def main():
trained_model = cfg.trained_model
thresh = 0.5
image_dir = '/home/cory/cedl/vid/videos/vid04'
net = Darknet19()
net_utils.load_net(trained_model, net)
net.eval()
net.cuda()
print('load model successfully')
print(net)
image_extensions = ['.jpg', '.JPG', '.png', '.PNG']
image_abs_paths = sorted([
os.path.join(image_dir, name) for name in os.listdir(image_dir)
if name[-4:] in image_extensions
])
t_det = Timer()
t_total = Timer()
for i, image_path in enumerate(image_abs_paths):
t_total.tic()
image, im_data = preprocess(image_path)
im_data = net_utils.np_to_variable(im_data,
is_cuda=True,
volatile=True).permute(0, 3, 1, 2)
t_det.tic()
bbox_pred, iou_pred, prob_pred = net.forward(im_data)
det_time = t_det.toc()
# to numpy
bbox_pred = bbox_pred.data.cpu().numpy()
iou_pred = iou_pred.data.cpu().numpy()
prob_pred = prob_pred.data.cpu().numpy()
# print bbox_pred.shape, iou_pred.shape, prob_pred.shape
bboxes, scores, cls_inds = yolo_utils.postprocess(
bbox_pred, iou_pred, prob_pred, image.shape, cfg, thresh)
im2show = yolo_utils.draw_detection(image, bboxes, scores, cls_inds,
cfg)
if im2show.shape[0] > 1100:
im2show = cv2.resize(im2show, (int(
1000. * float(im2show.shape[1]) / im2show.shape[0]), 1000))
cv2.imshow('test', im2show)
total_time = t_total.toc()
format_str = 'frame: %d, (detection: %.1f fps, %.1f ms) (total: %.1f fps, %.1f ms)'
print(format_str % (i, 1. / det_time, det_time * 1000, 1. / total_time,
total_time * 1000))
t_det.clear()
t_total.clear()
key = cv2.waitKey(1)
if key == ord('q'):
break
# print bbox_pred.shape, iou_pred.shape, prob_pred.shape
bboxes, scores, cls_inds = yolo_utils.postprocess(
bbox_pred, iou_pred, prob_pred, image.shape, cfg, thresh)
im2show = yolo_utils.draw_detection(image, bboxes, scores, cls_inds, cfg)
if im2show.shape[0] > 1100:
im2show = cv2.resize(im2show,
(int(1000. *
float(im2show.shape[1]) / im2show.shape[0]),
1000))
cv2.imshow('test', im2show)
total_time = t_total.toc()
# wait_time = max(int(60 - total_time * 1000), 1)
cv2.waitKey(0)
if i % 1 == 0:
format_str = 'frame: %d, ' \
'(detection: %.1f Hz, %.1f ms) ' \
'(total: %.1f Hz, %.1f ms)'
print((format_str % (
i,
1. / det_time, det_time * 1000,
1. / total_time, total_time * 1000)))
t_total.clear()
t_det.clear()
bboxes, scores, cls_inds = yolo_utils.postprocess(
bbox_pred,
iou_pred,
prob_pred,
image.shape,
cfg,
thresh=0.3,
size_index=size_index)
im2show = yolo_utils.draw_detection(image, bboxes, scores,
cls_inds, cfg)
summary_writer.add_image('predict', im2show, step)
train_loss = 0
bbox_loss, iou_loss, cls_loss = 0., 0., 0.
cnt = 0
t.clear()
size_index = randint(0, len(cfg.multi_scale_inp_size) - 1)
print("image_size {}".format(cfg.multi_scale_inp_size[size_index]))
if step > 0 and (step % imdb.batch_per_epoch == 0):
if imdb.epoch in cfg.lr_decay_epochs:
lr *= cfg.lr_decay
optimizer = torch.optim.SGD(net.parameters(),
lr=lr,
momentum=cfg.momentum,
weight_decay=cfg.weight_decay)
save_name = os.path.join(cfg.train_output_dir,
'{}_{}.h5'.format(cfg.exp_name, imdb.epoch))
net_utils.save_net(save_name, net)
print(('save model: {}'.format(save_name)))
def run_detection(im_root, result_root, conf_threshold):
# get symbol
pprint.pprint(config)
config.symbol = 'resnet_v1_101_rfcn_dcn' if not args.rfcn_only else 'resnet_v1_101_rfcn'
sym_instance = eval(config.symbol + '.' + config.symbol)()
sym = sym_instance.get_symbol(config, is_train=False)
# set up class names
num_classes = 81
classes = [
'person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train',
'truck', 'boat', 'traffic light', 'fire hydrant', 'stop sign',
'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep',
'cow', 'elephant', 'bear', 'zebra', 'giraffe', 'backpack', 'umbrella',
'handbag', 'tie', 'suitcase', 'frisbee', 'skis', 'snowboard',
'sports ball', 'kite', 'baseball bat', 'baseball glove', 'skateboard',
'surfboard', 'tennis racket', 'bottle', 'wine glass', 'cup', 'fork',
'knife', 'spoon', 'bowl', 'banana', 'apple', 'sandwich', 'orange',
'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake', 'chair',
'couch', 'potted plant', 'bed', 'dining table', 'toilet', 'tv',
'laptop', 'mouse', 'remote', 'keyboard', 'cell phone', 'microwave',
'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock', 'vase',
'scissors', 'teddy bear', 'hair drier', 'toothbrush'
]
print('detection in {}'.format(im_root))
im_names = sorted(os.listdir(im_root))
