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.det_data_loader = DataLoader(configer)
self.ssd_priorbox_layer = SSDPriorBoxLayer(configer)
self.ssd_target_generator = SSDTargetGenerator(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.det_data_loader = DataLoader(configer)
self.yolo_target_generator = YOLOTargetGenerator(configer)
self.yolo_detection_layer = YOLODetectionLayer(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 = DetModelManager(configer)
self.det_data_loader = DataLoader(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()
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_loss_manager = LossManager(configer)
self.det_model_manager = DetModelManager(configer)
self.det_data_loader = DataLoader(configer)
self.yolo_detection_layer = YOLODetectionLayer(configer)
self.yolo_target_generator = YOLOTargetGenerator(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 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 = DetModelManager(configer)
self.det_data_loader = DataLoader(configer)
self.ssd_priorbox_layer = SSDPriorBoxLayer(configer)
self.ssd_target_generator = SSDTargetGenerator(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_img(self, image_path, json_path, raw_path, vis_path):
Log.info('Image Path: {}'.format(image_path))
img = ImageHelper.read_image(
image_path,
tool=self.configer.get('data', 'image_tool'),
mode=self.configer.get('data', 'input_mode'))
ori_img_bgr = ImageHelper.get_cv2_bgr(img,
mode=self.configer.get(
'data', 'input_mode'))
inputs = self.blob_helper.make_input(img,
input_size=self.configer.get(
'test', 'input_size'),
scale=1.0)
with torch.no_grad():
feat_list, bbox, cls = self.det_net(inputs)
batch_detections = self.decode(
bbox, cls,
self.ssd_priorbox_layer(feat_list,
self.configer.get('test', 'input_size')),
self.configer, [inputs.size(3), inputs.size(2)])
json_dict = self.__get_info_tree(
batch_detections[0], ori_img_bgr,
[inputs.size(3), inputs.size(2)])
image_canvas = self.det_parser.draw_bboxes(
ori_img_bgr.copy(),
json_dict,
conf_threshold=self.configer.get('res', 'vis_conf_thre'))
cv2.imwrite(vis_path, image_canvas)
cv2.imwrite(raw_path, ori_img_bgr)
Log.info('Json Path: {}'.format(json_path))
JsonHelper.save_file(json_dict, json_path)
return json_dict
@staticmethod
def decode(bbox, conf, default_boxes, configer, input_size):
loc = bbox
if configer.get('phase') != 'debug':
conf = F.softmax(conf, dim=-1)
default_boxes = default_boxes.unsqueeze(0).repeat(loc.size(0), 1,
1).to(bbox.device)
variances = [0.1, 0.2]
wh = torch.exp(loc[:, :, 2:] * variances[1]) * default_boxes[:, :, 2:]
cxcy = loc[:, :, :2] * variances[
0] * default_boxes[:, :, 2:] + default_boxes[:, :, :2]
boxes = torch.cat([cxcy - wh / 2, cxcy + wh / 2], 2) # [b, 8732,4]
batch_size, num_priors, _ = boxes.size()
boxes = boxes.unsqueeze(2).repeat(1, 1,
configer.get('data', 'num_classes'),
1)
boxes = boxes.contiguous().view(boxes.size(0), -1, 4)
# clip bounding box
boxes[:, :, 0::2] = boxes[:, :, 0::2].clamp(min=0,
max=input_size[0] - 1)
boxes[:, :, 1::2] = boxes[:, :, 1::2].clamp(min=0,
max=input_size[1] - 1)
labels = torch.Tensor([
i for i in range(configer.get('data', 'num_classes'))
]).to(boxes.device)
labels = labels.view(1, 1, -1,
1).repeat(batch_size, num_priors, 1,
1).contiguous().view(batch_size, -1, 1)
max_conf = conf.contiguous().view(batch_size, -1, 1)
