krishnaik06 / huggingfacetransformer

Huggingfacetransformer

huggingfacetransformer's Issues

TypeError: Exception encountered when calling layer "tf_distil_bert_for_sequence_classification" (type TFDistilBertForSequenceClassification). TypeError: 'NoneType' object is not callable

---

TypeError Traceback (most recent call last)
in ()
9 )
10
---> 11 trainer.train()

2 frames
/usr/local/lib/python3.7/dist-packages/tensorflow/python/framework/func_graph.py in autograph_handler(*args, **kwargs)
1145 except Exception as e: # pylint:disable=broad-except
1146 if hasattr(e, "ag_error_metadata"):
-> 1147 raise e.ag_error_metadata.to_exception(e)
1148 else:
1149 raise

TypeError: in user code:

File "/usr/local/lib/python3.7/dist-packages/transformers/trainer_tf.py", line 697, in distributed_training_steps  *
    self.args.strategy.run(self.apply_gradients, inputs)
File "/usr/local/lib/python3.7/dist-packages/transformers/trainer_tf.py", line 639, in apply_gradients  *
    gradients = self.training_step(features, labels, nb_instances_in_global_batch)
File "/usr/local/lib/python3.7/dist-packages/transformers/trainer_tf.py", line 622, in training_step  *
    per_example_loss, _ = self.run_model(features, labels, True)
File "/usr/local/lib/python3.7/dist-packages/transformers/trainer_tf.py", line 744, in run_model  *
    outputs = self.model(features, labels=labels, training=training)[:2]
File "/usr/local/lib/python3.7/dist-packages/keras/utils/traceback_utils.py", line 67, in error_handler  **
    raise e.with_traceback(filtered_tb) from None

TypeError: Exception encountered when calling layer "tf_distil_bert_for_sequence_classification" (type TFDistilBertForSequenceClassification).

in user code:

    File "/usr/local/lib/python3.7/dist-packages/transformers/models/distilbert/modeling_tf_distilbert.py", line 816, in call  *
        loss = None if inputs["labels"] is None else self.compute_loss(inputs["labels"], logits)
    File "/usr/local/lib/python3.7/dist-packages/keras/engine/training.py", line 919, in compute_loss  **
        y, y_pred, sample_weight, regularization_losses=self.losses)

    TypeError: 'NoneType' object is not callable


Call arguments received:
  • input_ids={'input_ids': 'tf.Tensor(shape=(8, 238), dtype=int32)', 'attention_mask': 'tf.Tensor(shape=(8, 238), dtype=int32)'}
  • attention_mask=None
  • head_mask=None
  • inputs_embeds=None
  • output_attentions=None
  • output_hidden_states=None
  • return_dict=None
  • labels=tf.Tensor(shape=(8,), dtype=int32)
  • training=True
  • kwargs=<class 'inspect._empty'>

Predicting sentiment of a single sentence

How to predict sentiment for a single sentence using the trainer(TFTrainer) in the given code.

The TFTrainer class has been deprecated in the Hugging Face Transformers library. Instead you can use.

Compile the model

optimizer = tf.keras.optimizers.Adam(learning_rate=5e-5)
loss = tf.keras.losses.SparseCategoricalCrossentropy(from_logits=True)
model.compile(optimizer=optimizer, loss=loss, metrics=['accuracy'])

Train the model

model.fit(train_dataset.batch(8), epochs=2, validation_data=test_dataset.batch(16))

Evaluate the model

evaluation = model.evaluate(test_dataset.batch(16))
print(f"Loss: {evaluation[0]}, Accuracy: {evaluation[1]}")

Make predictions

predictions = model.predict(test_dataset.batch(16))
predicted_labels = tf.argmax(predictions.logits, axis=1).numpy()

Compute confusion matrix

cm = confusion_matrix(y_test, predicted_labels)
print(cm)

Save the model

model.save_pretrained('senti_model')

Import Error : Deprecation of TFTrainer in the Hugging Face and usage of Keras is suggested

Import Error : Deprecation of TFTrainer in the Hugging Face and usage of Keras is suggested

TypeError: '>' not supported between instances of 'NoneType' and 'int'

While Executing the following code getting error:

with training_args.strategy.scope():
    model = TFDistilBertForSequenceClassification.from_pretrained("distilbert-base-uncased")

trainer = TFTrainer(
    model=model,                         # the instantiated 🤗 Transformers model to be trained
    args=training_args,                  # training arguments, defined above
    train_dataset=train_dataset,         # training dataset
    eval_dataset=test_dataset             # evaluation dataset
)

trainer.train()

Error:

---------------------------------------------------------------------------
TypeError                                 Traceback (most recent call last)
<ipython-input-37-78414b52dd9d> in <module>()
      9 )
     10 
---> 11 trainer.train()

/usr/local/lib/python3.7/dist-packages/transformers/trainer_tf.py in train(self)
    583 
    584                     if (
--> 585                         self.args.eval_steps > 0
    586                         and self.args.evaluation_strategy == IntervalStrategy.STEPS
    587                         and self.global_step % self.args.eval_steps == 0

TypeError: '>' not supported between instances of 'NoneType' and 'int'

TypeError: Expected bool passed to parameter 'y' of op 'NotEqual', got -100 of type 'int' instead. Error: Expected bool, but got -100 of type 'int'.

TypeError: in user code:

File "H:\NLP_Training\NLP_3.8\lib\site-packages\transformers\trainer_tf.py", line 701, in distributed_training_steps  *
    nb_instances_in_batch = self._compute_nb_instances(batch)
File "H:\NLP_Training\NLP_3.8\lib\site-packages\transformers\trainer_tf.py", line 713, in _compute_nb_instances  *
    nb_instances = tf.reduce_sum(tf.cast(labels != -100, dtype=tf.int32))

TypeError: Expected bool passed to parameter 'y' of op 'NotEqual', got -100 of type 'int' instead. Error: Expected bool, but got -100 of type 'int'.