# get predictor
data_names = ['data', 'im_info']
label_names = []
data = []
for idx, im_name in enumerate(im_names[:2]):
im_file = os.path.join(im_root, im_name)
im = cv2.imread(im_file,
cv2.IMREAD_COLOR | cv2.IMREAD_IGNORE_ORIENTATION)
target_size = config.SCALES[0][0]
max_size = config.SCALES[0][1]
im, im_scale = resize(im,
target_size,
max_size,
stride=config.network.IMAGE_STRIDE)
im_tensor = transform(im, config.network.PIXEL_MEANS)
im_info = np.array(
[[im_tensor.shape[2], im_tensor.shape[3], im_scale]],
dtype=np.float32)
data.append({'data': im_tensor, 'im_info': im_info})
data = [[mx.nd.array(data[i][name]) for name in data_names]
for i in xrange(len(data))]
max_data_shape = [[('data', (1, 3, max([v[0] for v in config.SCALES]),
max([v[1] for v in config.SCALES])))]]
provide_data = [[(k, v.shape) for k, v in zip(data_names, data[i])]
for i in xrange(len(data))]
provide_label = [None for i in xrange(len(data))]
arg_params, aux_params = load_param(
cur_path + '/../model/' +
('rfcn_dcn_coco' if not args.rfcn_only else 'rfcn_coco'),
config.TEST.test_epoch,
process=True)
predictor = Predictor(sym,
data_names,
label_names,
context=[mx.gpu(0)],
max_data_shapes=max_data_shape,
provide_data=provide_data,
provide_label=provide_label,
arg_params=arg_params,
aux_params=aux_params)
# nms = gpu_nms_wrapper(config.TEST.NMS, 0)
# nms = soft_nms_wrapper(config.TEST.NMS, method=2)
nms = gpu_soft_nms_wrapper(config.TEST.NMS, method=2, device_id=0)
nms_t = Timer()
for idx, im_name in enumerate(im_names):
im_file = os.path.join(im_root, im_name)
im = cv2.imread(im_file,
cv2.IMREAD_COLOR | cv2.IMREAD_IGNORE_ORIENTATION)
origin_im = im.copy()
target_size = config.SCALES[0][0]
max_size = config.SCALES[0][1]
im, im_scale = resize(im,
target_size,
max_size,
stride=config.network.IMAGE_STRIDE)
im_tensor = transform(im, config.network.PIXEL_MEANS)
im_info = np.array(
[[im_tensor.shape[2], im_tensor.shape[3], im_scale]],
dtype=np.float32)
# input
data = [mx.nd.array(im_tensor), mx.nd.array(im_info)]
data_batch = mx.io.DataBatch(data=[data],
label=[],
pad=0,
index=idx,
provide_data=[[
(k, v.shape)
for k, v in zip(data_names, data)
]],
provide_label=[None])
scales = [
data_batch.data[i][1].asnumpy()[0, 2]
for i in xrange(len(data_batch.data))
]
tic()
scores, boxes, data_dict = im_detect(predictor, data_batch, data_names,
scales, config)
boxes = boxes[0].astype('f')
scores = scores[0].astype('f')
dets_nms = []
for j in range(1, scores.shape[1]):
cls_scores = scores[:, j, np.newaxis]
cls_boxes = boxes[:,
4:8] if config.CLASS_AGNOSTIC else boxes[:, j *
4:(j +
1) *
4]
cls_dets = np.hstack((cls_boxes, cls_scores))
nms_t.tic()
keep = nms(cls_dets)
nms_t.toc()
cls_dets = cls_dets[keep, :]
cls_dets = cls_dets[cls_dets[:, -1] > 0.7, :]
dets_nms.append(cls_dets)
print 'testing {} {:.2f}ms'.format(im_name, toc() * 1000)
print 'nms: {:.2f}ms'.format(nms_t.total_time * 1000)
nms_t.clear()
# save results
person_dets = dets_nms[0]
with open(os.path.join(result_root, '{:04d}.txt'.format(idx)),
'w') as f:
f.write('{}\n'.format(len(person_dets)))
for det in person_dets:
x1, y1, x2, y2, s = det
w = x2 - x1
h = y2 - y1
f.write('0 {} {} {} {} {}\n'.format(s, w, h, x1, y1))
# visualize
im = origin_im
# im = cv2.cvtColor(im, cv2.COLOR_BGR2RGB)
im = show_boxes_cv2(im, dets_nms, classes, 1)
cv2.imshow('det', im)
cv2.waitKey(1)
net.loss.backward()
optimizer.step()
duration = timer.toc()
if step % cfg.disp_interval == 0:
train_loss /= cnt
bbox_loss /= cnt
iou_loss /= cnt
cls_loss /= cnt
progress_in_epoch = (step % imdb.batch_per_epoch) / imdb.batch_per_epoch
print('epoch: %d, step: %d (%.2f %%),'
'loss: %.3f, bbox_loss: %.3f, iou_loss: %.3f, cls_loss: %.3f (%.2f s/batch)' % (
imdb.epoch, step, progress_in_epoch * 100, train_loss, bbox_loss, iou_loss, cls_loss, duration))
with open(cfg.log_file, 'a+') as log:
log.write('%d, %d, %.3f, %.3f, %.3f, %.3f, %.2f\n' % (
imdb.epoch, step, train_loss, bbox_loss, iou_loss, cls_loss, duration))
if use_tensorboard and step % cfg.log_interval == 0:
exp.add_scalar_value('loss_train', train_loss, step=step)
exp.add_scalar_value('loss_bbox', bbox_loss, step=step)
exp.add_scalar_value('loss_iou', iou_loss, step=step)
exp.add_scalar_value('loss_cls', cls_loss, step=step)
exp.add_scalar_value('learning_rate', get_optimizer_lr(optimizer), step=step)
train_loss = 0
bbox_loss, iou_loss, cls_loss = 0., 0., 0.
