-
Notifications
You must be signed in to change notification settings - Fork 59
/
train_frcnn.py
195 lines (154 loc) · 9.07 KB
/
train_frcnn.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
from __future__ import division
import random
import pprint
import sys
import time
import numpy as np
from optparse import OptionParser
import pickle
from keras import backend as K
from keras.optimizers import Adam, SGD, RMSprop
from keras.layers import Input
from keras.models import Model
from faster_rcnn import config, data_generators
from faster_rcnn import losses as losses
from faster_rcnn import resnet as nn
from faster_rcnn.parser import get_data
import faster_rcnn.roi_helpers as roi_helpers
from keras.utils import generic_utils
sys.setrecursionlimit(40000)
parser = OptionParser()
parser.add_option("-p", "--path", dest="train_path", help="Path to training data.")
parser.add_option("--hf", dest="horizontal_flips", help="Augment with horizontal flips in training. (Default=false).", action="store_true", default=False)
parser.add_option("--vf", dest="vertical_flips", help="Augment with vertical flips in training. (Default=false).", action="store_true", default=False)
parser.add_option("--rot", "--rot_90", dest="rot_90", help="Augment with 90 degree rotations in training. (Default=false).",
action="store_true", default=False)
(options, args) = parser.parse_args()
if not options.train_path: # if filename is not given
parser.error('Error: path to training data must be specified. Pass --path to command line')
# pass the settings from the command line, and persist them in the config object
C = config.Config()
C.use_horizontal_flips = bool(options.horizontal_flips)
C.use_vertical_flips = bool(options.vertical_flips)
C.rot_90 = bool(options.rot_90)
all_imgs, classes_count, class_mapping = get_data(options.train_path)
C.class_mapping = class_mapping
with open(C.config_filename, 'wb') as config_f:
pickle.dump(C,config_f)
print('Config has been written to {}, and can be loaded when testing to ensure correct results'.format(C.config_filename))
train_imgs = [s for s in all_imgs if s['imageset'] == 'trainval']
val_imgs = [s for s in all_imgs if s['imageset'] == 'test']
print('Train samples {}, Val samples {}'.format(len(train_imgs), len(val_imgs)))
data_gen_train = data_generators.get_anchor_gt(train_imgs, classes_count, C, K.image_dim_ordering(), mode='train')
data_gen_val = data_generators.get_anchor_gt(val_imgs, classes_count, C, K.image_dim_ordering(), mode='val')
img_input = Input(shape=(None, None, 3))
roi_input = Input(shape=(C.num_rois, 4))
# define the base network (resnet here)
shared_layers = nn.nn_base(img_input, trainable=True)
# define the RPN, built on the base layers
num_anchors = len(C.anchor_box_scales) * len(C.anchor_box_ratios)
rpn = nn.rpn(shared_layers, num_anchors)
# define the classifer, built on the base layers
classifier = nn.classifier(shared_layers, roi_input, C.num_rois, nb_classes=len(classes_count), trainable=True)
# defining the models and a model that holds both the RPN and the classifier
model_rpn = Model(img_input, rpn[:2])
model_classifier = Model([img_input, roi_input], classifier)
model_all = Model([img_input, roi_input], rpn[:2] + classifier)
model_rpn.compile(optimizer=Adam(lr=1e-4), loss=[losses.rpn_loss_cls(num_anchors), losses.rpn_loss_regr(num_anchors)])
model_classifier.compile(optimizer=Adam(lr=1e-4), loss=[losses.class_loss_cls, losses.class_loss_regr(len(classes_count)-1)], metrics={'dense_class_{}'.format(len(classes_count)): 'accuracy'})
model_all.compile(optimizer='sgd', loss='mae')
epoch_length = 1000
num_epochs = 2000
iter_num = 0
losses = np.zeros((epoch_length, 5))
rpn_accuracy_rpn_monitor, rpn_accuracy_for_epoch = [], []
t0 = start_time = time.time()
best_loss = np.Inf
with open('out.csv', 'w') as f:
f.write('Accuracy,RPN classifier,RPN regression,Detector classifier,Detector regression,Total')
f.write('\t')
try:
for epoch_num in range(num_epochs):
progbar = generic_utils.Progbar(epoch_length)
print('Epoch {}/{}'.format(epoch_num + 1, num_epochs))
while True:
try:
if len(rpn_accuracy_rpn_monitor) == epoch_length and C.verbose:
mean_overlapping_bboxes = float(sum(rpn_accuracy_rpn_monitor))/len(rpn_accuracy_rpn_monitor)
rpn_accuracy_rpn_monitor = []
print('Average number of overlapping bounding boxes from RPN = {} for {} previous iterations'.format(mean_overlapping_bboxes, epoch_length))
if mean_overlapping_bboxes == 0:
print('RPN is not producing bounding boxes that overlap the ground truth boxes. Check RPN settings or keep training.')