# max_conf, labels = conf.max(2, keepdim=True) # [b, 8732,1]
predictions = torch.cat((boxes, max_conf.float(), labels.float()), 2)
output = [None for _ in range(len(predictions))]
for image_i, image_pred in enumerate(predictions):
ids = labels[image_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('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_preds = DetHelper.cls_nms(
valid_preds[:, :6],
labels=valid_preds[:, 5],
max_threshold=configer.get('nms', 'max_threshold'),
cls_keep_num=configer.get('res', 'cls_keep_num'))
_, order = valid_preds[:, 4].sort(0, descending=True)
order = order[:configer.get('res', 'max_per_image')]
output[image_i] = valid_preds[order]
return output
def __get_info_tree(self, detections, image_raw, input_size):
height, width, _ = image_raw.shape
in_width, in_height = input_size
json_dict = dict()
object_list = list()
if detections is not None:
for x1, y1, x2, y2, conf, cls_pred in detections:
object_dict = dict()
xmin = x1.cpu().item() / in_width * width
ymin = y1.cpu().item() / in_height * height
xmax = x2.cpu().item() / in_width * width
ymax = y2.cpu().item() / in_height * height
object_dict['bbox'] = [xmin, ymin, xmax, ymax]
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
def debug(self, vis_dir):
count = 0
for i, data_dict in enumerate(self.det_data_loader.get_trainloader()):
inputs = data_dict['img']
batch_gt_bboxes = data_dict['bboxes']
batch_gt_labels = data_dict['labels']
input_size = [inputs.size(3), inputs.size(2)]
feat_list = list()
for stride in self.configer.get('network', 'stride_list'):
feat_list.append(
torch.zeros((inputs.size(0), 1, input_size[1] // stride,
input_size[0] // stride)))
bboxes, labels = self.ssd_target_generator(feat_list,
batch_gt_bboxes,
batch_gt_labels,
input_size)
eye_matrix = torch.eye(self.configer.get('data', 'num_classes'))
labels_target = eye_matrix[labels.view(-1)].view(
inputs.size(0), -1, self.configer.get('data', 'num_classes'))
batch_detections = self.decode(
bboxes, labels_target,
self.ssd_priorbox_layer(feat_list, input_size), self.configer,
input_size)
for j in range(inputs.size(0)):
count = count + 1
if count > 20:
exit(1)
ori_img_bgr = self.blob_helper.tensor2bgr(inputs[j])
self.det_visualizer.vis_default_bboxes(
ori_img_bgr,
self.ssd_priorbox_layer(feat_list, input_size), labels[j])
json_dict = self.__get_info_tree(batch_detections[j],
ori_img_bgr, input_size)
image_canvas = self.det_parser.draw_bboxes(
ori_img_bgr.copy(),
json_dict,
conf_threshold=self.configer.get('res', 'vis_conf_thre'))
cv2.imwrite(
os.path.join(vis_dir, '{}_{}_vis.png'.format(i, j)),
image_canvas)
cv2.imshow('main', image_canvas)
cv2.waitKey()
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 YOLOv3Test(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.det_data_loader = DataLoader(configer)
self.yolo_target_generator = YOLOTargetGenerator(configer)
self.yolo_detection_layer = YOLODetectionLayer(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_img(self, image_path, json_path, raw_path, vis_path):
Log.info('Image Path: {}'.format(image_path))
img = ImageHelper.read_image(
image_path,
tool=self.configer.get('data', 'image_tool'),
mode=self.configer.get('data', 'input_mode'))
ori_img_bgr = ImageHelper.get_cv2_bgr(img,
mode=self.configer.get(
'data', 'input_mode'))
inputs = self.blob_helper.make_input(img,
