Multiclass classification

[strongio]

Multiclass classification

[jacobzweig]

Hey @v4d0k – in convert_examples_to_features I reshape the labels array in the function return with np.array(labels).reshape(-1, 1). You'd want to change that to match your features.

[plchld]

Thank you!

[AxeldeRomblay]

Hello,

Like @v4d0k I have tried to apply your code on a multiclass problem (where each text/description can belong to several classes; eg: "Cristiano Ronaldo amazing goal vs Juventus" belongs both to "sport" and "football" classes). I have removed the .reshape(-1, 1) in convert_examples_to_features but after compiling the model with success, I have the following error when fitting the model :

InvalidArgumentError: logits must be 2-dimensional [[Node: bert_layer_1/bert_layer_2_module_apply_tokens/bert/encoder/layer_0/attention/self/Softmax = Softmax[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/device:CPU:0"](bert_layer_1/bert_layer_2_module_apply_tokens/bert/encoder/layer_0/attention/self/add)]]

Any ideas ? Also can you precise which tensorflow version you are using please ?
Thank you very much !

[Abhinav43]

@AxeldeRomblay have you found how to use this for multi class?

[Abhinav43]

@jacobzweig What changes i have to do in your model for multi class?

[Abhinav43]

@v4d0k did you find how to work with mulit-class? please share what changes we have to do??

[AxeldeRomblay]

@Abhinav43 it was just a version issue... Make sure you have tensorflow 1.14 and it should work ! :)

[Abhinav43]

@AxeldeRomblay I am getting other errors and not getting good accuracy in multi-class. can you share the code or tell me where I have to change in code for multi-label?

[AxeldeRomblay]

@Abhinav43 here is the code :

`class BertLayer(tf.keras.layers.Layer):
def init(
self,
n_fine_tune_layers=0,
pooling="first",
bert_path=BERT_PATH,
**kwargs,
):
self.n_fine_tune_layers = n_fine_tune_layers
self.trainable = True
self.output_size = BERT_OUTPUT
self.pooling = pooling
self.bert_path = bert_path
if self.pooling not in ["first", "mean"]:
raise NameError(
"Undefined pooling type (must be either first or mean)"
)

    super(BertLayer, self).__init__(**kwargs)

def build(self, input_shape):
    self.bert = hub.Module(
        self.bert_path,
        trainable=self.trainable,
        name="{}_module".format(self.name),
    )

    # Remove unused layers
    trainable_vars = self.bert.variables
    if self.pooling == "first":
        trainable_vars = [
            var for var in trainable_vars if not "/cls/" in var.name
        ]
        trainable_layers = ["pooler/dense"]

    elif self.pooling == "mean":
        trainable_vars = [
            var
            for var in trainable_vars
            if not "/cls/" in var.name and not "/pooler/" in var.name
        ]
        trainable_layers = []
    else:
        raise NameError(
            "Undefined pooling type (must be either first or mean)"
        )

    # Select how many layers to fine tune
    for i in range(self.n_fine_tune_layers):
        trainable_layers.append("encoder/layer_{}".format(str(11 - i)))

    # Update trainable vars to contain only the specified layers
    trainable_vars = [
        var
        for var in trainable_vars
        if any([l in var.name for l in trainable_layers])
    ]

    # Add to trainable weights
    for var in trainable_vars:
        self._trainable_weights.append(var)

    for var in self.bert.variables:
        if var not in self._trainable_weights:
            self._non_trainable_weights.append(var)

    super(BertLayer, self).build(input_shape)

def call(self, inputs):
    inputs = [K.cast(x, dtype="int32") for x in inputs]
    input_ids, input_mask, segment_ids = inputs
    bert_inputs = dict(
        input_ids=input_ids, input_mask=input_mask, segment_ids=segment_ids
    )
    if self.pooling == "first":
        pooled = self.bert(
            inputs=bert_inputs, signature="tokens", as_dict=True
        )["pooled_output"]
    elif self.pooling == "mean":
        result = self.bert(
            inputs=bert_inputs, signature="tokens", as_dict=True
        )["sequence_output"]

        mul_mask = lambda x, m: x * tf.expand_dims(m, axis=-1)
        masked_reduce_mean = lambda x, m: tf.reduce_sum(
            mul_mask(x, m), axis=1
        ) / (tf.reduce_sum(m, axis=1, keepdims=True) + 1e-10)
        input_mask = tf.cast(input_mask, tf.float32)
        pooled = masked_reduce_mean(result, input_mask)
    else:
        raise NameError(
            "Undefined pooling type (must be either first or mean)"
        )

    return pooled

def compute_output_shape(self, input_shape):
    return input_shape[0], self.output_size`

[AxeldeRomblay]

`class InputExample(object):
"""A single training/test example for simple sequence classification."""

