def next_train_batch(self):
"""Get the next batch from train partition (yield)"""
while True:
if self.index['train'] >= self.size['train']:
self.index['train'] = 0
index = self.index['train']
until = self.index['train'] + self.batch_size
self.index['train'] = until
x_train = self.dataset['train']['dt'][index:until]
y_train = self.dataset['train']['gt'][index:until]
x_train = pp.augmentation(x_train,
rotation_range=1.5,
scale_range=0.05,
height_shift_range=0.025,
width_shift_range=0.05,
erode_range=5,
dilate_range=3)
x_train = pp.normalization(x_train)
y_train = [self.tokenizer.encode(y) for y in y_train]
y_train = pad_sequences(y_train,
maxlen=self.tokenizer.maxlen,
padding="post")
yield (x_train, y_train, [])
def next_train_batch(self):
"""Get the next batch from train partition (yield)"""
while True:
if self.index['train'] >= self.size['train']:
self.index['train'] = 0
index = self.index['train']
until = self.index['train'] + self.batch_size
self.index['train'] = until
x_train = self.dataset['train']['dt'][index:until]
x_train = pp.augmentation(x_train,
rotation_range=1.5,
scale_range=0.05,
height_shift_range=0.025,
width_shift_range=0.05,
erode_range=5,
dilate_range=3)
x_train = pp.normalization(x_train)
y_train = [
self.tokenizer.encode(y)
for y in self.dataset['train']['gt'][index:until]
]
y_train = [
np.pad(y, (0, self.tokenizer.maxlen - len(y))) for y in y_train
]
y_train = np.asarray(y_train, dtype=np.int16)
yield (x_train, y_train)
def next_train_batch(self):
"""Get the next batch from train partition (yield)"""
while True:
if self.train_index >= self.total_train:
self.train_index = 0
index = self.train_index
until = self.train_index + self.batch_size
self.train_index += self.batch_size
x_train = self.dataset["train"]["dt"][index:until]
y_train = self.dataset["train"]["gt"][index:until]
x_train = pp.augmentation(x_train,
rotation_range=1.5,
scale_range=0.05,
height_shift_range=0.025,
width_shift_range=0.05,
erode_range=5,
dilate_range=3)
x_train = pp.normalization(x_train)
x_train_len = np.asarray([self.max_text_length for _ in range(self.batch_size)])
y_train_len = np.asarray([len(np.trim_zeros(y_train[i])) for i in range(self.batch_size)])
inputs = {
"input": x_train,
"labels": y_train,
"input_length": x_train_len,
"label_length": y_train_len
}
output = {"CTCloss": np.zeros(self.batch_size)}
yield (inputs, output)
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 next_train_batch(self):
"""Get the next batch from train partition (yield)"""
while True:
if self.index['train'] >= self.size['train']:
self.index['train'] = 0
index = self.index['train']
until = self.index['train'] + self.batch_size
self.index['train'] += self.batch_size
x_train = self.dataset['train']['dt'][index:until]
y_train = self.dataset['train']['gt'][index:until]
x_train_len = np.asarray([self.tokenizer.maxlen for _ in range(self.batch_size)])
y_train_len = np.asarray([len(y_train[i]) for i in range(self.batch_size)])
x_train = pp.augmentation(x_train,
rotation_range=1.5,
scale_range=0.05,
height_shift_range=0.025,
width_shift_range=0.05,
erode_range=5,
dilate_range=3)
x_train = pp.normalization(x_train)
y_train = [self.tokenizer.encode(y) for y in y_train]
y_train = pad_sequences(y_train, maxlen=self.tokenizer.maxlen, padding="post")
inputs = {
"input": x_train,
"labels": y_train,
"input_length": x_train_len,
"label_length": y_train_len
}
output = {"CTCloss": np.zeros(self.batch_size, dtype=int)}
# x, y and sample_weight
yield (inputs, output, [])