input_size=self.configer.get(
'data', 'input_size'),
scale=1.0)
with torch.no_grad():
inputs = inputs.unsqueeze(0).to(self.device)
_, _, detections = self.det_net(inputs)
batch_detections = self.decode(detections, self.configer)
json_dict = self.__get_info_tree(batch_detections[0], ori_img_bgr)
image_canvas = self.det_parser.draw_bboxes(
ori_img_bgr.copy(),
json_dict,
conf_threshold=self.configer.get('res', 'vis_conf_thre'))
ImageHelper.save(ori_img_bgr, raw_path)
ImageHelper.save(image_canvas, vis_path)
Log.info('Json Path: {}'.format(json_path))
JsonHelper.save_file(json_dict, json_path)
return json_dict
@staticmethod
def decode(batch_pred_bboxes, configer, input_size):
box_corner = batch_pred_bboxes.new(batch_pred_bboxes.shape)
box_corner[:, :,
0] = batch_pred_bboxes[:, :,
0] - batch_pred_bboxes[:, :, 2] / 2
box_corner[:, :,
1] = batch_pred_bboxes[:, :,
1] - batch_pred_bboxes[:, :, 3] / 2
box_corner[:, :,
2] = batch_pred_bboxes[:, :,
0] + batch_pred_bboxes[:, :, 2] / 2
box_corner[:, :,
3] = batch_pred_bboxes[:, :,
1] + batch_pred_bboxes[:, :, 3] / 2
# clip bounding box
box_corner[:, :, 0::2] = box_corner[:, :, 0::2].clamp(min=0, max=1.0)
box_corner[:, :, 1::2] = box_corner[:, :, 1::2].clamp(min=0, max=1.0)
batch_pred_bboxes[:, :, :4] = box_corner[:, :, :4]
batch_pred_bboxes[:, :, 0::2] *= input_size[0]
batch_pred_bboxes[:, :, 1::2] *= input_size[1]
output = [None for _ in range(len(batch_pred_bboxes))]
for image_i, image_pred in enumerate(batch_pred_bboxes):
# Filter out confidence scores below threshold
conf_mask = (image_pred[:, 4] > configer.get(
'res', 'val_conf_thre')).squeeze()
image_pred = image_pred[conf_mask]
# 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)
output[image_i] = DetHelper.cls_nms(detections,
labels=class_pred.squeeze(1),
max_threshold=configer.get(
'res',
'nms')['max_threshold'])
return output
def __get_info_tree(self, detections, image_raw, input_size):
height, width, _ = image_raw.shape
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()
xmin = x1.cpu().item() / input_size[0] * width
ymin = y1.cpu().item() / input_size[1] * height
xmax = x2.cpu().item() / input_size[0] * width
ymax = y2.cpu().item() / input_size[1] * height
object_dict['bbox'] = [xmin, ymin, xmax, ymax]
object_dict['label'] = int(cls_pred.cpu().item())
object_dict['score'] = float('%.2f' % conf.cpu().item())
object_list.append(object_dict)
json_dict['objects'] = object_list
return json_dict
def debug(self, vis_dir):
count = 0
for i, data_dict in enumerate(self.det_data_loader.get_trainloader()):
inputs = data_dict['img']
batch_gt_bboxes = data_dict['bboxes']
batch_gt_labels = data_dict['labels']
input_size = [inputs.size(3), inputs.size(2)]
feat_list = list()
for stride in self.configer.get('network', 'stride_list'):
feat_list.append(
torch.zeros((inputs.size(0), 1, input_size[1] // stride,
input_size[0] // stride)))
targets, _, _ = self.yolo_target_generator(feat_list,
batch_gt_bboxes,
batch_gt_labels,
input_size)
targets = targets.to(self.device)
anchors_list = self.configer.get('gt', 'anchors_list')
output_list = list()
be_c = 0
for f_index, anchors in enumerate(anchors_list):
feat_stride = self.configer.get('network',
'stride_list')[f_index]
fm_size = [
int(round(border / feat_stride)) for border in input_size
]
num_c = len(anchors) * fm_size[0] * fm_size[1]
output_list.append(
