def apply(self, sample: Sample) -> Sample:
inputs = sample.inputs.copy()
inputs["img"] = inputs["img"] / 255
if self.params.center:
inputs["img"] = (inputs["img"] - 0.5) * 2
return sample.new_inputs(inputs)
def apply(self, sample: Sample) -> Sample:
img = sample.inputs.transpose()
encoded = [self.data_params.codec.index(c) for c in sample.targets]
return sample.new_inputs({
Keys.Image: img,
Keys.ImageLength: np.array([img.shape[0]])
}).new_targets({
Keys.Targets: np.array(encoded),
Keys.TargetsLength: np.array([len(encoded)])
})
def apply(self, sample: Sample) -> Sample:
def encode_sentences(sentence1, sentence2):
tokens1 = list(self.tokenizer.tokenize(sentence1)) + [
self.tokenizer.sep_token
]
tokens2 = list(self.tokenizer.tokenize(sentence2)) + [
self.tokenizer.sep_token
]
return [self.tokenizer.cls_token] + tokens1 + tokens2, [
0
] + [0] * len(tokens1) + [1] * len(tokens2)
word_ids, type_ids = encode_sentences(
sample.inputs[Keys.InputSentence1],
sample.inputs[Keys.InputSentence2])
word_ids = self.tokenizer.convert_tokens_to_ids(word_ids)
return sample.new_inputs({
Keys.InputWordIds:
np.asarray(word_ids),
Keys.InputMask:
np.full(fill_value=1, shape=[len(word_ids)], dtype=np.int32),
Keys.InputTypeIds:
np.asarray(type_ids, dtype=np.int32),
})
def make_sample(self, file_id: str):
sample = Sample(
inputs={
k: self.parsed_files[k][file_id]
for k in self._input_keys
},
targets={
k: self.parsed_files[k][file_id]
for k in self._target_keys
},
meta={
"id": file_id,
**{
k + "_filename": v[file_id]
for k, v in self.parsed_files.items()
}
},
)
if len(sample.inputs) == 1:
sample = sample.new_inputs(list(sample.inputs.values())[0])
if len(sample.targets) == 1:
sample = sample.new_targets(list(sample.targets.values())[0])
return sample
def apply(self, sample: Sample) -> Sample:
return sample.new_inputs(
cv2.resize(
sample.inputs,
(self.data_params.image_height, self.data_params.image_width)))
def apply(self, sample: Sample) -> Sample:
return sample.new_inputs(sample.inputs + self.params.v)
def apply(self, sample: Sample) -> Sample:
return sample.new_inputs({"n": np.asarray([sample.inputs])}).new_targets(
{"n": np.asarray([sample.targets])}
)
def apply(self, sample: Sample) -> Sample:
img = cv2.imread(sample.inputs, flags=cv2.IMREAD_GRAYSCALE)
with open(sample.targets) as f:
txt = f.read().strip()
return sample.new_inputs(img).new_targets(txt)
def apply(self, sample: Sample) -> Sample:
assert self.data_params.height > 0 # Not initialized
return sample.new_inputs(
scale_to_h(sample.inputs, self.data_params.height))