-
Notifications
You must be signed in to change notification settings - Fork 205
/
darknet_util.py
382 lines (292 loc) · 12.8 KB
/
darknet_util.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
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
# coding:utf-8
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
import cv2
import matplotlib.pyplot as plt
from bbox import bbox_iou
def count_parameters(model):
return sum(p.numel() for p in model.parameters())
def count_learnable_parameters(model):
return sum(p.numel() for p in model.parameters() if p.requires_grad)
def convert2cpu(matrix):
if matrix.is_cuda:
return torch.FloatTensor(matrix.size()).copy_(matrix)
else:
return matrix
def predict_transform(prediction, inp_dim, anchors, num_classes, CUDA=True):
batch_size = prediction.size(0)
stride = inp_dim // prediction.size(2)
grid_size = inp_dim // stride
bbox_attrs = 5 + num_classes
num_anchors = len(anchors)
anchors = [(a[0] / stride, a[1] / stride) for a in anchors]
prediction = prediction.view(
batch_size, bbox_attrs * num_anchors, grid_size * grid_size)
prediction = prediction.transpose(1, 2).contiguous()
prediction = prediction.view(
batch_size, grid_size * grid_size * num_anchors, bbox_attrs)
# Sigmoid the centre_X, centre_Y. and object confidencce
prediction[:, :, 0] = torch.sigmoid(prediction[:, :, 0])
prediction[:, :, 1] = torch.sigmoid(prediction[:, :, 1])
prediction[:, :, 4] = torch.sigmoid(prediction[:, :, 4])
# Add the center offsets
grid_len = np.arange(grid_size)
a, b = np.meshgrid(grid_len, grid_len)
x_offset = torch.FloatTensor(a).view(-1, 1)
y_offset = torch.FloatTensor(b).view(-1, 1)
if CUDA:
x_offset = x_offset.cuda()
y_offset = y_offset.cuda()
x_y_offset = torch.cat((x_offset, y_offset), 1).repeat(
1, num_anchors).view(-1, 2).unsqueeze(0)
prediction[:, :, :2] += x_y_offset
# log space transform height and the width
anchors = torch.FloatTensor(anchors)
if CUDA:
anchors = anchors.cuda()
anchors = anchors.repeat(grid_size * grid_size, 1).unsqueeze(0)
prediction[:, :, 2:4] = torch.exp(prediction[:, :, 2:4]) * anchors
# Softmax the class scores
prediction[:, :, 5: 5 +
num_classes] = torch.sigmoid((prediction[:, :, 5: 5 + num_classes]))
prediction[:, :, :4] *= stride
return prediction
def load_classes(namesfile):
fp = open(namesfile, "r")
names = fp.read().split("\n")[:-1]
return names
def get_im_dim(im):
im = cv2.imread(im)
w, h = im.shape[1], im.shape[0]
return w, h
def unique(tensor):
tensor_np = tensor.cpu().numpy()
unique_np = np.unique(tensor_np)
unique_tensor = torch.from_numpy(unique_np)
tensor_res = tensor.new(unique_tensor.shape)
tensor_res.copy_(unique_tensor)
return tensor_res
def post_process(prediction,
confidence,
num_classes,
nms=True,
nms_conf=0.4,
CUDA=True):
conf_mask = (prediction[:, :, 4] > confidence).float().unsqueeze(2)
prediction = prediction * conf_mask
try:
ind_nz = torch.nonzero(
prediction[:, :, 4]).transpose(0, 1).contiguous()
except:
return 0
box_a = prediction.new(prediction.shape)
box_a[:, :, 0] = (prediction[:, :, 0] - prediction[:, :, 2] / 2)
box_a[:, :, 1] = (prediction[:, :, 1] - prediction[:, :, 3] / 2)
box_a[:, :, 2] = (prediction[:, :, 0] + prediction[:, :, 2] / 2)
box_a[:, :, 3] = (prediction[:, :, 1] + prediction[:, :, 3] / 2)
prediction[:, :, :4] = box_a[:, :, :4]
batch_size = prediction.size(0)
output = prediction.new(1, prediction.size(2) + 1)
write = False
for ind in range(batch_size):
# select the image from the batch
image_pred = prediction[ind]