def __init__(self, guid, text_a, text_b=None, label=None):
    """Constructs a InputExample.
Args:
  guid: Unique id for the example.
  text_a: string. The untokenized text of the first sequence. For single
    sequence tasks, only this sequence must be specified.
  text_b: (Optional) string. The untokenized text of the second sequence.
    Only must be specified for sequence pair tasks.
  label: (Optional) string. The label of the example. This should be
    specified for train and dev examples, but not for test examples.
"""
    self.guid = guid
    self.text_a = text_a
    self.text_b = text_b
    self.label = label

def convert_single_example(tokenizer, example, max_seq_length=512):
"""Converts a single InputExample into a single InputFeatures."""

if isinstance(example, PaddingInputExample):
    input_ids = [0] * max_seq_length
    input_mask = [0] * max_seq_length
    segment_ids = [0] * max_seq_length
    label = 0
    return input_ids, input_mask, segment_ids, label

tokens_a = tokenizer.tokenize(example.text_a)
if len(tokens_a) > max_seq_length - 2:
    tokens_a = tokens_a[0 : (max_seq_length - 2)]

tokens = []
segment_ids = []
tokens.append("[CLS]")
segment_ids.append(0)
for token in tokens_a:
    tokens.append(token)
    segment_ids.append(0)
tokens.append("[SEP]")
segment_ids.append(0)

input_ids = tokenizer.convert_tokens_to_ids(tokens)

# The mask has 1 for real tokens and 0 for padding tokens. Only real
# tokens are attended to.
input_mask = [1] * len(input_ids)

# Zero-pad up to the sequence length.
while len(input_ids) < max_seq_length:
    input_ids.append(0)
    input_mask.append(0)
    segment_ids.append(0)

assert len(input_ids) == max_seq_length
assert len(input_mask) == max_seq_length
assert len(segment_ids) == max_seq_length

return input_ids, input_mask, segment_ids, example.label

def convert_examples_to_features(tokenizer, examples, max_seq_length=512):
"""Convert a set of InputExamples to a list of InputFeatures."""

input_ids, input_masks, segment_ids, labels = [], [], [], []
for example in examples:
    input_id, input_mask, segment_id, label = convert_single_example(
        tokenizer, example, max_seq_length
    )
    input_ids.append(input_id)
    input_masks.append(input_mask)
    segment_ids.append(segment_id)
    labels.append(label)
return (
    np.array(input_ids).astype(np.int32),
    np.array(input_masks).astype(np.int32),
    np.array(segment_ids).astype(np.int32),
    np.array(labels),
)

def convert_text_to_examples(texts, labels):
"""Create InputExamples"""
InputExamples = []
for text, label in zip(texts, labels):
InputExamples.append(
InputExample(
guid=None, text_a=" ".join(text), text_b=None, label=label
)
)
return InputExamples`

[Abhinav43]

I am looking for model information. Should i use binary cross-entropy other one?

[elsheikh21]

@AxeldeRomblay I am trying to integrate bert as an embeddings layer in my model, however, everytime I get this Traceback

