def __init__(self, configer):
self.configer = configer
self.det_visualizer = DetVisualizer(configer)
self.det_parser = DetParser(configer)
self.det_model_manager = ModelManager(configer)
self.test_loader = TestDataLoader(configer)
self.device = torch.device('cpu' if self.configer.get('gpu') is None else 'cuda')
self.det_net = None
self._init_model()
def __init__(self, configer):
self.configer = configer
self.blob_helper = BlobHelper(configer)
self.det_visualizer = DetVisualizer(configer)
self.det_parser = DetParser(configer)
self.det_model_manager = ModelManager(configer)
self.test_loader = TestDataLoader(configer)
self.roi_sampler = FRROISampler(configer)
self.rpn_target_generator = RPNTargetAssigner(configer)
self.fr_priorbox_layer = FRPriorBoxLayer(configer)
self.fr_roi_generator = FRROIGenerator(configer)
self.device = torch.device('cpu' if self.configer.get('gpu') is None else 'cuda')
self.det_net = None
self._init_model()
def __init__(self, configer):
self.configer = configer
self.batch_time = AverageMeter()
self.data_time = AverageMeter()
self.train_losses = AverageMeter()
self.val_losses = AverageMeter()
self.det_visualizer = DetVisualizer(configer)
self.det_model_manager = ModelManager(configer)
self.det_data_loader = DataLoader(configer)
self.det_running_score = DetRunningScore(configer)
self.det_net = None
self.train_loader = None
self.val_loader = None
self.optimizer = None
self.scheduler = None
self.runner_state = dict()
self._init_model()
class FasterRCNN(object):
"""
The class for Single Shot Detector. Include train, val, test & predict.
"""
def __init__(self, configer):
self.configer = configer
self.batch_time = AverageMeter()
self.data_time = AverageMeter()
self.train_losses = AverageMeter()
self.val_losses = AverageMeter()
self.det_visualizer = DetVisualizer(configer)
self.det_model_manager = ModelManager(configer)
self.det_data_loader = DataLoader(configer)
self.fr_priorbox_layer = FRPriorBoxLayer(configer)
self.det_running_score = DetRunningScore(configer)
self.det_net = None
self.train_loader = None
self.val_loader = None
self.optimizer = None
self.scheduler = None
self.runner_state = dict()
self._init_model()
def _init_model(self):
self.det_net = self.det_model_manager.object_detector()
self.det_net = RunnerHelper.load_net(self, self.det_net)
self.optimizer, self.scheduler = Trainer.init( self._get_parameters(), self.configer.get('solver'))
self.train_loader = self.det_data_loader.get_trainloader()
self.val_loader = self.det_data_loader.get_valloader()
self.det_loss = self.det_model_manager.get_det_loss()
def _get_parameters(self):
lr_1 = []
lr_2 = []
params_dict = dict(self.det_net.named_parameters())
for key, value in params_dict.items():
if value.requires_grad:
if 'bias' in key:
lr_2.append(value)
else:
lr_1.append(value)
params = [{'params': lr_1, 'lr': self.configer.get('solver', 'lr')['base_lr']},
{'params': lr_2, 'lr': self.configer.get('solver', 'lr')['base_lr'] * 2., 'weight_decay': 0}]
return params
def train(self):
"""
Train function of every epoch during train phase.
"""
self.det_net.train()
start_time = time.time()
# Adjust the learning rate after every epoch.
self.runner_state['epoch'] += 1
for i, data_dict in enumerate(self.train_loader):
Trainer.update(self, solver_dict=self.configer.get('solver'))
self.data_time.update(time.time() - start_time)
# Forward pass.
data_dict = RunnerHelper.to_device(self, data_dict)
out = self.det_net(data_dict)
loss_dict = self.det_loss(out)
loss = loss_dict['loss'].mean()
self.train_losses.update(loss.item(), len(DCHelper.tolist(data_dict['meta'])))
self.optimizer.zero_grad()
loss.backward()
RunnerHelper.clip_grad(self.det_net, 10.)