# Get the class having maximum score, and the index of that class
# Get rid of num_classes softmax scores
# Add the class index and the class score of class having maximum score
max_conf, max_conf_score = torch.max(
image_pred[:, 5:5 + num_classes], 1)
max_conf = max_conf.float().unsqueeze(1)
max_conf_score = max_conf_score.float().unsqueeze(1)
seq = (image_pred[:, :5], max_conf, max_conf_score)
image_pred = torch.cat(seq, 1)
# Get rid of the zero entries
non_zero_ind = (torch.nonzero(image_pred[:, 4]))
image_pred_ = image_pred[non_zero_ind.squeeze(), :].view(-1, 7)
# Get the various classes detected in the image
try:
img_classes = unique(image_pred_[:, -1])
except:
continue
# WE will do NMS classwise
for cls in img_classes:
# get the detections with one particular class
cls_mask = image_pred_ * \
(image_pred_[:, -1] == cls).float().unsqueeze(1)
class_mask_ind = torch.nonzero(cls_mask[:, -2]).squeeze()
image_pred_class = image_pred_[class_mask_ind].view(-1, 7)
# sort the detections such that the entry with the maximum objectness
# confidence is at the top
conf_sort_index = torch.sort(
image_pred_class[:, 4], descending=True)[1]
image_pred_class = image_pred_class[conf_sort_index]
idx = image_pred_class.size(0)
# if nms has to be done
if nms:
# For each detection
for i in range(idx):
# Get the IOUs of all boxes that come after the one we are looking at
# in the loop
try:
ious = bbox_iou(image_pred_class[i].unsqueeze(0),
image_pred_class[i + 1:],
CUDA=CUDA)
except ValueError:
break
except IndexError:
break
# Zero out all the detections that have IoU > treshhold
iou_mask = (ious < nms_conf).float().unsqueeze(1)
image_pred_class[i + 1:] *= iou_mask
# Remove the non-zero entries
non_zero_ind = torch.nonzero(
image_pred_class[:, 4]).squeeze()
image_pred_class = image_pred_class[non_zero_ind].view(
-1, 7)
# Concatenate the batch_id of the image to the detection
# this helps us identify which image does the detection correspond to
# We use a linear straucture to hold ALL the detections from the batch
# the batch_dim is flattened
# batch is identified by extra batch column
batch_ind = image_pred_class.new(
image_pred_class.size(0), 1).fill_(ind)
seq = batch_ind, image_pred_class
if not write:
output = torch.cat(seq, 1)
write = True
else:
out = torch.cat(seq, 1)
output = torch.cat((output, out))
return output
# !/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Sat Mar 24 00:12:16 2018
@author: ayooshmac
"""
def predict_transform_half(prediction, inp_dim, anchors, num_classes, CUDA=True):
batch_size = prediction.size(0)
stride = inp_dim // prediction.size(2)
bbox_attrs = 5 + num_classes
num_anchors = len(anchors)
grid_size = inp_dim // stride
prediction = prediction.view(
batch_size, bbox_attrs * num_anchors, grid_size * grid_size)
prediction = prediction.transpose(1, 2).contiguous()
prediction = prediction.view(
batch_size, grid_size * grid_size * num_anchors, bbox_attrs)
# Sigmoid the centre_X, centre_Y. and object confidencce
prediction[:, :, 0] = torch.sigmoid(prediction[:, :, 0])
prediction[:, :, 1] = torch.sigmoid(prediction[:, :, 1])
prediction[:, :, 4] = torch.sigmoid(prediction[:, :, 4])
# Add the center offsets
grid_len = np.arange(grid_size)
a, b = np.meshgrid(grid_len, grid_len)
x_offset = torch.FloatTensor(a).view(-1, 1)
y_offset = torch.FloatTensor(b).view(-1, 1)
if CUDA:
x_offset = x_offset.cuda().half()
y_offset = y_offset.cuda().half()
x_y_offset = torch.cat((x_offset, y_offset), 1).repeat(
1, num_anchors).view(-1, 2).unsqueeze(0)
prediction[:, :, :2] += x_y_offset
