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.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 = 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()
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 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 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
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_size'][0] - 1)
tmp_dst_bbox[:, :, 1::2] = tmp_dst_bbox[:, :, 1::2].clamp(min=0, max=metas[i]['border_size'][1] - 1)
tmp_dst_bbox *= (metas[i]['ori_img_size'][0] / metas[i]['border_size'][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 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
loc, conf = self.det_net(data_dict)
meta_list = DCHelper.tolist(data_dict['meta'])
batch_detections = self.decode(loc, 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
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.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('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_preds = DetHelper.cls_nms(valid_preds[:, :6],
labels=valid_preds[:, 5],
max_threshold=configer.get('res', '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()