cnt = 0
timer.clear()
imdb.close()
accuracy_epoch, twod_dists, threed_dists, test_loss_epoch = test_net(
net2,
imdb_cullnettest,
dataloader_cullnettest,
args,
test_output_dir,
args.image_size_index,
args.batch_size,
objpoints3D,
corners_3d,
vertices,
thresh=args.thresh,
vis=args.vis)
_t.clear()
if args.save_results_bool:
resultsdist_dir = cfg.TEST_DIR + '/' + cfg.args.datadirname + '_topk' + str(
args.topk) + '_nearby' + str(args.nearby_test) + '_cullnetyolov3'
if not os.path.exists(resultsdist_dir):
os.makedirs(resultsdist_dir)
save_resultsdist(twod_dists, threed_dists, resultsdist_dir,
args.class_name)
save_results(cfg.args.datadirname + '_topk' + str(args.topk) +
'_nearby' + str(args.nearby_test),
args.class_name,
accuracy_epoch[0],
accuracy_epoch[1],
def main():
output_dir = '../output'
output_template_dir = '../output_template'
kitti_output_dir = '../kitti_det_output'
input_file_list = '/home/cory/project/yolo2-pytorch/train_data/kitti/kitti_val_images.txt'
# input_file_list = '/home/cory/project/yolo2-pytorch/flow/w01_imgs.txt'
vis_enable = False
thresh = 0.5
trained_model = '/home/cory/project/yolo2-pytorch/models/training/kitti_new_2_flow_center_ft_flownet2_joint/' \
'kitti_new_2_flow_center_ft_flownet2_joint_30.h5'
shutil.rmtree(output_dir, ignore_errors=True)
shutil.rmtree(kitti_output_dir, ignore_errors=True)
shutil.copytree(output_template_dir, output_dir)
os.makedirs(kitti_output_dir)
net = Darknet19(cfg)
net_utils.load_net(trained_model, net)
net.eval()
net.cuda()
print(trained_model)
print('load model successfully')
img_files = open(input_file_list)
image_abs_paths = img_files.readlines()
image_abs_paths = [f.strip() for f in image_abs_paths]
t_det = Timer()
t_total = Timer()
for i, image_path in enumerate(image_abs_paths):
t_total.tic()
image, im_data = preprocess(image_path)
im_data = net_utils.np_to_variable(im_data,
is_cuda=True,
volatile=True).permute(0, 3, 1, 2)
t_det.tic()
bbox_pred, iou_pred, prob_pred = net.forward(im_data)
det_time = t_det.toc()
bbox_pred = bbox_pred.data.cpu().numpy()
iou_pred = iou_pred.data.cpu().numpy()
prob_pred = prob_pred.data.cpu().numpy()
bboxes, scores, cls_inds = yolo_utils.postprocess(
bbox_pred, iou_pred, prob_pred, image.shape, cfg, thresh)
det_obj = detection_objects(bboxes, scores, cls_inds)
save_as_kitti_format(i, det_obj, kitti_output_dir, src_label='kitti')
total_time = t_total.toc()
format_str = 'frame: %d, (detection: %.1f fps, %.1f ms) (total: %.1f fps, %.1f ms) %s'
print(format_str % (i, 1. / det_time, det_time * 1000, 1. / total_time,
total_time * 1000, image_path))
t_det.clear()
t_total.clear()
if vis_enable:
im2show = yolo_utils.draw_detection(image, bboxes, scores,
cls_inds, cfg)
cv2.imshow('detection', im2show)
cv2.imwrite(output_dir + '/detection/{:04d}.jpg'.format(i),
im2show)
key = cv2.waitKey(0)
if key == ord('q'):
break
def train_main():
choice = 1
if choice == 0:
dataset_yaml = '/home/cory/project/yolo2-pytorch/cfgs/config_voc.yaml'
exp_yaml = '/home/cory/project/yolo2-pytorch/cfgs/exps/voc0712/voc0712_baseline_v3_rand.yaml'
gpu_id = 0
else:
dataset_yaml = '/home/cory/project/yolo2-pytorch/cfgs/config_kitti.yaml'
exp_yaml = '/home/cory/project/yolo2-pytorch/cfgs/exps/kitti/kitti_new_2_flow_center_ft_flownet2_joint.yaml'
gpu_id = 1
cfg = load_cfg_yamls([dataset_yaml, exp_yaml])
# runtime setting
os.environ['CUDA_VISIBLE_DEVICES'] = str(gpu_id)
os.makedirs(cfg['train_output_dir'], exist_ok=True)
# data loader
batch_size = cfg['train_batch_size']
dataset = DetectionDataset(cfg)
print('load dataset succeeded')
net = Darknet19(cfg)
start_epoch, use_model = read_ckp(cfg)
net_utils.load_net(use_model, net)
net.cuda()
net.train()
print('load net succeeded')
# show training parameters
print('-------------------------------')
print('pid', os.getpid())
print('gpu_id', os.environ.get('CUDA_VISIBLE_DEVICES'))
print('use_model', use_model)
print('exp_name', cfg['exp_name'])
print('dataset', cfg['dataset_name'])
print('optimizer', cfg['optimizer'])
print('opt_param', cfg['opt_param'])
print('train_batch_size', cfg['train_batch_size'])
print('start_epoch', start_epoch)
print('lr', lookup_lr(cfg, start_epoch))
print('inp_size', cfg['inp_size'])
print('inp_size_candidates', cfg['inp_size_candidates'])
print('-------------------------------')
timer = Timer()
try:
for epoch in range(start_epoch, cfg['max_epoch']):
time_epoch_begin = time.time()
optimizer = get_optimizer(cfg, net, epoch)
dataloader = DataLoaderX(dataset,
batch_size=batch_size,
shuffle=True,
num_workers=4,
pin_memory=False)
for step, data in enumerate(dataloader):
timer.tic()
barrier = Barrier()
images, labels = data
# debug_and_vis(data)
im_data = Variable(images.cuda())
barrier.add(1)
bbox_pred, iou_pred, class_pred = net.forward(im_data)
barrier.add(2)
# build training target
network_h = int(im_data.data.size()[2])
network_w = int(im_data.data.size()[3])
network_size_wh = np.array([network_w, network_h]) # (w, h)
net_bbox_loss, net_iou_loss, net_class_loss = training_target(
cfg, bbox_pred, class_pred, labels, network_size_wh,
iou_pred)
barrier.add(3)
# backward
optimizer.zero_grad()
net_loss = net_bbox_loss + net_iou_loss + net_class_loss
net_loss.backward()
optimizer.step()
barrier.add(4)
duration = timer.toc()
if step % cfg['disp_interval'] == 0:
# loss for this step
bbox_loss = net_bbox_loss.data.cpu().numpy()[0]
iou_loss = net_iou_loss.data.cpu().numpy()[0]
cls_loss = net_class_loss.data.cpu().numpy()[0]
train_loss = net_loss.data.cpu().numpy()[0]
barrier.add(5)
progress_in_epoch = (step + 1) * batch_size / len(dataset)
print(
'epoch %d, step %d (%.2f %%) '
'loss: %.3f, bbox_loss: %.3f, iou_loss: %.3f, cls_loss: %.3f (%.2f s/batch)'
% (epoch, step, progress_in_epoch * 100, train_loss,