targets[:, be_c:be_c + num_c].contiguous().view(
targets.size(0), len(anchors), fm_size[1], fm_size[0],
-1).permute(0, 1, 4, 2, 3).contiguous().view(
targets.size(0), -1, fm_size[1], fm_size[0]))
be_c += num_c
batch_detections = self.decode(
self.yolo_detection_layer(output_list)[2], self.configer,
input_size)
for j in range(inputs.size(0)):
count = count + 1
if count > 20:
exit(1)
ori_img_bgr = self.blob_helper.tensor2bgr(inputs[j])
json_dict = self.__get_info_tree(batch_detections[j],
ori_img_bgr, input_size)
image_canvas = self.det_parser.draw_bboxes(
ori_img_bgr.copy(),
json_dict,
conf_threshold=self.configer.get('vis', 'obj_threshold'))
cv2.imwrite(
os.path.join(vis_dir, '{}_{}_vis.png'.format(i, j)),
image_canvas)
cv2.imshow('main', image_canvas)
cv2.waitKey()
class YOLOv3(object):
"""
The class for YOLO v3. 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_loss_manager = LossManager(configer)
self.det_model_manager = DetModelManager(configer)
self.det_data_loader = DataLoader(configer)
self.yolo_detection_layer = YOLODetectionLayer(configer)
self.yolo_target_generator = YOLOTargetGenerator(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,
self._get_parameters())
self.train_loader = self.det_data_loader.get_trainloader()
self.val_loader = self.det_data_loader.get_valloader()
self.det_loss = self.det_loss_manager.get_det_loss()
def _get_parameters(self):
lr_1 = []
lr_10 = []
params_dict = dict(self.det_net.named_parameters())
for key, value in params_dict.items():
if 'backbone' not in key:
lr_10.append(value)
else:
lr_1.append(value)
params = [{
'params': lr_1,
'lr': self.configer.get('lr', 'base_lr')
}, {
'params': lr_10,
'lr': self.configer.get('lr', 'base_lr') * 10.
}]
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
# data_tuple: (inputs, heatmap, maskmap, vecmap)
for i, data_dict in enumerate(self.train_loader):
Trainer.update(self, backbone_list=(0, ))
inputs = data_dict['img']
batch_gt_bboxes = data_dict['bboxes']
batch_gt_labels = data_dict['labels']
input_size = [inputs.size(3), inputs.size(2)]
self.data_time.update(time.time() - start_time)
# Change the data type.
inputs = RunnerHelper.to_device(self, inputs)
# Forward pass.
feat_list, predictions, _ = self.det_net(inputs)
targets, objmask, noobjmask = self.yolo_target_generator(
feat_list, batch_gt_bboxes, batch_gt_labels, input_size)
targets, objmask, noobjmask = RunnerHelper.to_device(
self, targets, objmask, noobjmask)
# Compute the loss of the train batch & backward.
loss = self.det_loss(predictions, targets, objmask, noobjmask)
self.train_losses.update(loss.item(), inputs.size(0))
self.optimizer.zero_grad()
loss.backward()
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.configer.get('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('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 i, data_dict in enumerate(self.val_loader):
inputs = data_dict['img']
batch_gt_bboxes = data_dict['bboxes']
batch_gt_labels = data_dict['labels']
input_size = [inputs.size(3), inputs.size(2)]
# Forward pass.
inputs = RunnerHelper.to_device(self, inputs)
feat_list, predictions, detections = self.det_net(inputs)
targets, objmask, noobjmask = self.yolo_target_generator(
feat_list, batch_gt_bboxes, batch_gt_labels, input_size)
targets, objmask, noobjmask = RunnerHelper.to_device(
self, targets, objmask, noobjmask)
