def __call__(self, batch):
images, labels = zip(*batch)
imgH = self.imgH
imgW = self.imgW
images = [
resizePadding(image, self.imgW, self.imgH) for image in images
]
images = torch.cat([t.unsqueeze(0) for t in images], 0)
return images, labels
def predict(self, image):
image = Image.fromarray(image)
image = utils.resizePadding(image, None, self.height)
image = image.view(1, *image.size())
image = Variable(image)
image = image.to(self.device)
preds = self.model(image)
preds = preds.squeeze(1)
sim_pred, sent_prob = self.decode(preds)
return sim_pred, sent_prob
def predicts(self, images):
images = [Image.fromarray(image) for image in images]
sizes = [image.size for image in images]
maxW = utils.maxWidth(sizes, self.height)
images = [
utils.resizePadding(image, maxW, self.height) for image in images
]
image = torch.cat([t.unsqueeze(0) for t in images], 0)
image = image.to(self.device)
preds = self.model(image)
rs = []
for i in range(len(images)):
sim_pred, sent_prob = self.decode(preds[:, i, :])
rs.append((sim_pred, sent_prob))
return rs
opt = parser.parse_args()
alphabet = open(opt.alphabet).read().rstrip()
nclass = len(alphabet) + 1
nc = 3
model = crnn.CRNN(opt.imgH, nc, nclass, 256)
if torch.cuda.is_available():
model = model.cuda()
print('loading pretrained model from %s' % opt.model)
model.load_state_dict(torch.load(opt.model, map_location='cpu'))
converter = strLabelConverter(alphabet, ignore_case=False)
image = Image.open(opt.img).convert('RGB')
image = resizePadding(image, opt.imgW, opt.imgH)
if torch.cuda.is_available():
image = image.cuda()
image = image.view(1, *image.size())
image = Variable(image)
model.eval()
start_time = time.time()
preds = model(image)
values, prob = softmax(preds, dim=-1).max(2)
preds_idx = (prob > 0).nonzero()
sent_prob = values[preds_idx[:, 0], preds_idx[:, 1]].mean().item()