self.optimizer.step()
# Update the vars of the train phase.
self.batch_time.update(time.time() - start_time)
start_time = time.time()
self.runner_state['iters'] += 1
# Print the log info & reset the states.
if self.runner_state['iters'] % self.configer.get('solver', 'display_iter') == 0:
Log.info('Train Epoch: {0}\tTrain Iteration: {1}\t'
'Time {batch_time.sum:.3f}s / {2}iters, ({batch_time.avg:.3f})\t'
'Data load {data_time.sum:.3f}s / {2}iters, ({data_time.avg:3f})\n'
'Learning rate = {3}\tLoss = {loss.val:.8f} (ave = {loss.avg:.8f})\n'.format(
self.runner_state['epoch'], self.runner_state['iters'],
self.configer.get('solver', 'display_iter'),
RunnerHelper.get_lr(self.optimizer), batch_time=self.batch_time,
data_time=self.data_time, loss=self.train_losses))
self.batch_time.reset()
self.data_time.reset()
self.train_losses.reset()
if self.configer.get('solver', 'lr')['metric'] == 'iters' \
and self.runner_state['iters'] == self.configer.get('solver', 'max_iters'):
break
# Check to val the current model.
if self.runner_state['iters'] % self.configer.get('solver', 'test_interval') == 0:
self.val()
def val(self):
"""
Validation function during the train phase.
"""
self.det_net.eval()
start_time = time.time()
with torch.no_grad():
for j, data_dict in enumerate(self.val_loader):
# Forward pass.
data_dict = RunnerHelper.to_device(self, data_dict)
out = self.det_net(data_dict)
loss_dict = self.det_loss(out)
# Compute the loss of the train batch & backward.
loss = loss_dict['loss'].mean()
out_dict, _ = RunnerHelper.gather(self, out)
self.val_losses.update(loss.item(), len(DCHelper.tolist(data_dict['meta'])))
test_indices_and_rois, test_roi_locs, test_roi_scores, test_rois_num = out_dict['test_group']
batch_detections = FastRCNNTest.decode(test_roi_locs,
test_roi_scores,
test_indices_and_rois,
test_rois_num,
self.configer,
DCHelper.tolist(data_dict['meta']))
batch_pred_bboxes = self.__get_object_list(batch_detections)
self.det_running_score.update(batch_pred_bboxes,
[item['ori_bboxes'] for item in DCHelper.tolist(data_dict['meta'])],
[item['ori_labels'] for item in DCHelper.tolist(data_dict['meta'])])
# Update the vars of the val phase.
self.batch_time.update(time.time() - start_time)
start_time = time.time()
RunnerHelper.save_net(self, self.det_net, iters=self.runner_state['iters'])
# Print the log info & reset the states.
Log.info(
'Test Time {batch_time.sum:.3f}s, ({batch_time.avg:.3f})\t'
'Loss {loss.avg:.8f}\n'.format(
batch_time=self.batch_time, loss=self.val_losses))
Log.info('Val mAP: {}\n'.format(self.det_running_score.get_mAP()))
self.det_running_score.reset()
self.batch_time.reset()
self.val_losses.reset()
self.det_net.train()
def __get_object_list(self, batch_detections):
batch_pred_bboxes = list()
for idx, detections in enumerate(batch_detections):
object_list = list()
if detections is not None:
for x1, y1, x2, y2, conf, cls_pred in detections:
cf = float('%.2f' % conf.item())
cls_pred = int(cls_pred.cpu().item()) - 1
object_list.append([x1.item(), y1.item(), x2.item(), y2.item(), cls_pred, cf])
batch_pred_bboxes.append(object_list)
return batch_pred_bboxes
class FastRCNNTest(object):
def __init__(self, configer):
self.configer = configer
self.blob_helper = BlobHelper(configer)
self.det_visualizer = DetVisualizer(configer)
self.det_parser = DetParser(configer)
self.det_model_manager = ModelManager(configer)
self.test_loader = TestDataLoader(configer)
self.roi_sampler = FRROISampler(configer)
self.rpn_target_generator = RPNTargetAssigner(configer)
self.fr_priorbox_layer = FRPriorBoxLayer(configer)
self.fr_roi_generator = FRROIGenerator(configer)
