class OcrDetCTPN():
def __init__(self, model_path='./checkpoints/CTPN.pth'):
self.model = CTPN_Model()
self.use_gpu = torch.cuda.is_available()
if self.use_gpu:
self.model.cuda()
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
self.model.load_state_dict(
torch.load(model_path, map_location=device)['model_state_dict'])
for p in self.model.parameters():
p.requires_grad = False
self.model.eval()
self.prob_thresh = 0.5
def inference(self, image):
image_sz = resize(image, height=ctpn_params.IMAGE_HEIGHT)
# 宽高缩放比例(等比例缩放)
rescale_fac = image.shape[0] / image_sz.shape[0]
h, w = image_sz.shape[:2]
# 减均值
image_sz = image_sz.astype(np.float32) - ctpn_params.IMAGE_MEAN
image_sz = torch.from_numpy(image_sz.transpose(
2, 0, 1)).unsqueeze(0).float()
if self.use_gpu:
image_sz = image_sz.cuda()
cls, regr = self.model(image_sz)
cls_prob = F.softmax(cls, dim=-1).cpu().numpy()
regr = regr.cpu().numpy()
anchor = gen_anchor((int(h / 16), int(w / 16)), 16)
bbox = bbox_transfor_inv(anchor, regr)
bbox = clip_box(bbox, [h, w])
fg = np.where(cls_prob[0, :, 1] > self.prob_thresh)[0]
select_anchor = bbox[fg, :]
select_score = cls_prob[0, fg, 1]
select_anchor = select_anchor.astype(np.int32)
keep_index = filter_bbox(select_anchor, 16)
# nms
select_anchor = select_anchor[keep_index]
select_score = select_score[keep_index]
select_score = np.reshape(select_score, (select_score.shape[0], 1))
nmsbox = np.hstack((select_anchor, select_score))
keep = nms(nmsbox, 0.3)
select_anchor = select_anchor[keep]
select_score = select_score[keep]
# text line-
textConn = TextProposalConnectorOriented()
text = textConn.get_text_lines(select_anchor, select_score, [h, w])
text = [np.hstack((res[:8] * rescale_fac, res[8])) for res in text]
return text
print('#################### Start evaluate ####################')
print(f'loss: {total_loss:.4f}')
print(f'classification loss: {total_cls_loss:.4f}')
print(f'vertical regression loss: {total_v_reg_loss:.4f}')
print(f'{epoch_size} iterations for {total_time:.4f} seconds, avg {avg_infer_time:.4f} seconds.')
print('##################### Evaluate end #####################')
print('\n')
return total_cls_loss, total_v_reg_loss, total_loss
if __name__ == "__main__":
opt = parser.parse_args()
device = torch.device("cuda:0" if torch.cuda.is_available() else "cpu")
model = CTPN_Model()
criterion_cls = RPN_CLS_Loss(device)
criterion_regr = RPN_REGR_Loss(device)
if torch.cuda.is_available():
torch.backends.cudnn.benchmark = True
model = model.cuda()
val_dataset = vocDataset(opt.data_root)
val_dataloader = DataLoader(val_dataset, batch_size=opt.batch_size, shuffle=False, num_workers=4)
if opt.model_path !='' and os.path.exists(opt.model_path):
print('loading pretrained model from %s' % opt.model_path)
cc = torch.load(opt.model_path, map_location=device)
model.load_state_dict(cc['model_state_dict'])
loss_cls, loss_regr, loss = val(model, val_dataloader, criterion_cls, criterion_regr, device)
else:
print(f'evaluate Error: {opt.model_path} doesnot exist')