bbox_loss, iou_loss, cls_loss, duration))
with open(cfg['train_output_dir'] + '/train.log',
'a+') as log:
log.write('%d, %d, %.3f, %.3f, %.3f, %.3f, %.2f\n' %
(epoch, step, train_loss, bbox_loss,
iou_loss, cls_loss, duration))
timer.clear()
barrier.add(6)
# barrier.print()
# epoch_done
time_epoch_end = time.time()
print('{:.2f} seconds for this epoch'.format(time_epoch_end -
time_epoch_begin))
# save trained weights
ckp_epoch = epoch + 1
save_name = os.path.join(
cfg['train_output_dir'],
'{}_{}.h5'.format(cfg['exp_name'], ckp_epoch))
net_utils.save_net(save_name, net)
print('save model: {}'.format(save_name))
# update check_point file
ckp = open(
os.path.join(cfg['train_output_dir'], 'check_point.txt'), 'w')
ckp.write(str(ckp_epoch))
ckp.close()
except KeyboardInterrupt:
exit(1)
def main():
# get symbol
pprint.pprint(config)
config.symbol = 'resnet_v1_101_rfcn_dcn' if not args.rfcn_only else 'resnet_v1_101_rfcn'
sym_instance = eval(config.symbol + '.' + config.symbol)()
sym = sym_instance.get_symbol(config, is_train=False)
# set up class names
num_classes = 81
classes = [
'person', 'bicycle', 'car', 'motorcycle', 'airplane', 'bus', 'train',
'truck', 'boat', 'traffic light', 'fire hydrant', 'stop sign',
'parking meter', 'bench', 'bird', 'cat', 'dog', 'horse', 'sheep',
'cow', 'elephant', 'bear', 'zebra', 'giraffe', 'backpack', 'umbrella',
'handbag', 'tie', 'suitcase', 'frisbee', 'skis', 'snowboard',
'sports ball', 'kite', 'baseball bat', 'baseball glove', 'skateboard',
'surfboard', 'tennis racket', 'bottle', 'wine glass', 'cup', 'fork',
'knife', 'spoon', 'bowl', 'banana', 'apple', 'sandwich', 'orange',
'broccoli', 'carrot', 'hot dog', 'pizza', 'donut', 'cake', 'chair',
'couch', 'potted plant', 'bed', 'dining table', 'toilet', 'tv',
'laptop', 'mouse', 'remote', 'keyboard', 'cell phone', 'microwave',
'oven', 'toaster', 'sink', 'refrigerator', 'book', 'clock', 'vase',
'scissors', 'teddy bear', 'hair drier', 'toothbrush'
]
# load demo data
image_names = [
'lindau_000024_000019_leftImg8bit.png',
'COCO_test2015_000000000891.jpg', 'COCO_test2015_000000001669.jpg'
]
data = []
for im_name in image_names:
assert os.path.exists(cur_path + '/../demo/' + im_name), (
'%s does not exist'.format('../demo/' + im_name))
im = cv2.imread(cur_path + '/../demo/' + im_name,
cv2.IMREAD_COLOR | cv2.IMREAD_IGNORE_ORIENTATION)
target_size = config.SCALES[0][0]
max_size = config.SCALES[0][1]
im, im_scale = resize(im,
target_size,
max_size,
stride=config.network.IMAGE_STRIDE)
im_tensor = transform(im, config.network.PIXEL_MEANS)
im_info = np.array(
[[im_tensor.shape[2], im_tensor.shape[3], im_scale]],
dtype=np.float32)
data.append({'data': im_tensor, 'im_info': im_info})
# get predictor
data_names = ['data', 'im_info']
label_names = []
data = [[mx.nd.array(data[i][name]) for name in data_names]
for i in xrange(len(data))]
max_data_shape = [[('data', (1, 3, max([v[0] for v in config.SCALES]),
max([v[1] for v in config.SCALES])))]]
provide_data = [[(k, v.shape) for k, v in zip(data_names, data[i])]
for i in xrange(len(data))]
provide_label = [None for i in xrange(len(data))]
arg_params, aux_params = load_param(
cur_path + '/../model/' +
('rfcn_dcn_coco' if not args.rfcn_only else 'rfcn_coco'),
config.TEST.test_epoch,
process=True)
predictor = Predictor(sym,
data_names,
label_names,
context=[mx.gpu(0)],
max_data_shapes=max_data_shape,
provide_data=provide_data,
provide_label=provide_label,
arg_params=arg_params,
aux_params=aux_params)
# nms = gpu_nms_wrapper(config.TEST.NMS, 0)
# nms = soft_nms_wrapper(config.TEST.NMS, method=2)
nms = gpu_soft_nms_wrapper(config.TEST.NMS, method=2, device_id=0)
# warm up
for j in xrange(2):
data_batch = mx.io.DataBatch(data=[data[0]],
label=[],
pad=0,
index=0,
provide_data=[[
(k, v.shape)
for k, v in zip(data_names, data[0])
]],
provide_label=[None])
scales = [
data_batch.data[i][1].asnumpy()[0, 2]
for i in xrange(len(data_batch.data))
]
scores, boxes, data_dict = im_detect(predictor, data_batch, data_names,
scales, config)
# test
nms_t = Timer()
for idx, im_name in enumerate(image_names):
data_batch = mx.io.DataBatch(
data=[data[idx]],
label=[],
pad=0,
index=idx,
provide_data=[[(k, v.shape)
for k, v in zip(data_names, data[idx])]],
provide_label=[None])
scales = [
data_batch.data[i][1].asnumpy()[0, 2]
for i in xrange(len(data_batch.data))
]
tic()
scores, boxes, data_dict = im_detect(predictor, data_batch, data_names,
scales, config)
boxes = boxes[0].astype('f')
scores = scores[0].astype('f')
dets_nms = []
for j in range(1, scores.shape[1]):
cls_scores = scores[:, j, np.newaxis]
cls_boxes = boxes[:,
4:8] if config.CLASS_AGNOSTIC else boxes[:, j *
4:(j +
1) *
4]
cls_dets = np.hstack((cls_boxes, cls_scores))
nms_t.tic()
keep = nms(cls_dets)
nms_t.toc()
cls_dets = cls_dets[keep, :]
cls_dets = cls_dets[cls_dets[:, -1] > 0.7, :]
dets_nms.append(cls_dets)
print 'testing {} {:.2f}ms'.format(im_name, toc() * 1000)
print 'nms: {:.2f}ms'.format(nms_t.average_time * 1000)
nms_t.clear()
# visualize
im = cv2.imread(cur_path + '/../demo/' + im_name)
im = cv2.cvtColor(im, cv2.COLOR_BGR2RGB)
show_boxes(im, dets_nms, classes, 1)
print 'done'
def main():
shutil.rmtree('output', ignore_errors=True)
shutil.copytree('output_template', 'output')
shutil.rmtree('kitti_det_output', ignore_errors=True)
os.makedirs('kitti_det_output')
trained_model = '/home/cory/yolo2-pytorch/models/training/kitti_new_2/kitti_new_2_100.h5'
thresh = 0.5
use_kitti = True
image_dir = '/home/cory/KITTI_Dataset/data_object_image_2/training/image_2'
net = Darknet19()
net_utils.load_net(trained_model, net)
net.eval()
net.cuda()
print('load model successfully')
# print(net)
def str_index(filename):
if use_kitti:
return filename
begin_pos = filename.rfind('_') + 1
end_pos = filename.rfind('.')