self.device = torch.device(
'cpu' if self.configer.get('gpu') is None else 'cuda')
self.det_net = None
self._init_model()
def _init_model(self):
self.det_net = self.det_model_manager.object_detector()
self.det_net = RunnerHelper.load_net(self, self.det_net)
self.det_net.eval()
def test(self, test_dir, out_dir):
for _, data_dict in enumerate(
self.test_loader.get_testloader(test_dir=test_dir)):
data_dict['testing'] = True
data_dict = RunnerHelper.to_device(self, data_dict)
out_dict = self.det_net(data_dict)
meta_list = DCHelper.tolist(data_dict['meta'])
test_indices_and_rois, test_roi_locs, test_roi_scores, test_rois_num = out_dict[
'test_group']
batch_detections = self.decode(test_roi_locs, test_roi_scores,
test_indices_and_rois,
test_rois_num, self.configer,
meta_list)
for i in range(len(meta_list)):
ori_img_bgr = ImageHelper.read_image(meta_list[i]['img_path'],
tool='cv2',
mode='BGR')
json_dict = self.__get_info_tree(batch_detections[i])
image_canvas = self.det_parser.draw_bboxes(
ori_img_bgr.copy(),
json_dict,
conf_threshold=self.configer.get('res', 'vis_conf_thre'))
ImageHelper.save(image_canvas,
save_path=os.path.join(
out_dir, 'vis/{}.png'.format(
meta_list[i]['filename'])))
Log.info('Json Path: {}'.format(
os.path.join(
out_dir,
'json/{}.json'.format(meta_list[i]['filename']))))
JsonHelper.save_file(json_dict,
save_path=os.path.join(
out_dir, 'json/{}.json'.format(
meta_list[i]['filename'])))
@staticmethod
def decode(roi_locs, roi_scores, indices_and_rois, test_rois_num, configer,
metas):
indices_and_rois = indices_and_rois
num_classes = configer.get('data', 'num_classes')
mean = torch.Tensor(configer.get(
'roi', 'loc_normalize_mean')).repeat(num_classes)[None]
std = torch.Tensor(configer.get(
'roi', 'loc_normalize_std')).repeat(num_classes)[None]
mean = mean.to(roi_locs.device)
std = std.to(roi_locs.device)
roi_locs = (roi_locs * std + mean)
roi_locs = roi_locs.contiguous().view(-1, num_classes, 4)
rois = indices_and_rois[:, 1:]
rois = rois.contiguous().view(-1, 1, 4).expand_as(roi_locs)
wh = torch.exp(roi_locs[:, :, 2:]) * (rois[:, :, 2:] - rois[:, :, :2])
cxcy = roi_locs[:, :, :2] * (rois[:, :, 2:] - rois[:, :, :2]) + (
rois[:, :, :2] + rois[:, :, 2:]) / 2
dst_bbox = torch.cat([cxcy - wh / 2, cxcy + wh / 2], 2) # [b, 8732,4]
if configer.get('phase') != 'debug':
cls_prob = F.softmax(roi_scores, dim=1)
else:
cls_prob = roi_scores
cls_label = torch.LongTensor([i for i in range(num_classes)])\
.contiguous().view(1, num_classes).repeat(indices_and_rois.size(0), 1).to(roi_locs.device)
output = [None for _ in range(test_rois_num.size(0))]
start_index = 0
for i in range(test_rois_num.size(0)):
tmp_dst_bbox = dst_bbox[start_index:start_index + test_rois_num[i]]
tmp_dst_bbox[:, :, 0::2] = tmp_dst_bbox[:, :, 0::2].clamp(
min=0, max=metas[i]['border_wh'][0] - 1)
tmp_dst_bbox[:, :, 1::2] = tmp_dst_bbox[:, :, 1::2].clamp(
min=0, max=metas[i]['border_wh'][1] - 1)
tmp_dst_bbox *= (metas[i]['ori_img_size'][0] /
metas[i]['border_wh'][0])
tmp_cls_prob = cls_prob[start_index:start_index + test_rois_num[i]]
tmp_cls_label = cls_label[start_index:start_index +
test_rois_num[i]]
start_index += test_rois_num[i]
mask = (tmp_cls_prob > configer.get(
'res', 'val_conf_thre')) & (tmp_cls_label > 0)
tmp_dst_bbox = tmp_dst_bbox[mask].contiguous().view(-1, 4)
if tmp_dst_bbox.numel() == 0:
continue
tmp_cls_prob = tmp_cls_prob[mask].contiguous().view(
-1, ).unsqueeze(1)
tmp_cls_label = tmp_cls_label[mask].contiguous().view(
-1, ).unsqueeze(1)
valid_preds = torch.cat(
(tmp_dst_bbox, tmp_cls_prob.float(), tmp_cls_label.float()), 1)
valid_ind = DetHelper.cls_nms(valid_preds[:, :5],
