Alexander Abramov Ab1992ao

## siamesenetwork_training.ipynb

      
              1 file
            
          
              0 forks
            
          
              0 comments
            
          
              0 stars
            
          
                Ab1992ao
                / siamesenetwork_training.ipynb
            
            
              Created
              January 28, 2023 21:07
                — forked from ishacusp/siamesenetwork_training.ipynb
            
              
                siamesenetwork_training
              
          
        Loading

      Sorry, something went wrong. Reload?
      Sorry, we cannot display this file.
      Sorry, this file is invalid so it cannot be displayed.
      
          Viewer requires iframe.
      
    
## softmax_loss.py
def softmax_loss(vectors):
    anc, pos, neg = vectors

    c = 0.5

    anc = c * anc
    pos = c * pos
    neg = c * neg

    pos_sim = tf.reduce_sum((anc * pos), axis=-1, keepdims=True)

## train_sbert_config.py
class TrainingConfig:
    def __init__(self, **kwargs):

        self.model_name = "sbert_tuned"
        self.data_dir = "/content/drive/MyDrive/"
        self.module_path = "/content/bert_module/"
        self.pretrained_ckpt = None
        self.generation = "sbert"

        self.ctx_len = 24

## ner_tag_collback.py
class TagCallback(Callback):
    def __init__(self, dataset, call_model=None, name="NER_ACC"):

        self.call_model = call_model
        self.dataset = dataset
        self.best = 0
        self.name = name
        super(TagCallback, self).__init__()

    def on_epoch_end(self, epoch, logs=None):

## toxic_task_callback.py
class AucCallback(Callback):
    def __init__(self, dataset, call_model=None, savepath=None, name="AUC"):

        self.call_model = call_model
        self.dataset = dataset
        self.best = 0
        self.name = name
        self.savepath = savepath
        super(AucCallback, self).__init__()

## build_mltsk_model.py
class SBERT:
    def __init__(self, config):
        self.loss = 0
        self.metrics = []
        self.inputs = []
        self.config = config
        self.build()

    def build(self):


## joint_loss.py
def softmax_loss(vectors):
    anc, pos, neg = vectors

    c = 0.5

    anc = c * anc
    pos = c * pos
    neg = c * neg

    pos_sim = tf.reduce_sum((anc * pos), axis=-1, keepdims=True)

## multitask_data_generator.py
class MultitaskDataGenerator:
    def __init__(self, generators):
        self.generators = generators
        self.generator = self.generate_batch()

    def generate_batch(self, batch_size=None):
        while True:
            batch = self.__next__()
            yield batch


## multiclass_generator.py
class MulticlassGenerator:
    def __init__(self, data_tuple, batch_size=256):
        self._data = data_tuple
        self._idx = np.arange(len(data_tuple[-1]))
        self.generator = self.generate_batch(batch_size)

    def generate_batch(self, size):
        while True:
            px_ids = np.random.choice(self._idx, size, replace=False)
            samples = [p[px_ids] for p in self._data[:-1]]

## triplet_generator.py
class TripletGenerator:
    def __init__(self, datadict, hard_frac = 0.5, batch_size=256):
        self.datadict = datadict
        self._anchor_idx = np.array(list(self.datadict.keys()))
        self._hard_frac = hard_frac
        self.generator = self.generate_batch(batch_size)

    def generate_batch(self, size):
        while True:
	def softmax_loss(vectors):
	anc, pos, neg = vectors

	c = 0.5

	anc = c * anc
	pos = c * pos
	neg = c * neg

	pos_sim = tf.reduce_sum((anc * pos), axis=-1, keepdims=True)
	class TrainingConfig:
	def __init__(self, **kwargs):

	self.model_name = "sbert_tuned"
	self.data_dir = "/content/drive/MyDrive/"
	self.module_path = "/content/bert_module/"
	self.pretrained_ckpt = None
	self.generation = "sbert"

	self.ctx_len = 24
	class TagCallback(Callback):
	def __init__(self, dataset, call_model=None, name="NER_ACC"):

	self.call_model = call_model
	self.dataset = dataset
	self.best = 0
	self.name = name
	super(TagCallback, self).__init__()

	def on_epoch_end(self, epoch, logs=None):
	class AucCallback(Callback):
	def __init__(self, dataset, call_model=None, savepath=None, name="AUC"):

	self.call_model = call_model
	self.dataset = dataset
	self.best = 0
	self.name = name
	self.savepath = savepath
	super(AucCallback, self).__init__()
	class SBERT:
	def __init__(self, config):
	self.loss = 0
	self.metrics = []
	self.inputs = []
	self.config = config
	self.build()

	def build(self):
	class MultitaskDataGenerator:
	def __init__(self, generators):
	self.generators = generators
	self.generator = self.generate_batch()

	def generate_batch(self, batch_size=None):
	while True:
	batch = self.__next__()
	yield batch
	class MulticlassGenerator:
	def __init__(self, data_tuple, batch_size=256):
	self._data = data_tuple
	self._idx = np.arange(len(data_tuple[-1]))
	self.generator = self.generate_batch(batch_size)

	def generate_batch(self, size):
	while True:
	px_ids = np.random.choice(self._idx, size, replace=False)
	samples = [p[px_ids] for p in self._data[:-1]]
	class TripletGenerator:
	def __init__(self, datadict, hard_frac = 0.5, batch_size=256):
	self.datadict = datadict
	self._anchor_idx = np.array(list(self.datadict.keys()))
	self._hard_frac = hard_frac
	self.generator = self.generate_batch(batch_size)

	def generate_batch(self, size):
	while True: