-
Notifications
You must be signed in to change notification settings - Fork 0
/
darknet.py
272 lines (200 loc) · 9.24 KB
/
darknet.py
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
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
263
264
265
266
267
268
269
270
271
272
from __future__ import division
import torch
import torch.nn as nn
import torch.nn.functional as F
from torch.autograd import Variable
import numpy as np
from utils import *
def parse_cfg(cfgfile):
"""
Takes a configuration file
Returns a list of blocks. Each blocks describes a block in the neural
network to be built. Block is represented as a dictionary in the list
"""
file = open(cfgfile, 'r')
lines = file.read().split('\n') # store the lines in a list
lines = [x for x in lines if len(x) > 0] # get read of the empty lines
lines = [x for x in lines if x[0] != '#'] # get rid of comments
lines = [x.rstrip().lstrip() for x in lines] # get rid of fringe whitespaces
block = {}
blocks = []
for line in lines:
if line[0] == "[":
if len(block) != 0:
blocks.append(block)
block = {}
block["type"] = line[1:-1].rstrip()
else:
key,value = line.split("=")
block[key.rstrip()] = value.lstrip()
blocks.append(block)
return blocks
class EmptyLayer(nn.Module):
def __init__(self):
super(EmptyLayer, self).__init__()
class DetectionLayer(nn.Module):
def __init__(self, anchors):
super(DetectionLayer, self).__init__()
self.anchors = anchors
def create_modules(blocks):
net_info = blocks[0]
module_list = nn.ModuleList()
prev_filters = 3
output_filters = []
for index, x in enumerate(blocks[1:]):
module = nn.Sequential()
if (x["type"] == "convolutional"):
activation = x["activation"]
try:
batch_normalize = int(x["batch_normalize"])
bias = False
except:
batch_normalize = 0
bias = True
filters= int(x["filters"])
padding = int(x["pad"])
kernel_size = int(x["size"])
stride = int(x["stride"])
if padding:
pad = (kernel_size - 1) // 2
else:
pad = 0
conv = nn.Conv2d(prev_filters, filters, kernel_size, stride, pad, bias = bias)
module.add_module("conv_{0}".format(index), conv)
if batch_normalize:
bn = nn.BatchNorm2d(filters)
module.add_module("batch_norm_{0}".format(index), bn)
if activation == "leaky":
activn = nn.LeakyReLU(0.1, inplace = True)
module.add_module("leaky_{0}".format(index), activn)
elif (x["type"] == "upsample"):
stride = int(x["stride"])
upsample = nn.Upsample(scale_factor = 2, mode = "nearest")
module.add_module("upsample_{}".format(index), upsample)
elif (x["type"] == "route"):
x["layers"] = x["layers"].split(',')
start = int(x["layers"][0])
try:
end = int(x["layers"][1])
except:
end = 0
if start > 0:
start = start - index
if end > 0:
end = end - index
route = EmptyLayer()
module.add_module("route_{0}".format(index), route)
if end < 0:
filters = output_filters[index + start] + output_filters[index + end]
else:
filters= output_filters[index + start]
elif x["type"] == "shortcut":
shortcut = EmptyLayer()
module.add_module("shortcut_{}".format(index), shortcut)
elif x["type"] == "yolo":
mask = x["mask"].split(",")
mask = [int(x) for x in mask]
anchors = x["anchors"].split(",")
anchors = [int(a) for a in anchors]
anchors = [(anchors[i], anchors[i+1]) for i in range(0, len(anchors),2)]
anchors = [anchors[i] for i in mask]
detection = DetectionLayer(anchors)
module.add_module("Detection_{}".format(index), detection)
module_list.append(module)
prev_filters = filters
output_filters.append(filters)
return (net_info, module_list)
class Darknet(nn.Module):
def __init__(self, cfgfile):
super(Darknet, self).__init__()
self.blocks = parse_cfg(cfgfile)
self.net_info, self.module_list = create_modules(self.blocks)
def forward(self, x, CUDA):
modules = self.blocks[1:]
outputs = {} #We cache the outputs for the route layer
write = 0
for i, module in enumerate(modules):
module_type = (module["type"])
if module_type == "convolutional" or module_type == "upsample":
x = self.module_list[i](x)
elif module_type == "route":
layers = module["layers"]
layers = [int(a) for a in layers]
if (layers[0]) > 0:
layers[0] = layers[0] - i
if len(layers) == 1:
x = outputs[i + (layers[0])]
else:
if (layers[1]) > 0:
layers[1] = layers[1] - i
map1 = outputs[i + layers[0]]
map2 = outputs[i + layers[1]]
x = torch.cat((map1, map2), 1)
elif module_type == "shortcut":
from_ = int(module["from"])
x = outputs[i-1] + outputs[i+from_]
elif module_type == 'yolo':
anchors = self.module_list[i][0].anchors
inp_dim = int (self.net_info["height"])
num_classes = int (module["classes"])
x = x.data
x = predict_transform(x, inp_dim, anchors, num_classes, CUDA)
if not write: #if no collector has been intialised.
detections = x
write = 1
else:
detections = torch.cat((detections, x), 1)
outputs[i] = x
return detections
def load_weights(self, weightfile):
#Open the weights file
fp = open(weightfile, "rb")
#The first 5 values are header information
# 1. Major version number
# 2. Minor Version Number
# 3. Subversion number
# 4,5. Images seen by the network (during training)
header = np.fromfile(fp, dtype = np.int32, count = 5)
self.header = torch.from_numpy(header)
self.seen = self.header[3]
weights = np.fromfile(fp, dtype = np.float32)
ptr = 0
for i in range(len(self.module_list)):
module_type = self.blocks[i + 1]["type"]
if module_type == "convolutional":
model = self.module_list[i]
try:
batch_normalize = int(self.blocks[i+1]["batch_normalize"])
except:
batch_normalize = 0
conv = model[0]
if (batch_normalize):
bn = model[1]
num_bn_biases = bn.bias.numel()
bn_biases = torch.from_numpy(weights[ptr:ptr + num_bn_biases])
ptr += num_bn_biases
bn_weights = torch.from_numpy(weights[ptr: ptr + num_bn_biases])
ptr += num_bn_biases
bn_running_mean = torch.from_numpy(weights[ptr: ptr + num_bn_biases])
ptr += num_bn_biases
bn_running_var = torch.from_numpy(weights[ptr: ptr + num_bn_biases])
ptr += num_bn_biases
bn_biases = bn_biases.view_as(bn.bias.data)
bn_weights = bn_weights.view_as(bn.weight.data)
bn_running_mean = bn_running_mean.view_as(bn.running_mean)
bn_running_var = bn_running_var.view_as(bn.running_var)
bn.bias.data.copy_(bn_biases)
bn.weight.data.copy_(bn_weights)
bn.running_mean.copy_(bn_running_mean)
bn.running_var.copy_(bn_running_var)
else:
num_biases = conv.bias.numel()
conv_biases = torch.from_numpy(weights[ptr: ptr + num_biases])
ptr = ptr + num_biases
conv_biases = conv_biases.view_as(conv.bias.data)
conv.bias.data.copy_(conv_biases)
num_weights = conv.weight.numel()
conv_weights = torch.from_numpy(weights[ptr:ptr+num_weights])
ptr = ptr + num_weights
conv_weights = conv_weights.view_as(conv.weight.data)
conv.weight.data.copy_(conv_weights)