labels=valid_preds[:, 5],
max_threshold=configer.get(
'res', 'nms')['max_threshold'],
return_ind=True)
valid_preds = valid_preds[valid_ind]
output[i] = valid_preds
return output
def __get_info_tree(self, detections):
json_dict = dict()
object_list = list()
if detections is not None:
for x1, y1, x2, y2, conf, cls_pred in detections:
object_dict = dict()
object_dict['bbox'] = [
x1.item(), y1.item(),
x2.item(), y2.item()
]
object_dict['label'] = int(cls_pred.cpu().item()) - 1
object_dict['score'] = float('%.2f' % conf.cpu().item())
object_list.append(object_dict)
json_dict['objects'] = object_list
return json_dict
class YOLOv3Test(object):
def __init__(self, configer):
self.configer = configer
self.det_visualizer = DetVisualizer(configer)
self.det_parser = DetParser(configer)
self.det_model_manager = ModelManager(configer)
self.test_loader = TestDataLoader(configer)
self.device = torch.device('cpu' if self.configer.get('gpu') is None else 'cuda')
self.det_net = None
self._init_model()
def _init_model(self):
self.det_net = self.det_model_manager.object_detector()
self.det_net = RunnerHelper.load_net(self, self.det_net)
self.det_net.eval()
def test(self, test_dir, out_dir):
for _, data_dict in enumerate(self.test_loader.get_testloader(test_dir=test_dir)):
data_dict['testing'] = True
detections = self.det_net(data_dict)
meta_list = DCHelper.tolist(data_dict['meta'])
batch_detections = self.decode(detections, self.configer, meta_list)
for i in range(len(meta_list)):
ori_img_bgr = ImageHelper.read_image(meta_list[i]['img_path'], tool='cv2', mode='BGR')
json_dict = self.__get_info_tree(batch_detections[i])
image_canvas = self.det_parser.draw_bboxes(ori_img_bgr.copy(), json_dict,
conf_threshold=self.configer.get('res', 'vis_conf_thre'))
ImageHelper.save(image_canvas,
save_path=os.path.join(out_dir, 'vis/{}.png'.format(meta_list[i]['filename'])))
Log.info('Json Path: {}'.format(os.path.join(out_dir, 'json/{}.json'.format(meta_list[i]['filename']))))
JsonHelper.save_file(json_dict,
save_path=os.path.join(out_dir, 'json/{}.json'.format(meta_list[i]['filename'])))
@staticmethod
def decode(batch_detections, configer, meta):
output = [None for _ in range(len(meta))]
for i in range(len(meta)):
image_pred = batch_detections[i]
image_pred[:, 0] *= meta[i]['ori_img_size'][0]
image_pred[:, 1] *= meta[i]['ori_img_size'][1]
image_pred[:, 2] *= meta[i]['ori_img_size'][0]
image_pred[:, 3] *= meta[i]['ori_img_size'][1]
# Filter out confidence scores below threshold
image_pred = image_pred[image_pred[:, 4] > configer.get('res', 'val_conf_thre')]
# If none are remaining => process next image
if image_pred.numel() == 0:
continue
# Get score and class with highest confidence
class_conf, class_pred = torch.max(image_pred[:, 5:5 + configer.get('data', 'num_classes')], 1, keepdim=True)
# Detections ordered as (x1, y1, x2, y2, obj_conf, class_conf, class_pred)
detections = torch.cat((image_pred[:, :5], class_conf.float(), class_pred.float()), 1)
valid_ind = DetHelper.cls_nms(detections[:, :5], labels=class_pred.squeeze(1),
max_threshold=configer.get('res', 'nms')['max_threshold'], return_ind=True)
output[i] = detections[valid_ind]
return output
def __get_info_tree(self, detections):
json_dict = dict()
object_list = list()
if detections is not None:
for x1, y1, x2, y2, conf, cls_conf, cls_pred in detections:
object_dict = dict()
object_dict['bbox'] = [x1.item(), y1.item(), x2.item(), y2.item()]
object_dict['label'] = int(cls_pred.item())
object_dict['score'] = float('%.2f' % conf.item())
object_list.append(object_dict)
json_dict['objects'] = object_list
return json_dict
class SingleShotDetectorTest(object):
