def __init__(self):
self.reader = im_reader(is_training=True)
self.net = Net()
self.rpn_loss_obj = RPN_loss(
self.net.rpn_predictions['rpn_coord_bias'],
self.net.rpn_predictions['rpn_bk_score'],
self.net.rpn_predictions['rpn_targets'],
self.net.rpn_predictions['rpn_bk_label'],
self.net.rpn_predictions['rpn_index']
)
self.roi_loss_obj = ROI_loss(
self.net.roi_predictions['reg_bias'],
self.net.roi_predictions['cls_score'],
self.net.roi_predictions['roi_targets'],
self.net.roi_predictions['roi_cls_label'],
self.net.roi_predictions['roi_inside_w']
)
self.rpn_bk_loss, self.rpn_reg_loss = self.rpn_loss_obj.add_loss()
self.roi_cls_loss, self.roi_reg_loss = self.roi_loss_obj.add_loss()
self.total_loss = self.rpn_bk_loss + self.rpn_reg_loss + \
self.roi_cls_loss+self.roi_reg_loss
self.loss_dict = {
'rpn_bk_loss': self.rpn_bk_loss,
'rpn_reg_loss': self.rpn_reg_loss,
'roi_cls_loss': self.roi_cls_loss,
'roi_reg_loss': self.roi_reg_loss,
'total_loss': self.total_loss
}
if os.path.exists('result.txt'):
with open('result.txt') as f:
self.loss = eval(f.read())
else:
self.loss = []
def __init__(self):
self.reader = im_reader(is_training=False)
self.net = Net(is_training=False)
self.saver = tf.train.Saver()
self.num_classes = len(cfg.CLASSES)
abs_in_box_diff = tf.abs(in_box_diff)
smoothL1_sign = tf.stop_gradient(
tf.to_float(tf.less(abs_in_box_diff, 1. / sigma_2)))
in_loss_box = tf.pow(in_box_diff, 2) * (sigma_2 / 2.) * smoothL1_sign \
+ (abs_in_box_diff - (0.5 / sigma_2)) * (1. - smoothL1_sign)
out_loss_box = in_loss_box
loss = tf.reduce_mean(tf.reduce_sum(out_loss_box, axis=dim))
return loss
if __name__ == "__main__":
from network import Net
from read_data import im_reader
reader = im_reader(is_training=True)
net = Net()
data = reader.generate()
_, height, width, _ = data['image'].shape
rpn_loss_obj = RPN_loss(net.rpn_predictions['rpn_coord_bias'],
net.rpn_predictions['rpn_bk_score'],
net.rpn_predictions['rpn_targets'],
net.rpn_predictions['rpn_bk_label'],
net.rpn_predictions['rpn_index'])
'pred_bias, pred_bk_score, targets, true_bk_labels, keep_index'
bk_loss, reg_loss = rpn_loss_obj.add_loss()