X, Y, img_data = next(data_gen_train)
loss_rpn = model_rpn.train_on_batch(X, Y)
P_rpn = model_rpn.predict_on_batch(X)
R = roi_helpers.rpn_to_roi(P_rpn[0], P_rpn[1], C, K.image_dim_ordering(), use_regr=True, overlap_thresh=0.7, max_boxes=300)
# note: calc_iou converts from (x1,y1,x2,y2) to (x,y,w,h) format
X2, Y1, Y2 = roi_helpers.calc_iou(R, img_data, C, class_mapping)
neg_samples = np.where(Y1[0, :, -1] == 1)
pos_samples = np.where(Y1[0, :, -1] == 0)
if len(neg_samples) > 0:
neg_samples = neg_samples[0]
else:
neg_samples = []
if len(pos_samples) > 0:
pos_samples = pos_samples[0]
else:
pos_samples = []
rpn_accuracy_rpn_monitor.append(len(pos_samples))
rpn_accuracy_for_epoch.append((len(pos_samples)))
if len(pos_samples) < C.num_rois//2:
selected_pos_samples = pos_samples.tolist()
else:
selected_pos_samples = np.random.choice(pos_samples, C.num_rois//2, replace=False).tolist()
try:
selected_neg_samples = np.random.choice(neg_samples, C.num_rois - len(selected_pos_samples), replace=False).tolist()
except:
selected_neg_samples = np.random.choice(neg_samples, C.num_rois - len(selected_pos_samples), replace=True).tolist()
sel_samples = selected_pos_samples + selected_neg_samples
loss_class = model_classifier.train_on_batch([X, X2[:, sel_samples, :]], [Y1[:, sel_samples, :], Y2[:, sel_samples, :]])
losses[iter_num, 0] = loss_rpn[1]
losses[iter_num, 1] = loss_rpn[2]
losses[iter_num, 2] = loss_class[1]
losses[iter_num, 3] = loss_class[2]
losses[iter_num, 4] = loss_class[3]
iter_num += 1
progbar.update(iter_num, [('rpn_cls', np.mean(losses[:iter_num, 0])), ('rpn_regr', np.mean(losses[:iter_num, 1])),
('detector_cls', np.mean(losses[:iter_num, 2])), ('detector_regr', np.mean(losses[:iter_num, 3]))])
if iter_num == epoch_length:
loss_rpn_cls = np.mean(losses[:, 0])
loss_rpn_regr = np.mean(losses[:, 1])
loss_class_cls = np.mean(losses[:, 2])
loss_class_regr = np.mean(losses[:, 3])
class_acc = np.mean(losses[:, 4])
mean_overlapping_bboxes = float(sum(rpn_accuracy_for_epoch)) / len(rpn_accuracy_for_epoch)
rpn_accuracy_for_epoch = []
if C.verbose:
print('Mean number of bounding boxes from RPN overlapping ground truth boxes: {}'.format(mean_overlapping_bboxes))
print('Classifier accuracy for bounding boxes from RPN: {}'.format(class_acc))
print('Loss RPN classifier: {}'.format(loss_rpn_cls))
print('Loss RPN regression: {}'.format(loss_rpn_regr))
print('Loss Detector classifier: {}'.format(loss_class_cls))
print('Loss Detector regression: {}'.format(loss_class_regr))
print('Elapsed time: {}'.format(time.time() - start_time))
target_text_file = open('out.csv', 'a')
target_text_file.write('{},{},{},{},{},{}'.format(class_acc, loss_rpn_cls,
loss_rpn_regr, loss_class_cls, loss_class_regr,
loss_rpn_cls + loss_rpn_regr + loss_class_cls + loss_class_regr))
target_text_file.write('\t')
curr_loss = loss_rpn_cls + loss_rpn_regr + loss_class_cls + loss_class_regr
iter_num = 0
start_time = time.time()
if curr_loss < best_loss:
if C.verbose:
print('Total loss decreased from {} to {}, saving weights'.format(best_loss,curr_loss))
best_loss = curr_loss
model_all.save_weights(C.model_path)
break
except Exception as e:
print('Exception: {}'.format(e))
continue
except KeyboardInterrupt:
t1 = time.time()
print('\nIt took {:.2f}s'.format(t1-t0))
sys.exit('Keyboard Interrupt')