str_v = filename[begin_pos:end_pos]
return int(str_v)
image_extensions = ['.jpg', '.JPG', '.png', '.PNG']
img_files = open(
'/home/cory/yolo2-pytorch/train_data/kitti/kitti_val_images.txt')
image_abs_paths = img_files.readlines()
image_abs_paths = [f.strip() for f in image_abs_paths]
'''image_abs_paths = sorted([os.path.join(image_dir, name)
for name in os.listdir(image_dir)
if name[-4:] in image_extensions],
key=str_index)'''
key_frame_path = ''
detection_period = 5
use_flow = False
kitti_filename = 'yolo_flow_kitti_det.txt'
try:
os.remove(kitti_filename)
except OSError:
pass
t_det = Timer()
t_total = Timer()
for i, image_path in enumerate(image_abs_paths):
t_total.tic()
image, im_data = preprocess(image_path)
im_data = net_utils.np_to_variable(im_data,
is_cuda=True,
volatile=True).permute(0, 3, 1, 2)
layer_of_flow = 'conv4'
t_det.tic()
bbox_pred, iou_pred, prob_pred = net.forward(im_data)
det_time = t_det.toc()
# to numpy
bbox_pred = bbox_pred.data.cpu().numpy()
iou_pred = iou_pred.data.cpu().numpy()
prob_pred = prob_pred.data.cpu().numpy()
# print bbox_pred.shape, iou_pred.shape, prob_pred.shape
bboxes, scores, cls_inds = yolo_utils.postprocess(
bbox_pred, iou_pred, prob_pred, image.shape, cfg, thresh)
det_obj = detection_objects(bboxes, scores, cls_inds)
save_as_kitti_format(i, det_obj, kitti_filename, src_label='kitti')
vis_enable = False
if vis_enable:
im2show = yolo_utils.draw_detection(image, bboxes, scores,
cls_inds, cfg)
cv2.imshow('detection', im2show)
cv2.imwrite('output/detection/{:04d}.jpg'.format(i), im2show)
total_time = t_total.toc()
format_str = 'frame: %d, (detection: %.1f fps, %.1f ms) (total: %.1f fps, %.1f ms)'
print(format_str % (i, 1. / det_time, det_time * 1000, 1. / total_time,
total_time * 1000))
t_det.clear()
t_total.clear()
if vis_enable:
key = cv2.waitKey(0)
if key == ord('q'):
break
def main():
root_dir = '/home/cory/project/yolo2-pytorch'
output_dir = root_dir + '/output'
output_template_dir = root_dir + '/output_template'
kitti_filename = root_dir + '/yolo_flow_kitti_det.txt'
shutil.rmtree(output_dir, ignore_errors=True)
shutil.copytree(output_template_dir, output_dir)
# trained_model = cfg.trained_model
# trained_model = '/home/cory/yolo2-pytorch/models/training/kitti_new_2/kitti_new_2_100.h5'
# trained_model = '/home/cory/project/yolo2-pytorch/models/training/kitti_baseline_v3/kitti_baseline_v3_80.h5'
trained_model = '/home/cory/project/yolo2-pytorch/models/training/kitti_new_2_flow_center_ft/kitti_new_2_flow_center_ft_50.h5'
# trained_model = '/home/cory/yolo2-pytorch/models/training/kitti_new_2_flow_ft/kitti_new_2_flow_ft_2.h5'
# trained_model = '/home/cory/yolo2-pytorch/models/training/voc0712_obj_scale/voc0712_obj_scale_1.h5'
# trained_model = '/home/cory/yolo2-pytorch/models/training/kitti_det_new_2/kitti_det_new_2_40.h5'
# trained_model = '/home/cory/yolo2-pytorch/models/training/kitti_det_new_2/kitti_det_new_2_10.h5'
thresh = 0.5
# car = 1 5
# pedestrian = 13 17
net = Darknet19()
net_utils.load_net(trained_model, net)
net.eval()
net.cuda()
print('load model successfully')
# print(net)
img_files = open(
'/home/cory/project/yolo2-pytorch/train_data/kitti/kitti_val_images.txt'
)
# img_files = open('/home/cory/project/yolo2-pytorch/train_data/kitti/0001_images.txt')
# img_files = open('/home/cory/yolo2-pytorch/train_data/ImageNetVID_test.txt')
# img_files = open('/home/cory/yolo2-pytorch/train_data/vid04_images.txt')
image_abs_paths = img_files.readlines()
image_abs_paths = [f.strip() for f in image_abs_paths]
image_abs_paths = image_abs_paths[500:]
key_frame_path = ''
detection_period = 1
use_flow = False
layer_of_flow = 'conv4'
try:
os.remove(kitti_filename)
except OSError:
pass
t_det = Timer()
t_total = Timer()
for i, image_path in enumerate(image_abs_paths):
t_total.tic()
t0 = time.time()
image, im_data = preprocess(image_path)
im_data = net_utils.np_to_variable(im_data,
is_cuda=True,
volatile=True).permute(0, 3, 1, 2)
t1 = time.time()
print('t1', t1 - t0)
# key frame
if use_flow and i % detection_period == 0:
key_frame_path = image_path
# conv5 feature map
feature = net.get_feature_map(im_data=im_data, layer=layer_of_flow)
feature = feature.data.cpu().numpy()
feature_map_all = plot_feature_map(feature, resize_ratio=1)
# cv2.imshow('feature_map', feature_map_all)
cv2.imwrite(output_dir + '/feature_map/{:04d}.jpg'.format(i),
feature_map_all * 255)
t_det.tic()
if use_flow:
conv5_shifted_gpu = detect_by_flow(i, feature, image, image_path,
key_frame_path, output_dir)
bbox_pred, iou_pred, prob_pred = net.feed_feature(
Variable(conv5_shifted_gpu), layer=layer_of_flow)
else:
bbox_pred, iou_pred, prob_pred = net.forward(im_data)
det_time = t_det.toc()
t2 = time.time()
print('t2', t2 - t1)
# to numpy
bbox_pred = bbox_pred.data.cpu().numpy()
iou_pred = iou_pred.data.cpu().numpy()
prob_pred = prob_pred.data.cpu().numpy()
t3 = time.time()
print('t3', t3 - t2)
# print bbox_pred.shape, iou_pred.shape, prob_pred.shape
bboxes, scores, cls_inds = yolo_utils.postprocess(
bbox_pred, iou_pred, prob_pred, image.shape, cfg, thresh)
t4 = time.time()
print('t4', t4 - t3)
det_obj = detection_objects(bboxes, scores, cls_inds)
save_as_kitti_format(i, det_obj, kitti_filename, src_label='kitti')
im2show = yolo_utils.draw_detection(image, bboxes, scores, cls_inds,
cfg)
cv2.imshow('detection', im2show)
