Spaces:
Sleeping
Sleeping
File size: 4,995 Bytes
ac4ce84 |
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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 |
import torch
import torch.nn as nn
import torch.nn.functional as F
from collections import OrderedDict
import numpy as np
from configs.paths_config import model_paths
PNET_PATH = model_paths["mtcnn_pnet"]
ONET_PATH = model_paths["mtcnn_onet"]
RNET_PATH = model_paths["mtcnn_rnet"]
class Flatten(nn.Module):
def __init__(self):
super(Flatten, self).__init__()
def forward(self, x):
"""
Arguments:
x: a float tensor with shape [batch_size, c, h, w].
Returns:
a float tensor with shape [batch_size, c*h*w].
"""
# without this pretrained model isn't working
x = x.transpose(3, 2).contiguous()
return x.view(x.size(0), -1)
class PNet(nn.Module):
def __init__(self):
super().__init__()
# suppose we have input with size HxW, then
# after first layer: H - 2,
# after pool: ceil((H - 2)/2),
# after second conv: ceil((H - 2)/2) - 2,
# after last conv: ceil((H - 2)/2) - 4,
# and the same for W
self.features = nn.Sequential(OrderedDict([
('conv1', nn.Conv2d(3, 10, 3, 1)),
('prelu1', nn.PReLU(10)),
('pool1', nn.MaxPool2d(2, 2, ceil_mode=True)),
('conv2', nn.Conv2d(10, 16, 3, 1)),
('prelu2', nn.PReLU(16)),
('conv3', nn.Conv2d(16, 32, 3, 1)),
('prelu3', nn.PReLU(32))
]))
self.conv4_1 = nn.Conv2d(32, 2, 1, 1)
self.conv4_2 = nn.Conv2d(32, 4, 1, 1)
weights = np.load(PNET_PATH, allow_pickle=True)[()]
for n, p in self.named_parameters():
p.data = torch.FloatTensor(weights[n])
def forward(self, x):
"""
Arguments:
x: a float tensor with shape [batch_size, 3, h, w].
Returns:
b: a float tensor with shape [batch_size, 4, h', w'].
a: a float tensor with shape [batch_size, 2, h', w'].
"""
x = self.features(x)
a = self.conv4_1(x)
b = self.conv4_2(x)
a = F.softmax(a, dim=-1)
return b, a
class RNet(nn.Module):
def __init__(self):
super().__init__()
self.features = nn.Sequential(OrderedDict([
('conv1', nn.Conv2d(3, 28, 3, 1)),
('prelu1', nn.PReLU(28)),
('pool1', nn.MaxPool2d(3, 2, ceil_mode=True)),
('conv2', nn.Conv2d(28, 48, 3, 1)),
('prelu2', nn.PReLU(48)),
('pool2', nn.MaxPool2d(3, 2, ceil_mode=True)),
('conv3', nn.Conv2d(48, 64, 2, 1)),
('prelu3', nn.PReLU(64)),
('flatten', Flatten()),
('conv4', nn.Linear(576, 128)),
('prelu4', nn.PReLU(128))
]))
self.conv5_1 = nn.Linear(128, 2)
self.conv5_2 = nn.Linear(128, 4)
weights = np.load(RNET_PATH, allow_pickle=True)[()]
for n, p in self.named_parameters():
p.data = torch.FloatTensor(weights[n])
def forward(self, x):
"""
Arguments:
x: a float tensor with shape [batch_size, 3, h, w].
Returns:
b: a float tensor with shape [batch_size, 4].
a: a float tensor with shape [batch_size, 2].
"""
x = self.features(x)
a = self.conv5_1(x)
b = self.conv5_2(x)
a = F.softmax(a, dim=-1)
return b, a
class ONet(nn.Module):
def __init__(self):
super().__init__()
self.features = nn.Sequential(OrderedDict([
('conv1', nn.Conv2d(3, 32, 3, 1)),
('prelu1', nn.PReLU(32)),
('pool1', nn.MaxPool2d(3, 2, ceil_mode=True)),
('conv2', nn.Conv2d(32, 64, 3, 1)),
('prelu2', nn.PReLU(64)),
('pool2', nn.MaxPool2d(3, 2, ceil_mode=True)),
('conv3', nn.Conv2d(64, 64, 3, 1)),
('prelu3', nn.PReLU(64)),
('pool3', nn.MaxPool2d(2, 2, ceil_mode=True)),
('conv4', nn.Conv2d(64, 128, 2, 1)),
('prelu4', nn.PReLU(128)),
('flatten', Flatten()),
('conv5', nn.Linear(1152, 256)),
('drop5', nn.Dropout(0.25)),
('prelu5', nn.PReLU(256)),
]))
self.conv6_1 = nn.Linear(256, 2)
self.conv6_2 = nn.Linear(256, 4)
self.conv6_3 = nn.Linear(256, 10)
weights = np.load(ONET_PATH, allow_pickle=True)[()]
for n, p in self.named_parameters():
p.data = torch.FloatTensor(weights[n])
def forward(self, x):
"""
Arguments:
x: a float tensor with shape [batch_size, 3, h, w].
Returns:
c: a float tensor with shape [batch_size, 10].
b: a float tensor with shape [batch_size, 4].
a: a float tensor with shape [batch_size, 2].
"""
x = self.features(x)
a = self.conv6_1(x)
b = self.conv6_2(x)
c = self.conv6_3(x)
a = F.softmax(a, dim=-1)
return c, b, a
|