os.path.join(cfg.TRAIN_DIR, 'runs', cfg.exp_name))
else:
summary_writer = None
batch_per_epoch = imdb.batch_per_epoch
train_loss = 0
bbox_loss, iou_loss, cls_loss = 0., 0., 0.
cnt = 0
t = Timer()
step_cnt = 0
size_index = 0
for step in range(start_epoch * imdb.batch_per_epoch,
cfg.max_epoch * imdb.batch_per_epoch):
t.tic()
# batch
batch = imdb.next_batch(size_index)
im = batch['images']
gt_boxes = batch['gt_boxes']
gt_classes = batch['gt_classes']
dontcare = batch['dontcare']
orgin_im = batch['origin_im']
# forward
im_data = net_utils.np_to_variable(im, is_cuda=True,
volatile=False).permute(0, 3, 1, 2)
bbox_pred, iou_pred, prob_pred = net(im_data, gt_boxes, gt_classes,
dontcare, size_index)
# backward
loss = net.loss
bbox_loss += net.bbox_loss.data.cpu().numpy()
pass
exp = cc.create_experiment(cfg.exp_name)
else:
exp = cc.open_experiment(cfg.exp_name)
batch_per_epoch = imdb.batch_per_epoch
train_loss = 0
bbox_loss, iou_loss, cls_loss = 0., 0., 0.
cnt = 0
t = Timer()
step_cnt = 0
for step in range(start_epoch * imdb.batch_per_epoch,
cfg.max_epoch * imdb.batch_per_epoch):
t.tic()
# batch
batch = imdb.next_batch()
im = batch['images']
gt_boxes = batch['gt_boxes']
gt_classes = batch['gt_classes']
dontcare = batch['dontcare']
orgin_im = batch['origin_im']
# forward
im_data = net_utils.np_to_variable(im, is_cuda=True,
volatile=False).permute(0, 3, 1, 2)
net(im_data, gt_boxes, gt_classes, dontcare)
# backward
loss = net.loss
bbox_loss += net.bbox_loss.data.cpu().numpy()[0]
iou_loss += net.iou_loss.data.cpu().numpy()[0]