# log space transform height and the width
anchors = torch.HalfTensor(anchors)
if CUDA:
anchors = anchors.cuda()
anchors = anchors.repeat(grid_size * grid_size, 1).unsqueeze(0)
prediction[:, :, 2:4] = torch.exp(prediction[:, :, 2:4]) * anchors
# Softmax the class scores
prediction[:, :, 5: 5 + num_classes] = nn.Softmax(-1)(
Variable(prediction[:, :, 5: 5 + num_classes])).data
prediction[:, :, :4] *= stride
return prediction
def write_results_half(prediction, confidence, num_classes, nms=True, nms_conf=0.4):
conf_mask = (prediction[:, :, 4] > confidence).half().unsqueeze(2)
prediction = prediction * conf_mask
try:
ind_nz = torch.nonzero(
prediction[:, :, 4]).transpose(0, 1).contiguous()
except:
return 0
box_a = prediction.new(prediction.shape)
box_a[:, :, 0] = (prediction[:, :, 0] - prediction[:, :, 2] / 2)
box_a[:, :, 1] = (prediction[:, :, 1] - prediction[:, :, 3] / 2)
box_a[:, :, 2] = (prediction[:, :, 0] + prediction[:, :, 2] / 2)
box_a[:, :, 3] = (prediction[:, :, 1] + prediction[:, :, 3] / 2)
prediction[:, :, :4] = box_a[:, :, :4]
batch_size = prediction.size(0)
output = prediction.new(1, prediction.size(2) + 1)
write = False
for ind in range(batch_size):
# select the image from the batch
image_pred = prediction[ind]
# Get the class having maximum score, and the index of that class
# Get rid of num_classes softmax scores
# Add the class index and the class score of class having maximum score
max_conf, max_conf_score = torch.max(
image_pred[:, 5:5 + num_classes], 1)
max_conf = max_conf.half().unsqueeze(1)
max_conf_score = max_conf_score.half().unsqueeze(1)
seq = (image_pred[:, :5], max_conf, max_conf_score)
image_pred = torch.cat(seq, 1)
# Get rid of the zero entries
non_zero_ind = (torch.nonzero(image_pred[:, 4]))
try:
image_pred_ = image_pred[non_zero_ind.squeeze(), :]
except:
continue
# Get the various classes detected in the image
img_classes = unique(image_pred_[:, -1].long()).half()
# WE will do NMS classwise
for cls in img_classes:
# get the detections with one particular class
cls_mask = image_pred_ * \
(image_pred_[:, -1] == cls).half().unsqueeze(1)
class_mask_ind = torch.nonzero(cls_mask[:, -2]).squeeze()
image_pred_class = image_pred_[class_mask_ind]
# sort the detections such that the entry with the maximum objectness
# confidence is at the top
conf_sort_index = torch.sort(
image_pred_class[:, 4], descending=True)[1]
image_pred_class = image_pred_class[conf_sort_index]
idx = image_pred_class.size(0)
# if nms has to be done
if nms:
# For each detection
for i in range(idx):
# Get the IOUs of all boxes that come after the one we are looking at
# in the loop
try:
ious = bbox_iou(image_pred_class[i].unsqueeze(
0), image_pred_class[i + 1:])
except ValueError:
break
except IndexError:
break
# Zero out all the detections that have IoU > treshhold
iou_mask = (ious < nms_conf).half().unsqueeze(1)
image_pred_class[i + 1:] *= iou_mask
# Remove the non-zero entries
non_zero_ind = torch.nonzero(
image_pred_class[:, 4]).squeeze()
image_pred_class = image_pred_class[non_zero_ind]
# Concatenate the batch_id of the image to the detection
# this helps us identify which image does the detection correspond to
# We use a linear straucture to hold ALL the detections from the batch
# the batch_dim is flattened
# batch is identified by extra batch column
batch_ind = image_pred_class.new(
image_pred_class.size(0), 1).fill_(ind)
seq = batch_ind, image_pred_class
if not write:
output = torch.cat(seq, 1)
write = True
else:
out = torch.cat(seq, 1)
output = torch.cat((output, out))
return output