cv2.imwrite(output_dir + '/detection/{:04d}.jpg'.format(i), im2show)
total_time = t_total.toc()
format_str = 'frame: %d, (detection: %.1f fps, %.1f ms) (total: %.1f fps, %.1f ms)'
print(format_str % (i, 1. / det_time, det_time * 1000, 1. / total_time,
total_time * 1000))
t5 = time.time()
print('t5', t5 - t4)
t_det.clear()
t_total.clear()
key = cv2.waitKey(1)
if key == ord('q'):
break
def test_ontime(
self,
path_in='demo',
path_out='./interface/tmp/wx_d',
dec_flag=0,
cv_im=[],
da_flag=1,
retrival_params=['自动', None, None, '全选', '全选', '全选', '全选', '全选',
'全选']):
#Read Infomation
#print "Test"
t_det = Timer()
t_total = Timer()
# if dec_flag==1:
# shutil.rmtree("./result/cut/")
# os.mkdir("./result/cut/")
# im_fnames = ['person.jpg']
im_fnames = sorted(
(fname for fname in os.listdir(path_in)
if os.path.splitext(fname)[-1] == '.jpg')) # shuffle data
im_fname = os.path.join(path_in, im_fnames[0])
if cv_im == []:
(image, im_data, im_name) = preprocess(im_fname)
exit()
else:
#print "OOOOOOOOOOOOOOOOOOOOOOJBK"
image = cv_im
im_name = im_fname
im_data = get_ImData(cv_im)
t_total.tic()
im_data = net_utils.np_to_variable(im_data,
is_cuda=True,
volatile=True).permute(0, 3, 1, 2)
im_name = os.path.split(im_name)[-1]
# print im_name
t_det.tic()
if dec_flag:
self.people_sex = None
self.people_age = 20
#if retrival_params[0] == '自动' or retrival_params[-1] == '自动':
if '自动' in retrival_params[0] or '自动' in retrival_params[-1]:
try:
#self.img_uploader.run(im_fname)
self.result = self.face.run(im_fname)
#print self.result
if len(self.result) == 1:
if self.result[0][u'faceAttributes'][
u'gender'] == u'female':
self.people_sex = '2'
else:
self.people_sex = '1'
#print "people_sex:"
#print self.people_sex
except:
print "can't contact face identify"
pass
#print 'sex:'
#print self.people_sex
#print "ooooooooooooooooooooooooooooooooooooooooooo"
#print "oooooooooooooooo1"
#print "oook"
bbox_pred, iou_pred, prob_pred = self.net(im_data)
det_time = t_det.toc()
det_time = t_det.toc()
# to numpy
bbox_pred = bbox_pred.data.cpu().numpy()
iou_pred = iou_pred.data.cpu().numpy()
prob_pred = prob_pred.data.cpu().numpy()
# print bbox_pred.shape, iou_pred.shape, prob_pred.shape
#print "oooooooooooooooo2"
self.bboxes, self.scores, self.cls_inds = yolo_utils.postprocess(
bbox_pred, iou_pred, prob_pred, image.shape, cfg, self.thresh)
#print image.shape
#print "bboxes"
#print bboxes
#print "HAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA"
cls_res = []
cls_score = []
cls_res_top5 = []
cls_score_top5 = []
flag = 0
for i, bbox in enumerate(self.bboxes):
#print "bbox",bbox
cut_image = image[bbox[1]:bbox[3], bbox[0]:bbox[2]]
res_num, res_score = cloth_num(cut_image, self.model_res)
cls_res.append(self.num_classes[res_num[0]])
cls_re = []
for n in range(10):
cls_re.append(self.num_classes[res_num[n]])
#print "++++++++++++++++++++++++++++++"+str(n)
#print Cnum[0][n],res_num[0]
#print self.num_classes[Cnum[0][n]]
cls_res_top5.append(cls_re)
cls_score_top5.append(res_score)
#print "-------------"
#print res_score
#If the adjacent two types of differentiation is too small,it is considered that the category that the category can not be determined
if res_score[
0] < 12 and res_score[1] * 1.0 / res_score[0] > 0.9:
#print res_score[1]*1.0/res_score[0]
cls_score.append(0)
else:
#If two overlapping frames of the same category exceed 0.4,only the box with the largest weight is saved
for j, obox in enumerate(self.bboxes[:i]):
# (bbox[0], bbox[1]), (bbox[2], bbox[3])
if obox[2] > bbox[0] and obox[3] > bbox[1] and obox[
0] < bbox[2] and obox[1] < bbox[3]:
print "------------------------xiangjiao------------------------------"
box_inter = (max(obox[0],
bbox[0]), max(obox[1], bbox[1]),
min(obox[2],
bbox[2]), min(obox[3], bbox[3]))
area1 = (bbox[2] - bbox[0]) * (bbox[3] - bbox[1])
area2 = (obox[2] - obox[0]) * (obox[3] - obox[1])
area_min = min((area1, area2))
area_inter = (box_inter[2] - box_inter[0]) * (
box_inter[3] - box_inter[1])
#print area_min,area_inter
if area_inter * 1.0 / area_min >= 0.5:
print "====================YEEEEEES++++++++++++++++"
#if cls_res[i]==cls_res[j]:
if res_score[0] > cls_score[j]:
if cls_score[j] != 0:
cls_score[j] = 1
else:
res_score[0] = 1
break
cls_score.append(res_score[0])
#print res_num
#cls_score.append(res_score)
#print "resnet"
#print cls_res,cls_score
#cut_for_intel = cv2.resize(cut_image, (800, 500))
#cut_for_intel = cv2.resize(cut_image,(int(1000. * float(cut_image.shape[1]) / cut_image.shape[0]), 1000))
#cv2.imwrite("./result/cut/%d_%s"%(i,im_name),cut_for_intel)
self.cls_res = cls_res
self.cls_score = cls_score
self.cls_res_top5 = cls_res_top5
self.cls_score_top5 = cls_score_top5
#print "bbboxes"
#print self.bboxes
# im2show = yolo_utils.draw_detection_rec(image, self.bboxes, self.scores, self.cls_res,self.cls_score,f_info,f_pic,self.cls_res_top5,self.cls_score_top5,f_pic_like,f_pic_rec,f_pic_rec_like,self.cls_inds)
else:
# 用于显示
#print "bbboxes"
#print self.bboxes
#im2show = yolo_utils.draw_detection_rec(image, self.bboxes, self.scores, self.cls_res,self.cls_score,f_info,f_pic,self.cls_res_top5,self.cls_score_top5,f_pic_like,f_pic_rec,f_pic_rec_like,self.cls_inds)
f_info = open(InfoDir, 'w')
f_pic = open(InfoPicPath, 'w')
f_pic_like = open(InfoPicLikePath, 'w')
f_pic_rec = open(InfoPicPathRec, 'w')
f_pic_rec_like = open(InfoPicLikePathRec, 'w')
