Spaces:
Paused
Paused
File size: 1,630 Bytes
3d49622 |
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 |
#!/usr/bin/env python
# -*- encoding: utf-8 -*-
"""
@Author : Peike Li
@Contact : [email protected]
@File : psp.py
@Time : 8/4/19 3:36 PM
@Desc :
@License : This source code is licensed under the license found in the
LICENSE file in the root directory of this source tree.
"""
import torch
import torch.nn as nn
from torch.nn import functional as F
from modules import InPlaceABNSync
class PSPModule(nn.Module):
"""
Reference:
Zhao, Hengshuang, et al. *"Pyramid scene parsing network."*
"""
def __init__(self, features, out_features=512, sizes=(1, 2, 3, 6)):
super(PSPModule, self).__init__()
self.stages = []
self.stages = nn.ModuleList([self._make_stage(features, out_features, size) for size in sizes])
self.bottleneck = nn.Sequential(
nn.Conv2d(features + len(sizes) * out_features, out_features, kernel_size=3, padding=1, dilation=1,
bias=False),
InPlaceABNSync(out_features),
)
def _make_stage(self, features, out_features, size):
prior = nn.AdaptiveAvgPool2d(output_size=(size, size))
conv = nn.Conv2d(features, out_features, kernel_size=1, bias=False)
bn = InPlaceABNSync(out_features)
return nn.Sequential(prior, conv, bn)
def forward(self, feats):
h, w = feats.size(2), feats.size(3)
priors = [F.interpolate(input=stage(feats), size=(h, w), mode='bilinear', align_corners=True) for stage in
self.stages] + [feats]
bottle = self.bottleneck(torch.cat(priors, 1))
return bottle |