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
from ctpn_utils import gen_anchor, bbox_transfor_inv, clip_box, filter_bbox,nms, TextProposalConnectorOriented
from ctpn_utils import resize
import config
prob_thresh = 0.8
width = 600
#device = torch.device('cuda:0' if torch.cuda.is_available() else 'cpu')
device = torch.device('cpu')
#weights = os.path.join(config.checkpoints_dir, 'trained weights file.pth.tar')
weights = config.model_path
model = CTPN_Model()
model.load_state_dict(torch.load(weights, map_location=device)['model_state_dict'])
model.to(device)
model.eval()
def dis(image):
cv2.imshow('image', image)
cv2.waitKey(0)
cv2.destroyAllWindows()
filenames = [os.path.join(config.img_path, file) for file in os.listdir(config.img_path)]
print(filenames)
if os.path.exists(checkpoints_weight):
pretrained = False
# dataset = VOCDataset(args['image_dir'], args['labels_dir'])
dataset = FakepagesDataset(args['image_dir'], args['labels_dir'])
dataloader = DataLoader(dataset,
batch_size=1,
shuffle=True,
num_workers=args['num_workers'])
model = CTPN_Model()
model.to(device)
if os.path.exists(checkpoints_weight):
print('using pretrained weight: {}'.format(checkpoints_weight))
cc = torch.load(checkpoints_weight, map_location=device)
model.load_state_dict(cc['model_state_dict'])
try:
resume_epoch = cc['epoch']
except KeyError:
resume_epoch = 0
params_to_uodate = model.parameters()
optimizer = optim.SGD(params_to_uodate, lr=lr, momentum=0.9)
critetion_cls = RPN_CLS_Loss(device)
critetion_regr = RPN_REGR_Loss(device)
best_loss_cls = 100
best_loss_regr = 100
best_loss = 100
best_model = None