im2show = self.draw_detection_rec(image,
self.bboxes,
self.cls_inds,
self.scores,
self.cls_res_top5,
self.cls_score_top5,
f_info,
f_pic,
f_pic_like,
f_pic_rec,
f_pic_rec_like,
flag=1,
sex_dec=self.people_sex,
age_dec=self.people_age,
retrival_params=retrival_params)
if im2show.shape[0] > 1100:
im2show = cv2.resize(im2show, (int(
1000. * float(im2show.shape[1]) / im2show.shape[0]), 1000))
cv2.imwrite(os.path.join(path_out, im_name), im2show)
f_info.close()
f_pic.close()
f_pic_like.close()
f_pic_rec.close()
f_pic_rec_like.close()
t_total.clear()
t_det.clear()
def test(
self,
path_in='demo',
path_out='./interface/tmp/wx_d',
cut_path='./result/cut/',
retrival_params=['自动', None, None, '全选', '全选', '全选', '全选', '全选',
'全选']):
#Read Infomation
#params---->sex，prince1,prince2,dress,top,bottom,version,style,age_value
#print "Test"
t_det = Timer()
t_total = Timer()
# im_fnames = ['person.jpg']
im_fnames = sorted(
(fname for fname in os.listdir(path_in)
if os.path.splitext(fname)[-1] == '.jpg')) # shuffle data
# shutil.rmtree(cut_path)
# os.mkdir(cut_path)
for i in im_fnames:
im_fname = os.path.join(path_in, i)
#im_fnames = (os.path.join(path_in, fname) for fname in im_fnames)
#print im_fname
self.people_sex = None
self.people_age = 20
if '自动' in retrival_params[0] or '自动' in retrival_params[-1]:
try:
#self.img_uploader.run(im_fname)
self.result = self.face.run(im_fname)
#print self.result
if len(self.result) == 1:
if self.result[0][u'faceAttributes'][
u'gender'] == u'female':
self.people_sex = '2'
else:
self.people_sex = '1'
self.people_age = self.result[0][u'faceAttributes'][u'age']
#print "people_sex:"
#print self.people_sex
except:
print "can't found face identify"
pass
print 'sex:'
print self.people_sex
#pool = Pool(processes=1)
#print "HAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA"
#for i, (image, im_data, im_name) in enumerate(pool.imap(preprocess, im_fnames, chunksize=1)):
(image, im_data, im_name) = preprocess(im_fname)
t_total.tic()
im_data = net_utils.np_to_variable(im_data,
is_cuda=True,
volatile=True).permute(
0, 3, 1, 2)
im_name = os.path.split(im_name)[-1]
# print im_name
t_det.tic()
#print "oooooooooooooooo1"
bbox_pred, iou_pred, prob_pred = self.net(im_data)
det_time = t_det.toc()
# to numpy
bbox_pred = bbox_pred.data.cpu().numpy()
iou_pred = iou_pred.data.cpu().numpy()
prob_pred = prob_pred.data.cpu().numpy()
# print bbox_pred.shape, iou_pred.shape, prob_pred.shape
#print "oooooooooooooooo2"
self.bboxes, self.scores, self.cls_inds = yolo_utils.postprocess(
bbox_pred, iou_pred, prob_pred, image.shape, cfg, self.thresh)
#print image.shape
#print "bboxes"
#print bboxes
#print "HAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAAA"
cls_res = []
cls_score = []
cls_res_top5 = []
cls_score_top5 = []
flag = 0
for i, bbox in enumerate(self.bboxes):
#print "bbox",bbox
print "start===================================================%d" % i
cut_image = image[bbox[1]:bbox[3], bbox[0]:bbox[2]]
res_num, res_score = cloth_num(cut_image, self.model_res)
cls_res.append(self.num_classes[res_num[0]])
cls_re = []
for n in range(10):
cls_re.append(self.num_classes[res_num[n]])
#print "++++++++++++++++++++++++++++++"+str(n)
#print Cnum[0][n],res_num[0]
#print self.num_classes[Cnum[0][n]]
#print "-------------"
#print res_score
#If the adjacent two types of differentiation is too small,it is considered that the category that the category can not be determined
if res_score[
0] < 12 and res_score[1] * 1.0 / res_score[0] > 0.9:
#print res_score[1]*1.0/res_score[0]
cls_score.append(0)
else:
#If two overlapping frames of the same category exceed 0.4,only the box with the largest weight is saved
for j, obox in enumerate(self.bboxes[:i]):
# (bbox[0], bbox[1]), (bbox[2], bbox[3])
if obox[2] > bbox[0] and obox[3] > bbox[1] and obox[
0] < bbox[2] and obox[1] < bbox[3]:
print "------------------------xiangjiao------------------------------"
box_inter = (max(obox[0],
bbox[0]), max(obox[1], bbox[1]),
min(obox[2],
bbox[2]), min(obox[3], bbox[3]))
area1 = (bbox[2] - bbox[0]) * (bbox[3] - bbox[1])
area2 = (obox[2] - obox[0]) * (obox[3] - obox[1])
area_min = min((area1, area2))
area_inter = (box_inter[2] - box_inter[0]) * (
box_inter[3] - box_inter[1])
#print area_min,area_inter
if area_inter * 1.0 / area_min >= 0.5:
print "====================YEEEEEES++++++++++++++++"
#if cls_res[i]==cls_res[j]:
if res_score[0] > cls_score[j]:
if cls_score[j] != 0:
cls_score[j] = 1
cls_score_top5[j][0] = 1
else:
res_score[0] = 1
break
cls_score.append(res_score[0])
cls_res_top5.append(cls_re)
#print cls_score
cls_score_top5.append(res_score)
#print res_num
#cls_score.append(res_score)
#print "resnet"
#print cls_res,cls_score
#cut_for_intel = cv2.resize(cut_image, (800, 500))
#print "===================================================%d"%i
#cut_for_intel = cv2.resize(cut_image, (int(1000. * float(cut_image.shape[1]) / cut_image.shape[0]), 1000))
#cv2.imwrite(os.path.join(cut_path,"%d_%s"%(i,im_name)),cut_for_intel)
self.cls_res = cls_res
self.cls_score = cls_score
self.cls_res_top5 = cls_res_top5
self.cls_score_top5 = cls_score_top5
#im2show = yolo_utils.draw_detection(image, bboxes, scores, cls_inds, cfg)
#print "cls_inds:"
#print type(self.cls_inds),self.cls_inds
# print "cls_res:"
#
# cls_res=np.array(cls_res)
#print type(cls_res),cls_res
