def create_and_check_bert_model(self, config, input_ids, token_type_ids,
input_mask, sequence_labels, token_labels,
choice_labels):
model = TFBertModel(config=config)
inputs = {
"input_ids": input_ids,
"attention_mask": input_mask,
"token_type_ids": token_type_ids
}
sequence_output, pooled_output = model(inputs)
inputs = [input_ids, input_mask]
sequence_output, pooled_output = model(inputs)
sequence_output, pooled_output = model(input_ids)
result = {
"sequence_output": sequence_output.numpy(),
"pooled_output": pooled_output.numpy(),
}
self.parent.assertListEqual(
list(result["sequence_output"].shape),
[self.batch_size, self.seq_length, self.hidden_size])
self.parent.assertListEqual(list(result["pooled_output"].shape),
[self.batch_size, self.hidden_size])
def test_model_from_pretrained(self):
cache_dir = "/tmp/transformers_test/"
# for model_name in list(TF_BERT_PRETRAINED_MODEL_ARCHIVE_MAP.keys())[:1]:
for model_name in ['bert-base-uncased']:
model = TFBertModel.from_pretrained(model_name, cache_dir=cache_dir)
shutil.rmtree(cache_dir)
self.assertIsNotNone(model)
def create_and_check_bert_model(
self, config, input_ids, token_type_ids, input_mask, sequence_labels, token_labels, choice_labels
):
model = TFBertModel(config=config)
inputs = {"input_ids": input_ids, "attention_mask": input_mask, "token_type_ids": token_type_ids}
sequence_output, pooled_output = model(inputs)
inputs = [input_ids, input_mask]
result = model(inputs)
result = model(input_ids)
self.parent.assertEqual(result.last_hidden_state.shape, (self.batch_size, self.seq_length, self.hidden_size))
self.parent.assertEqual(result.pooler_output.shape, (self.batch_size, self.hidden_size))
def __init__(self, config, *inputs, **kwargs):
super().__init__(config, *inputs, **kwargs)
self.num_layers = config.num_labels
self.backbone = TFBertModel(config,
*inputs,
**kwargs,
name="bert_backbone")
self.dropout = tf.keras.layers.Dropout(0.2)
self.dropout_multisampled = tf.keras.layers.Dropout(0.5)
self.weighted_sum = WeightedSumLayer(config.num_hidden_layers)
self.classifier = tf.keras.layers.Dense(
config.num_labels,
kernel_initializer=get_initializer(config.initializer_range),
name="classifier")
self.backbone.bert.pooler._trainable = False
def test_model_from_pretrained(self):
# for model_name in TF_BERT_PRETRAINED_MODEL_ARCHIVE_LIST[:1]:
for model_name in ["bert-base-uncased"]:
model = TFBertModel.from_pretrained(model_name)
self.assertIsNotNone(model)
def test_model_from_pretrained(self):
# for model_name in list(TF_BERT_PRETRAINED_MODEL_ARCHIVE_MAP.keys())[:1]:
for model_name in ["bert-base-uncased"]:
model = TFBertModel.from_pretrained(model_name, cache_dir=CACHE_DIR)
self.assertIsNotNone(model)
def test_model_from_pretrained(self):
model = TFBertModel.from_pretrained("jplu/tiny-tf-bert-random")
self.assertIsNotNone(model)