# Compute the loss of the val batch.
loss = self.det_loss(predictions, targets, objmask, noobjmask)
self.val_losses.update(loss.item(), inputs.size(0))
batch_detections = YOLOv3Test.decode(detections, self.configer,
input_size)
batch_pred_bboxes = self.__get_object_list(
batch_detections, input_size)
self.det_running_score.update(batch_pred_bboxes,
batch_gt_bboxes, batch_gt_labels)
# 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: {}'.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, input_size):
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_conf, cls_pred in detections:
xmin = x1.cpu().item()
ymin = y1.cpu().item()
xmax = x2.cpu().item()
ymax = y2.cpu().item()
cf = conf.cpu().item()
cls_pred = cls_pred.cpu().item()
object_list.append([
xmin, ymin, xmax, ymax,
int(cls_pred),
float('%.2f' % 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 = DetModelManager(configer)
self.det_data_loader = DataLoader(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_img(self, image_path, json_path, raw_path, vis_path):
Log.info('Image Path: {}'.format(image_path))
image = ImageHelper.read_image(
image_path,
tool=self.configer.get('data', 'image_tool'),
mode=self.configer.get('data', 'input_mode'))
ori_img_bgr = ImageHelper.get_cv2_bgr(image,
mode=self.configer.get(
'data', 'input_mode'))
width, height = ImageHelper.get_size(image)
scale1 = self.configer.get('test', 'resize_bound')[0] / min(
width, height)
scale2 = self.configer.get('test', 'resize_bound')[1] / max(
width, height)
scale = min(scale1, scale2)
inputs = self.blob_helper.make_input(image, scale=scale)
b, c, h, w = inputs.size()
border_wh = [w, h]
if self.configer.exists('test', 'fit_stride'):
stride = self.configer.get('test', 'fit_stride')
pad_w = 0 if (w % stride == 0) else stride - (w % stride) # right
pad_h = 0 if (h % stride == 0) else stride - (h % stride) # down
expand_image = torch.zeros(
(b, c, h + pad_h, w + pad_w)).to(inputs.device)
expand_image[:, :, 0:h, 0:w] = inputs
inputs = expand_image
data_dict = dict(
img=inputs,
meta=DataContainer([[
dict(ori_img_size=ImageHelper.get_size(ori_img_bgr),
aug_img_size=border_wh,
img_scale=scale,
input_size=[inputs.size(3),
inputs.size(2)])
]],
cpu_only=True))
with torch.no_grad():
# Forward pass.
test_group = self.det_net(data_dict)
test_indices_and_rois, test_roi_locs, test_roi_scores, test_rois_num = test_group
batch_detections = self.decode(test_roi_locs, test_roi_scores,
test_indices_and_rois, test_rois_num,
self.configer,
DCHelper.tolist(data_dict['meta']))
json_dict = self.__get_info_tree(batch_detections[0],
ori_img_bgr,
scale=scale)
image_canvas = self.det_parser.draw_bboxes(
ori_img_bgr.copy(),
json_dict,
conf_threshold=self.configer.get('res', 'vis_conf_thre'))
cv2.imwrite(vis_path, image_canvas)
cv2.imwrite(raw_path, ori_img_bgr)
Log.info('Json Path: {}'.format(json_path))
JsonHelper.save_file(json_dict, json_path)
return json_dict
@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)
# roi_locs = roi_locs[:,:, [1, 0, 3, 2]]
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)):
# batch_index = (indices_and_rois[:, 0] == i).nonzero().contiguous().view(-1,)
# tmp_dst_bbox = dst_bbox[batch_index]
# tmp_cls_prob = cls_prob[batch_index]
# tmp_cls_label = cls_label[batch_index]
tmp_dst_bbox = dst_bbox[start_index:start_index + test_rois_num[i]]
