File size: 4,881 Bytes
a50312e
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
 
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
# Copyright Niantic 2019. Patent Pending. All rights reserved.
#
# This software is licensed under the terms of the Monodepth2 licence
# which allows for non-commercial use only, the full terms of which are made
# available in the LICENSE file.

from __future__ import absolute_import, division, print_function

import numpy as np

import torch
import torch.nn as nn
import torchvision.models as models
import torch.utils.model_zoo as model_zoo
from torchvision.models.resnet import ResNet18_Weights, ResNet50_Weights


class ResNetMultiImageInput(models.ResNet):
    """Constructs a resnet model with varying number of input images.
    Adapted from https://github.com/pytorch/vision/blob/master/torchvision/models/resnet.py
    """
    def __init__(self, block, layers, num_classes=1000, num_input_images=1):
        super(ResNetMultiImageInput, self).__init__(block, layers)
        self.inplanes = 64
        self.conv1 = nn.Conv2d(
            num_input_images * 3, 64, kernel_size=7, stride=2, padding=3, bias=False)
        self.bn1 = nn.BatchNorm2d(64)
        self.relu = nn.ReLU(inplace=True)
        self.maxpool = nn.MaxPool2d(kernel_size=3, stride=2, padding=1)
        self.layer1 = self._make_layer(block, 64, layers[0])
        self.layer2 = self._make_layer(block, 128, layers[1], stride=2)
        self.layer3 = self._make_layer(block, 256, layers[2], stride=2)
        self.layer4 = self._make_layer(block, 512, layers[3], stride=2)
        
        
        

        for m in self.modules():
            if isinstance(m, nn.Conv2d):
                nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')
            elif isinstance(m, nn.BatchNorm2d):
                nn.init.constant_(m.weight, 1)
                nn.init.constant_(m.bias, 0)


def resnet_multiimage_input(num_layers, pretrained=False, num_input_images=1):
    """Constructs a ResNet model.
    Args:
        num_layers (int): Number of resnet layers. Must be 18 or 50
        pretrained (bool): If True, returns a model pre-trained on ImageNet
        num_input_images (int): Number of frames stacked as input
    """
    assert num_layers in [18, 50], "Can only run with 18 or 50 layer resnet"
    blocks = {18: [2, 2, 2, 2], 50: [3, 4, 6, 3]}[num_layers]
    block_type = {18: models.resnet.BasicBlock, 50: models.resnet.Bottleneck}[num_layers]
    model = ResNetMultiImageInput(block_type, blocks, num_input_images=num_input_images)

    if pretrained:
        # loaded = torch.utils.model_zoo.load_url(ResNet50_Weights.IMAGENET1K_V1.url)
        loaded = torch.utils.model_zoo.load_url(ResNet18_Weights.IMAGENET1K_V1.url)
        # loaded = model_zoo.load_url(models.resnet.model_urls['resnet{}'.format(num_layers)])
        loaded['conv1.weight'] = torch.cat(
            [loaded['conv1.weight']] * num_input_images, 1) / num_input_images
        model.load_state_dict(loaded)
    return model


class ResnetEncoder(nn.Module):
    """Pytorch module for a resnet encoder
    """
    def __init__(self, num_layers, pretrained, num_input_images=1, batch_norm_apply = False):
        super(ResnetEncoder, self).__init__()

        self.num_ch_enc = np.array([64, 64, 128, 256, 512])

        resnets = {18: models.resnet18,
                   34: models.resnet34,
                   50: models.resnet50,
                   101: models.resnet101,
                   152: models.resnet152}

        if num_layers not in resnets:
            raise ValueError("{} is not a valid number of resnet layers".format(num_layers))

        if num_input_images > 1:
            self.encoder = resnet_multiimage_input(num_layers, pretrained, num_input_images)
        else:
            self.encoder = resnets[num_layers](pretrained)

        if num_layers > 34:
            self.num_ch_enc[1:] *= 4
        
        self.drop = True
        self.dropout = torch.nn.Dropout(p=0.2)

    def forward(self, input_image):
        self.features = []
        # x = (input_image - 0.45) / 0.225 # ?
        x = input_image
        x = self.encoder.conv1(x)
        x = self.encoder.bn1(x)
        self.features.append(self.encoder.relu(x))
        if self.drop:
            self.features.append(self.encoder.layer1(self.encoder.maxpool(self.features[-1])))
            self.features.append(self.encoder.layer2(self.dropout(self.features[-1])))
            self.features.append(self.encoder.layer3(self.dropout(self.features[-1])))
            self.features.append(self.encoder.layer4(self.dropout(self.features[-1])))
        else:
            self.features.append(self.encoder.layer1(self.encoder.maxpool(self.features[-1])))
            self.features.append(self.encoder.layer2((self.features[-1])))
            self.features.append(self.encoder.layer3((self.features[-1])))
            self.features.append(self.encoder.layer4((self.features[-1])))
            
        return self.features