Traceback (most recent call last):
  File "code/prova_bert.py", line 230, in <module>
    model = baseline_model(output_size, max_seq_len, visualize=True)
  File "code/prova_bert.py", line 165, in baseline_model
    )(bert_embeddings)
  File "C:\Users\Sheikh\AppData\Local\Programs\Python\Python36\Lib\site-packages\tensorflow\python\keras\layers\wrappers.py", line 473, in __call__
    return super(Bidirectional, self).__call__(inputs, **kwargs)
  File "C:\Users\Sheikh\AppData\Local\Programs\Python\Python36\Lib\site-packages\tensorflow\python\keras\engine\base_layer.py", line 746, in __call__
    self.build(input_shapes)
  File "C:\Users\Sheikh\AppData\Local\Programs\Python\Python36\Lib\site-packages\tensorflow\python\keras\layers\wrappers.py", line 612, in build
    self.forward_layer.build(input_shape)
  File "C:\Users\Sheikh\AppData\Local\Programs\Python\Python36\Lib\site-packages\tensorflow\python\keras\utils\tf_utils.py", line 149, in wrapper
    output_shape = fn(instance, input_shape)
  File "C:\Users\Sheikh\AppData\Local\Programs\Python\Python36\Lib\site-packages\tensorflow\python\keras\layers\recurrent.py", line 552, in build
    self.cell.build(step_input_shape)
  File "C:\Users\Sheikh\AppData\Local\Programs\Python\Python36\Lib\site-packages\tensorflow\python\keras\utils\tf_utils.py", line 149, in wrapper
    output_shape = fn(instance, input_shape)
  File "C:\Users\Sheikh\AppData\Local\Programs\Python\Python36\Lib\site-packages\tensorflow\python\keras\layers\recurrent.py", line 1934, in build
    constraint=self.kernel_constraint)
  File "C:\Users\Sheikh\AppData\Local\Programs\Python\Python36\Lib\site-packages\tensorflow\python\keras\engine\base_layer.py", line 609, in add_weight
    aggregation=aggregation)
  File "C:\Users\Sheikh\AppData\Local\Programs\Python\Python36\Lib\site-packages\tensorflow\python\training\checkpointable\base.py", line 639, in _add_variable_with_custom_getter
    **kwargs_for_getter)
  File "C:\Users\Sheikh\AppData\Local\Programs\Python\Python36\Lib\site-packages\tensorflow\python\keras\engine\base_layer.py", line 1977, in make_variable
    aggregation=aggregation)
  File "C:\Users\Sheikh\AppData\Local\Programs\Python\Python36\Lib\site-packages\tensorflow\python\ops\variables.py", line 183, in __call__
    return cls._variable_v1_call(*args, **kwargs)
  File "C:\Users\Sheikh\AppData\Local\Programs\Python\Python36\Lib\site-packages\tensorflow\python\ops\variables.py", line 146, in _variable_v1_call
    aggregation=aggregation)
  File "C:\Users\Sheikh\AppData\Local\Programs\Python\Python36\Lib\site-packages\tensorflow\python\ops\variables.py", line 125, in <lambda>
    previous_getter = lambda **kwargs: default_variable_creator(None, **kwargs)
  File "C:\Users\Sheikh\AppData\Local\Programs\Python\Python36\Lib\site-packages\tensorflow\python\ops\variable_scope.py", line 2437, in default_variable_creator
    import_scope=import_scope)
  File "C:\Users\Sheikh\AppData\Local\Programs\Python\Python36\Lib\site-packages\tensorflow\python\ops\variables.py", line 187, in __call__
    return super(VariableMetaclass, cls).__call__(*args, **kwargs)
  File "C:\Users\Sheikh\AppData\Local\Programs\Python\Python36\Lib\site-packages\tensorflow\python\ops\resource_variable_ops.py", line 297, in __init__
    constraint=constraint)
  File "C:\Users\Sheikh\AppData\Local\Programs\Python\Python36\Lib\site-packages\tensorflow\python\ops\resource_variable_ops.py", line 409, in _init_from_args
    initial_value() if init_from_fn else initial_value,
  File "C:\Users\Sheikh\AppData\Local\Programs\Python\Python36\Lib\site-packages\tensorflow\python\keras\engine\base_layer.py", line 1959, in <lambda>
    shape, dtype=dtype, partition_info=partition_info)
  File "C:\Users\Sheikh\AppData\Local\Programs\Python\Python36\Lib\site-packages\tensorflow\python\ops\init_ops.py", line 473, in __call__
    scale /= max(1., (fan_in + fan_out) / 2.)
TypeError: unsupported operand type(s) for +: 'NoneType' and 'int'
Exception ignored in: <bound method BaseSession.__del__ of <tensorflow.python.client.session.Session object at 0x0000026396AD0630>>
Traceback (most recent call last):
  File "C:\Users\Sheikh\AppData\Local\Programs\Python\Python36\Lib\site-packages\tensorflow\python\client\session.py", line 738, in __del__
TypeError: 'NoneType' object is not callable

Here is my model, and I am using the implementation of strongio to the bert layer

here is an example of my data

# before tokenization, both are list of lists
train_x[0] = ['how long have it be since you review the objective of you benefit and service program ?']
train_y[0] =  [101, 1365, 13, 14, 20, 127, 32, 7939, 2, 2977, 5, 32, 7570, 6, 25584, 3785, 45]

""" 
# after those lines
tokenizer = create_tokenizer_from_hub_module()
train_examples = convert_text_to_examples(train_text, train_labels)
"""
train_examples[0].text_a = 'how long have it be since you review the objective of you benefit and service program ?'
train_examples[0].label= [101, 1365, 13, 14, 20, 127, 32, 7939, 2, 2977, 5, 32, 7570, 6, 25584, 3785, 45]

"""
# After the following lines
# Extract features
(train_input_ids, train_input_masks, train_segment_ids, train_labels) = convert_examples_to_features(tokenizer, train_examples, max_seq_length=max_seq_len) # max_seq_len = 512
"""

train_input_ids[0] = [ 101 2129 2146 2031 2009 2022 2144 2017 3319 1996 7863 1997 2017 5770
 1998 2326 2565 1029  102    0    0    0    0    0    0    0    0    0
    0    0    0    0    0    0    0    0    0    0    0    0    0    0
    0    0    0    0    0    0    0    0]

train_input_masks[0] = [1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 1 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0]

train_segment_ids[0] = [0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0
 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0 0]

train_labels[0] = [101, 1365, 13, 14, 20, 127, 32, 7939, 2, 2977, 5, 32, 7570, 6, 25584, 3785, 45]

Thank you and you may refer to my issue

[elsheikh21]

Solved my issue stackoverflow