SUMIN/HuggingFace_transformer
1
0
Fork 0
Code Issues Pull Requests Actions 7 Packages Projects Releases Wiki Activity

Model output test (#6155)

Browse Source 
* Use return_dict=True in all tests

* Formatting
This commit is contained in:
Sylvain Gugger
2020-07-31 09:44:37 -04:00
committed by GitHub
parent 86caab1e0b
commit d951c14ae4
26 changed files with 320 additions and 765 deletions
Download Patch File Download Diff File Expand all files Collapse all files

46
tests/test_modeling_roberta.py
View File

@@ -96,6 +96,7 @@ class RobertaModelTester:
max_position_embeddings=self.max_position_embeddings,
type_vocab_size=self.type_vocab_size,
initializer_range=self.initializer_range,
return_dict=True,
)
return config, input_ids, token_type_ids, input_mask, sequence_labels, token_labels, choice_labels
@@ -109,18 +110,14 @@ class RobertaModelTester:
model = RobertaModel(config=config)
model.to(torch_device)
model.eval()
sequence_output, pooled_output = model(input_ids, attention_mask=input_mask, token_type_ids=token_type_ids)
sequence_output, pooled_output = model(input_ids, token_type_ids=token_type_ids)
sequence_output, pooled_output = model(input_ids)
result = model(input_ids, attention_mask=input_mask, token_type_ids=token_type_ids)
result = model(input_ids, token_type_ids=token_type_ids)
result = model(input_ids)
result = {
"sequence_output": sequence_output,
"pooled_output": pooled_output,
}
self.parent.assertListEqual(
list(result["sequence_output"].size()), [self.batch_size, self.seq_length, self.hidden_size]
list(result["last_hidden_state"].size()), [self.batch_size, self.seq_length, self.hidden_size]
)
self.parent.assertListEqual(list(result["pooled_output"].size()), [self.batch_size, self.hidden_size])
self.parent.assertListEqual(list(result["pooler_output"].size()), [self.batch_size, self.hidden_size])
def create_and_check_roberta_for_masked_lm(
self, config, input_ids, token_type_ids, input_mask, sequence_labels, token_labels, choice_labels
@@ -128,16 +125,8 @@ class RobertaModelTester:
model = RobertaForMaskedLM(config=config)
model.to(torch_device)
model.eval()
loss, prediction_scores = model(
input_ids, attention_mask=input_mask, token_type_ids=token_type_ids, labels=token_labels
)
result = {
"loss": loss,
"prediction_scores": prediction_scores,
}
self.parent.assertListEqual(
list(result["prediction_scores"].size()), [self.batch_size, self.seq_length, self.vocab_size]
)
result = model(input_ids, attention_mask=input_mask, token_type_ids=token_type_ids, labels=token_labels)
self.parent.assertListEqual(list(result["logits"].size()), [self.batch_size, self.seq_length, self.vocab_size])
self.check_loss_output(result)
def create_and_check_roberta_for_token_classification(
@@ -147,11 +136,7 @@ class RobertaModelTester:
model = RobertaForTokenClassification(config=config)
model.to(torch_device)
model.eval()
loss, logits = model(input_ids, attention_mask=input_mask, token_type_ids=token_type_ids, labels=token_labels)
result = {
"loss": loss,
"logits": logits,
}
result = model(input_ids, attention_mask=input_mask, token_type_ids=token_type_ids, labels=token_labels)
self.parent.assertListEqual(list(result["logits"].size()), [self.batch_size, self.seq_length, self.num_labels])
self.check_loss_output(result)
@@ -165,16 +150,12 @@ class RobertaModelTester:
multiple_choice_inputs_ids = input_ids.unsqueeze(1).expand(-1, self.num_choices, -1).contiguous()
multiple_choice_token_type_ids = token_type_ids.unsqueeze(1).expand(-1, self.num_choices, -1).contiguous()
multiple_choice_input_mask = input_mask.unsqueeze(1).expand(-1, self.num_choices, -1).contiguous()
loss, logits = model(
result = model(
multiple_choice_inputs_ids,
attention_mask=multiple_choice_input_mask,
token_type_ids=multiple_choice_token_type_ids,
labels=choice_labels,
)
result = {
"loss": loss,
"logits": logits,
}
self.parent.assertListEqual(list(result["logits"].size()), [self.batch_size, self.num_choices])
self.check_loss_output(result)
@@ -184,18 +165,13 @@ class RobertaModelTester:
model = RobertaForQuestionAnswering(config=config)
model.to(torch_device)
model.eval()
loss, start_logits, end_logits = model(
result = model(
input_ids,
attention_mask=input_mask,
token_type_ids=token_type_ids,
start_positions=sequence_labels,
end_positions=sequence_labels,
)
result = {
"loss": loss,
"start_logits": start_logits,
"end_logits": end_logits,
}
self.parent.assertListEqual(list(result["start_logits"].size()), [self.batch_size, self.seq_length])
self.parent.assertListEqual(list(result["end_logits"].size()), [self.batch_size, self.seq_length])
self.check_loss_output(result)