def preprocess_partitions(self, input_size):
"""Preprocess images and sentences from partitions"""
for y in self.partitions:
arange = range(len(self.dataset[y]['gt']))
for i in reversed(arange):
text = pp.text_standardize(self.dataset[y]['gt'][i])
if not self.check_text(text):
self.dataset[y]['gt'].pop(i)
self.dataset[y]['dt'].pop(i)
continue
self.dataset[y]['gt'][i] = text.encode()
results = []
# print("using cpu count:", 2)
# with multiprocessing.Pool(2) as pool:
# print(f"Partition: {y}")
# for result in tqdm(pool.imap(partial(pp.preprocess, input_size=input_size), self.dataset[y]['dt']),
# total=len(self.dataset[y]['dt'])):
# results.append(result)
# pool.close()
# pool.join()
print(f"Partition: {y}")
for imgpath in tqdm(self.dataset[y]['dt'],
total=len(self.dataset[y]['dt'])):
results.append(pp.preprocess(imgpath, input_size=input_size))
self.dataset[y]['dt'] = results
def getNext(self,train = True):
"iterator"
self.train = train
if self.train == True:
j = 0
else:
j = 1
while True:
if self.currIdx <= len(self.img_partitions[j]):
index = self.currIdx
until = self.currIdx + self.batchSize
else:
index = self.currIdx
until = len(self.img_partitions[j])
imgs = [pp.preprocess(os.path.join(self.filePath,self.img_partitions[j][i].filePath),self.imgSize) for i in range(index,until)]
imgs = pp.augmentation(imgs,
rotation_range=1.5,
scale_range=0.05,
height_shift_range=0.025,
width_shift_range=0.05,
erode_range=5,
dilate_range=3)
imgs = pp.normalization(imgs)
gtTexts = [self.img_partitions[j][i].gtText for i in range(index,until)]
gtTexts = [self.tokenizer.encode(gtTexts[i]) for i in range(len(gtTexts))]
gtTexts = [np.pad(i, (0, self.tokenizer.maxlen - len(i))) for i in gtTexts]
gtTexts = np.asarray(gtTexts, dtype=np.int16)
yield(imgs,gtTexts)
def read_text_from_image(self, img):
img = pp.preprocess(img, input_size=self.input_size)
x_test = pp.normalization([img])
predicts, probabilities = self.model.predict(x_test, ctc_decode=True)
predicts = [[self.tokenizer.decode(x) for x in y] for y in predicts]
for i, (pred, prob) in enumerate(zip(predicts, probabilities)):
return pred[0]
return ""
with open(predict_file, "r") as lg:
predicts = [line[5:] for line in lg if line.startswith("TE_P")]
for x in range(len(dt)):
print(f"Image shape:\t{dt[x].shape}")
print(f"Ground truth:\t{gt[x].decode()}")
print(f"Predict:\t{predicts[x]}\n")
cv2.imshow("img", pp.adjust_to_see(dt[x]))
cv2.waitKey(0)
elif args.image:
tokenizer = Tokenizer(chars=charset_base,
max_text_length=max_text_length)
img = pp.preprocess(args.image, input_size=input_size)
x_test = pp.normalization([img])
model = HTRModel(architecture=args.arch,
input_size=input_size,
vocab_size=tokenizer.vocab_size,
top_paths=10)
model.compile()
model.load_checkpoint(target=target_path)
predicts, probabilities = model.predict(x_test, ctc_decode=True)
predicts = [[tokenizer.decode(x) for x in y] for y in predicts]
print("\n####################################")
for i, (pred, prob) in enumerate(zip(predicts, probabilities)):