# image 原始图像 bboxes 识别框坐标 scores识别置信度 cls_res 第一个分类类别 cls_score 第一个分类置信度 f_info 识别文本信息 f_pic识别的类别信息 cls_res_top5前十个分类类别
# cls_score_top5前十个分类置信度，f_pic_like识别的相似类别信息，f_pic_rec根据类别推荐的信息，f_pic_rec_like根据相似类别推荐的信息，cls_inds识别的大类别
f_info = open(InfoDir, 'w')
f_pic = open(InfoPicPath, 'w')
f_pic_like = open(InfoPicLikePath, 'w')
f_pic_rec = open(InfoPicPathRec, 'w')
f_pic_rec_like = open(InfoPicLikePathRec, 'w')
im2show = self.draw_detection_rec(image,
self.bboxes,
self.cls_inds,
self.scores,
self.cls_res_top5,
self.cls_score_top5,
f_info,
f_pic,
f_pic_like,
f_pic_rec,
f_pic_rec_like,
sex_dec=self.people_sex,
age_dec=self.people_age,
retrival_params=retrival_params)
f_info.close()
f_pic.close()
f_pic_like.close()
f_pic_rec.close()
f_pic_rec_like.close()
#for i,j in enumerate(cls_res):
# info = "识别概率:%0.2f\t准确度:%0.2f\t类别:%s\n" % ((i[0][1]), i[0][0], score_class)
if im2show.shape[0] > 1100:
im2show = cv2.resize(im2show, (int(
1000. * float(im2show.shape[1]) / im2show.shape[0]), 1000))
# cv2.imshow('test', im2show)
#cv2.imwrite("./result/test/{}".format(im_name), im2show)
cv2.imwrite(os.path.join(path_out, im_name), im2show)
total_time = t_total.toc()
# wait_time = max(int(60 - total_time * 1000), 1)
# cv2.waitKey(0)
#format_str = 'frame: %d, (detection: %.1f Hz, %.1f ms) (total: %.1f Hz, %.1f ms)'
#print(format_str % (i, 1. / det_time, det_time * 1000, 1. / total_time, total_time * 1000))
t_total.clear()
t_det.clear()
def main():
shutil.rmtree('output', ignore_errors=True)
shutil.copytree('output_template', 'output')
# trained_model = cfg.trained_model
# trained_model = '/home/cory/yolo2-pytorch/models/training/kitti_new_2/kitti_new_2_60.h5'
trained_model = '/home/cory/yolo2-pytorch/models/training/voc0712_obj_scale/voc0712_obj_scale_1.h5'
# trained_model = '/home/cory/yolo2-pytorch/models/training/kitti_det_new_2/kitti_det_new_2_40.h5'
# trained_model = '/home/cory/yolo2-pytorch/models/training/kitti_det_new_2/kitti_det_new_2_10.h5'
thresh = 0.5
use_kitti = True
image_dir = '/home/cory/KITTI_Dataset/data_tracking_image_2/training/image_02/0013'
# car = 1 5
# pedestrian = 13 17
net = Darknet19()
net_utils.load_net(trained_model, net)
net.eval()
net.cuda()
print('load model successfully')
# print(net)
def str_index(filename):
if use_kitti:
return filename
begin_pos = filename.rfind('_') + 1
end_pos = filename.rfind('.')
str_v = filename[begin_pos: end_pos]
return int(str_v)
image_extensions = ['.jpg', '.JPG', '.png', '.PNG']
image_abs_paths = sorted([os.path.join(image_dir, name)
for name in os.listdir(image_dir)
if name[-4:] in image_extensions],
key=str_index)
key_frame_path = ''
detection_period = 5
use_flow = False
kitti_filename = 'yolo_flow_kitti_det.txt'
try:
os.remove(kitti_filename)
except OSError:
pass
t_det = Timer()
t_total = Timer()
for i, image_path in enumerate(image_abs_paths):
t_total.tic()
image, im_data = preprocess(image_path)
im_data = net_utils.np_to_variable(im_data, is_cuda=True, volatile=True).permute(0, 3, 1, 2)
layer_of_flow = 'conv4'
# key frame
if i % detection_period == 0 and use_flow:
key_frame_path = image_path
# conv5 feature map
feature = net.get_feature_map(im_data=im_data, layer=layer_of_flow)
feature = feature.data.cpu().numpy()
feature_map_all = plot_feature_map(feature, resize_ratio=1)
# cv2.imshow('feature_map', feature_map_all)
cv2.imwrite('output/feature_map/{:04d}.jpg'.format(i), feature_map_all * 255)
t_det.tic()
if use_flow:
t1 = time.time()
conv5_shifted_gpu = detect_by_flow(i, feature, image, image_path, key_frame_path)
t2 = time.time()
print('detect_by_flow', t2 - t1)
bbox_pred, iou_pred, prob_pred = net.feed_feature(Variable(conv5_shifted_gpu), layer=layer_of_flow)
else:
bbox_pred, iou_pred, prob_pred = net.forward(im_data)
det_time = t_det.toc()
# to numpy
bbox_pred = bbox_pred.data.cpu().numpy()
iou_pred = iou_pred.data.cpu().numpy()
prob_pred = prob_pred.data.cpu().numpy()
# print bbox_pred.shape, iou_pred.shape, prob_pred.shape
bboxes, scores, cls_inds = yolo_utils.postprocess(bbox_pred, iou_pred, prob_pred, image.shape, cfg, thresh)
det_obj = detection_objects(bboxes, scores, cls_inds)
save_as_kitti_format(i, det_obj, kitti_filename, src_label='kitti')
im2show = yolo_utils.draw_detection(image, bboxes, scores, cls_inds, cfg)
cv2.imshow('detection', im2show)
cv2.imwrite('output/detection/{:04d}.jpg'.format(i), im2show)
total_time = t_total.toc()
format_str = 'frame: %d, (detection: %.1f fps, %.1f ms) (total: %.1f fps, %.1f ms)'
print(format_str % (
i, 1. / det_time, det_time * 1000, 1. / total_time, total_time * 1000))
t_det.clear()
t_total.clear()
key = cv2.waitKey(1)
if key == ord('q'):
break
# print bbox_pred.shape, iou_pred.shape, prob_pred.shape
bboxes, scores, cls_inds = yolo_utils.postprocess(
bbox_pred, iou_pred, prob_pred, image.shape, cfg, thresh)
im2show = yolo_utils.draw_detection(image, bboxes, scores, cls_inds, cfg)
if im2show.shape[0] > 1100:
im2show = cv2.resize(im2show,
(int(1000. *
float(im2show.shape[1]) / im2show.shape[0]),
1000))
cv2.imshow('test', im2show)
total_time = t_total.toc()
# wait_time = max(int(60 - total_time * 1000), 1)
cv2.waitKey(0)
if i % 1 == 0:
format_str = 'frame: %d, ' \
'(detection: %.1f Hz, %.1f ms) ' \
'(total: %.1f Hz, %.1f ms)'
print((format_str % (
i,
1. / det_time, det_time * 1000,
1. / total_time, total_time * 1000)))
t_total.clear()
t_det.clear()
