vgg19',
use_input_norm=True,
range_norm=False,
requires_grad=False,
remove_pooling=False,
pooling_stride=2):
super(VGGFeatureExtractor, self).__init__()
self.layer_name_list = layer_name_list
self.use_input_norm = use_input_norm
self.range_norm = range_norm
self.names = NAMES[vgg_type.replace('_bn', '')]
if 'bn' in vgg_type:
self.names = insert_bn(self.names)
# only borrow layers that will be used to avoid unused params
max_idx = 0
for v in layer_name_list:
idx = self.names.index(v)
if idx > max_idx:
max_idx = idx
if os.path.exists(VGG_PRETRAIN_PATH):
vgg_net = getattr(vgg, vgg_type)(pretrained=False)
state_dict = torch.load(VGG_PRETRAIN_PATH, map_location=lambda storage, loc: storage)
vgg_net.load_state_dict(state_dict)
else:
vgg_net = getattr(vgg, vgg_type)(pretrained=True)
features = vgg_net.features[:max_idx + 1]
modified_net = OrderedDict()
for k, v in zip(self.names, features):
if 'pool' in k:
# if remove_pooling is true, pooling operation will be removed
if remove_pooling:
continue
else:
# in some cases, we may want to change the default stride
modified_net[k] = nn.MaxPool2d(kernel_size=2, stride=pooling_stride)
else:
modified_net[k] = v
self.vgg_net = nn.Sequential(modified_net)
if not requires_grad:
self.vgg_net.eval()
for param in self.parameters():
param.requires_grad = False
else:
self.vgg_net.train()
for param in self.parameters():
param.requires_grad = True
if self.use_input_norm:
# the mean is for image with range [0, 1]
self.register_buffer('mean', torch.Tensor([0.485, 0.456, 0.406]).view(1, 3, 1, 1))
# the std is for image with range [0, 1]
self.register_buffer('std', torch.Tensor([0.229, 0.224, 0.225]).view(1, 3, 1, 1))
def forward(self, x):
"""Forward function.
Args:
x (Tensor): Input tensor with shape (n, c, h, w).
Returns:
Tensor: Forward results.
"""
if self.range_norm:
x = (x + 1) / 2
if self.use_input_norm:
x = (x - self.mean) / self.std
output = {}
for key, layer in self.vgg_net._modules.items():
x = layer(x)
if key in self.layer_name_list:
output[key] = x.clone()
return output
|