# -*- coding:utf-8 -*-
# ------------------------
# written by Songjian Chen
# 2018-11
# ------------------------
import torch.nn as nn
from torchvision import models
import torch.nn.functional as F
[docs]class VGG(nn.Module):
"""Refer from `"VGG..." <https://arxiv.org/abs/1409.1556>`_ paper
Args:
load_weights (bool): If True, CSRNet will be pre-trained on ImageNet
"""
def __init__(self, load_weights=True):
super(VGG, self).__init__()
print("*****init VGG net*****")
self.seen = 0
self.frontend_feat = [64, 64, 'M', 128, 128, 'M', 256, 256, 256, 'M', 512, 512, 512]
self.backend_feat = [512, 512, 512, 256, 128, 64]
self.frontend = make_layers(self.frontend_feat)
self.backend = make_layers(self.backend_feat, in_channels=512)
self.output_layer = nn.Conv2d(64, 1, kernel_size=1)
if not load_weights:
mod = models.vgg16(pretrained=True)
self._initialize_weights()
for i in range(len(self.frontend.state_dict().items())):
list(self.frontend.state_dict().items())[i][1].data[:] = list(mod.state_dict().items())[i][1].data[:]
def forward(self, x):
x = self.frontend(x)
x = self.backend(x)
x = self.output_layer(x)
x = F.interpolate(x, scale_factor=8)
return x
def _initialize_weights(self):
for m in self.modules():
if isinstance(m, nn.Conv2d):
m.weight.data.normal_(0.0, std=0.01)
if m.bias is not None:
m.bias.data.fill_(0)
elif isinstance(m, nn.BatchNorm2d):
m.weight.fill_(1)
m.bias.data.fill_(0)
def make_layers(cfg, in_channels=3, batch_norm=False):
layers = []
for v in cfg:
if v == 'M':
layers += [nn.MaxPool2d(kernel_size=2, stride=2)]
else:
conv2d = nn.Conv2d(in_channels, v, kernel_size=3, padding=1)
if batch_norm:
layers += [conv2d, nn.BatchNorm2d(v), nn.ReLU(inplace=True)]
else:
layers += [conv2d, nn.ReLU(inplace=True)]
in_channels = v
return nn.Sequential(*layers)