# clip bounding box
tmp_dst_bbox[:, :, 0::2] = tmp_dst_bbox[:, :, 0::2].clamp(
min=0, max=metas[i]['border_size'][0] - 1)
tmp_dst_bbox[:, :, 1::2] = tmp_dst_bbox[:, :, 1::2].clamp(
min=0, max=metas[i]['border_size'][1] - 1)
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)
output[i] = DetHelper.cls_nms(valid_preds,
labels=valid_preds[:, 5],
max_threshold=configer.get(
'nms', 'max_threshold'))
return output
def __get_info_tree(self, detections, image_raw, scale=1.0):
height, width, _ = image_raw.shape
json_dict = dict()
object_list = list()
if detections is not None:
for x1, y1, x2, y2, conf, cls_pred in detections:
object_dict = dict()
xmin = min(x1.cpu().item() / scale, width - 1)
ymin = min(y1.cpu().item() / scale, height - 1)
xmax = min(x2.cpu().item() / scale, width - 1)
ymax = min(y2.cpu().item() / scale, height - 1)
object_dict['bbox'] = [xmin, ymin, xmax, ymax]
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
def debug(self, vis_dir):
count = 0
for i, data_dict in enumerate(self.det_data_loader.get_trainloader()):
feat_list = list()
input_size = data_dict['meta'][0]['input_size']
for stride in self.configer.get('rpn', 'stride_list'):
feat_list.append(
torch.zeros(
(data_dict['img'].size(0), 1, input_size[1] // stride,
input_size[0] // stride)))
gt_rpn_locs, gt_rpn_labels = self.rpn_target_generator(
feat_list, data_dict['bboxes'], data_dict['meta'])
eye_matrix = torch.eye(2)
gt_rpn_labels[gt_rpn_labels == -1] = 0
gt_rpn_scores = eye_matrix[gt_rpn_labels.view(-1)].view(
data_dict['img'].size(0), -1, 2)
test_indices_and_rois, _ = self.fr_roi_generator(
feat_list, gt_rpn_locs, gt_rpn_scores,
self.configer.get('rpn', 'n_test_pre_nms'),
self.configer.get('rpn', 'n_test_post_nms'), data_dict['meta'])
sample_rois, gt_roi_locs, gt_roi_labels = self.roi_sampler(
test_indices_and_rois, data_dict['bboxes'],
data_dict['labels'], data_dict['meta'])
self.det_visualizer.vis_rois(data_dict['img'],
sample_rois[gt_roi_labels > 0])
gt_cls_roi_locs = torch.zeros(
(gt_roi_locs.size(0), self.configer.get('data',
'num_classes'), 4))
gt_cls_roi_locs[torch.arange(0, sample_rois.size(0)).long(),
gt_roi_labels.long()] = gt_roi_locs
gt_cls_roi_locs = gt_cls_roi_locs.contiguous().view(
-1, 4 * self.configer.get('data', 'num_classes'))
eye_matrix = torch.eye(self.configer.get('data', 'num_classes'))
gt_roi_scores = eye_matrix[gt_roi_labels.view(-1)].view(
gt_roi_labels.size(0),
self.configer.get('data', 'num_classes'))
test_rois_num = torch.zeros((len(data_dict['bboxes']), )).long()
for batch_id in range(len(data_dict['bboxes'])):
batch_index = (
sample_rois[:, 0] == batch_id).nonzero().contiguous().view(
-1, )
test_rois_num[batch_id] = batch_index.numel()
batch_detections = FastRCNNTest.decode(gt_cls_roi_locs,
gt_roi_scores, sample_rois,
test_rois_num,
self.configer,
data_dict['meta'])
for j in range(data_dict['img'].size(0)):
count = count + 1
if count > 20:
exit(1)
ori_img_bgr = self.blob_helper.tensor2bgr(data_dict['img'][j])
self.det_visualizer.vis_default_bboxes(
ori_img_bgr, self.fr_priorbox_layer(feat_list, input_size),
gt_rpn_labels[j])
json_dict = self.__get_info_tree(batch_detections[j],
ori_img_bgr)
image_canvas = self.det_parser.draw_bboxes(
ori_img_bgr.copy(),
json_dict,
conf_threshold=self.configer.get('res', 'vis_conf_thre'))
cv2.imwrite(
os.path.join(vis_dir, '{}_{}_vis.png'.format(i, j)),
image_canvas)
cv2.imshow('main', image_canvas)
cv2.waitKey()