def main(opts):
alphabet = '0123456789.'
nclass = len(alphabet) + 1
model_name = 'crnn'
net = CRNN(nclass)
print("Using {0}".format(model_name))
if opts.cuda:
net.cuda()
learning_rate = opts.base_lr
optimizer = torch.optim.Adam(net.parameters(), lr=opts.base_lr, weight_decay=weight_decay)
if os.path.exists(opts.model):
print('loading model from %s' % args.model)
step_start, learning_rate = net_utils.load_net(args.model, net, optimizer)
## 数据集
converter = strLabelConverter(alphabet)
dataset = ImgDataset(
root='/home/yangna/deepblue/OCR/mech_demo2/dataset/imgs/image',
csv_root='/home/yangna/deepblue/OCR/mech_demo2/dataset/imgs/train_list.txt',
transform=None,
target_transform=converter.encode
)
ocrdataloader = torch.utils.data.DataLoader(
dataset, batch_size=1, shuffle=False, collate_fn=own_collate
)
num_count = 0
net = net.eval()
converter = strLabelConverter(alphabet)
ctc_loss = CTCLoss()
for step in range(len(dataset)):
try:
data = next(data_iter)
except:
data_iter = iter(ocrdataloader)
data = next(data_iter)
im_data, gt_boxes, text = data
im_data = im_data.cuda()
try:
res = process_crnn(im_data, gt_boxes, text, net, ctc_loss, converter, training=False)
pred, target = res
if pred == target[0]:
num_count += 1
except:
import sys, traceback
traceback.print_exc(file=sys.stdout)
pass
print('correct/total:%d/%d'%(num_count, len(dataset)))
def main(opts):
alphabet = '0123456789.'
nclass = len(alphabet) + 1
model_name = 'crnn'
net = CRNN(nclass)
print("Using {0}".format(model_name))
if opts.cuda:
net.cuda()
learning_rate = opts.base_lr
optimizer = torch.optim.Adam(net.parameters(), lr=opts.base_lr, weight_decay=weight_decay)
if os.path.exists(opts.model):
print('loading model from %s' % args.model)
step_start, learning_rate = net_utils.load_net(args.model, net, optimizer)
## 数据集
converter = strLabelConverter(alphabet)
dataset = ImgDataset(
root='/home/yangna/deepblue/OCR/mech_demo2/dataset/imgs/image',
csv_root='/home/yangna/deepblue/OCR/mech_demo2/dataset/imgs/train_list.txt',
transform=None,
target_transform=converter.encode
)
ocrdataloader = torch.utils.data.DataLoader(
dataset, batch_size=opts.batch_size, shuffle=True, collate_fn=own_collate
)
step_start = 0
net.train()
converter = strLabelConverter(alphabet)
ctc_loss = CTCLoss()
for step in range(step_start, opts.max_iters):
try:
data = next(data_iter)
except:
data_iter = iter(ocrdataloader)
data = next(data_iter)
im_data, gt_boxes, text = data
im_data = im_data.cuda()
try:
loss= process_crnn(im_data, gt_boxes, text, net, ctc_loss, converter, training=True)
net.zero_grad()
optimizer.zero_grad()
loss.backward()
optimizer.step()
except:
import sys, traceback
traceback.print_exc(file=sys.stdout)
pass
if step % disp_interval == 0:
try:
print('step:%d || loss %.4f' % (step, loss))
except:
import sys, traceback
traceback.print_exc(file=sys.stdout)
pass
if step > step_start and (step % batch_per_epoch == 0):
save_name = os.path.join(opts.save_path, '{}_{}.h5'.format(model_name, step))
state = {'step': step,
'learning_rate': learning_rate,
'state_dict': net.state_dict(),
'optimizer': optimizer.state_dict()}
torch.save(state, save_name)
print('save model: {}'.format(save_name))
m.bias.data.fill_(0)
crnn = crnn.CRNN(opt.imgH, nc, nclass, opt.nh)
crnn.apply(weights_init)
if opt.pretrained != '':
print('loading pretrained model from %s' % opt.pretrained)
crnn.load_state_dict(torch.load(opt.pretrained))
print(crnn)
image = torch.FloatTensor(opt.batchSize, 3, opt.imgH, opt.imgH)
text = torch.IntTensor(opt.batchSize * 5)
length = torch.IntTensor(opt.batchSize)
if opt.cuda:
crnn.cuda()
crnn = torch.nn.DataParallel(crnn, device_ids=range(opt.ngpu))
image = image.cuda()
criterion = criterion.cuda()
image = Variable(image)
text = Variable(text)
length = Variable(length)
# loss averager
loss_avg = utils.averager()
# setup optimizer
if opt.adam:
optimizer = optim.Adam(crnn.parameters(),
lr=opt.lr,