def __init__(self, configer):
self.configer = configer
self.blob_helper = BlobHelper(configer)
self.det_visualizer = DetVisualizer(configer)
self.det_parser = DetParser(configer)
self.det_model_manager = ModelManager(configer)
self.test_loader = TestDataLoader(configer)
self.device = torch.device(
'cpu' if self.configer.get('gpu') is None else 'cuda')
self.det_net = None
self._init_model()
def _init_model(self):
self.det_net = self.det_model_manager.object_detector()
self.det_net = RunnerHelper.load_net(self, self.det_net)
self.det_net.eval()
def test(self, test_dir, out_dir):
for _, data_dict in enumerate(
self.test_loader.get_testloader(test_dir=test_dir)):
data_dict['testing'] = True
out_dict = self.det_net(data_dict)
meta_list = DCHelper.tolist(data_dict['meta'])
batch_detections = self.decode(out_dict['loc'], out_dict['conf'],
self.configer, meta_list)
for i in range(len(meta_list)):
ori_img_bgr = ImageHelper.read_image(meta_list[i]['img_path'],
tool='cv2',
mode='BGR')
json_dict = self.__get_info_tree(batch_detections[i])
image_canvas = self.det_parser.draw_bboxes(
ori_img_bgr.copy(),
json_dict,
conf_threshold=self.configer.get('res', 'vis_conf_thre'))
ImageHelper.save(image_canvas,
save_path=os.path.join(
out_dir, 'vis/{}.png'.format(
meta_list[i]['filename'])))
Log.info('Json Path: {}'.format(
os.path.join(
out_dir,
'json/{}.json'.format(meta_list[i]['filename']))))
JsonHelper.save_file(json_dict,
save_path=os.path.join(
out_dir, 'json/{}.json'.format(
meta_list[i]['filename'])))
@staticmethod
def decode(loc, conf, configer, meta):
batch_size, num_priors, _ = loc.size()
loc = loc.unsqueeze(2).repeat(1, 1,
configer.get('data', 'num_classes'), 1)
loc = loc.contiguous().view(loc.size(0), -1, 4)
labels = torch.Tensor([
i for i in range(configer.get('data', 'num_classes'))
]).to(loc.device)
labels = labels.view(1, 1, -1,
1).repeat(batch_size, num_priors, 1,
1).contiguous().view(batch_size, -1, 1)
conf = conf.contiguous().view(batch_size, -1, 1)
# max_conf, labels = conf.max(2, keepdim=True) # [b, 8732,1]
predictions = torch.cat((loc.float(), conf.float(), labels.float()), 2)
output = [None for _ in range(len(predictions))]
for i, image_pred in enumerate(predictions):
image_pred[:, 0] *= meta[i]['ori_img_size'][0]
image_pred[:, 1] *= meta[i]['ori_img_size'][1]
image_pred[:, 2] *= meta[i]['ori_img_size'][0]
image_pred[:, 3] *= meta[i]['ori_img_size'][1]
ids = labels[i].squeeze(1).nonzero().contiguous().view(-1, )
if ids.numel() == 0:
continue
valid_preds = image_pred[ids]
_, order = valid_preds[:, 4].sort(0, descending=True)
order = order[:configer.get('res', 'nms')['pre_nms']]
valid_preds = valid_preds[order]
valid_preds = valid_preds[
valid_preds[:, 4] > configer.get('res', 'val_conf_thre')]
if valid_preds.numel() == 0:
continue
valid_ind = DetHelper.cls_nms(
valid_preds[:, :5],
labels=valid_preds[:, 5],
max_threshold=configer.get('res', 'nms')['max_threshold'],
cls_keep_num=configer.get('res', 'cls_keep_num'),
return_ind=True)
valid_preds = valid_preds[valid_ind]
_, order = valid_preds[:, 4].sort(0, descending=True)
order = order[:configer.get('res', 'max_per_image')]
output[i] = valid_preds[order]
return output
def __get_info_tree(self, detections):
json_dict = dict()
object_list = list()
if detections is not None:
for x1, y1, x2, y2, conf, cls_pred in detections:
object_dict = dict()
object_dict['bbox'] = [
x1.item(), y1.item(),
x2.item(), y2.item()
]
object_dict['label'] = int(cls_pred.cpu().item()) - 1
object_dict['score'] = float('%.2f' % conf.cpu().item())
object_list.append(object_dict)
json_dict['objects'] = object_list
return json_dict
