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

[T5, TF 2.2] change tf t5 argument naming (#3547)

Browse Source 
* change tf t5 argument naming for TF 2.2

* correct bug in testing
This commit is contained in:
Patrick von Platen
2020-04-01 22:04:20 +02:00
committed by GitHub
parent 06dd597552
commit a4ee4da18a
3 changed files with 36 additions and 25 deletions
Download Patch File Download Diff File Expand all files Collapse all files

18
tests/test_modeling_tf_common.py
View File

@@ -162,6 +162,10 @@ class TFModelTesterMixin:
pt_inputs_dict = dict(
(name, torch.from_numpy(key.numpy()).to(torch.long)) for name, key in inputs_dict.items()
)
# need to rename encoder-decoder "inputs" for PyTorch
if "inputs" in pt_inputs_dict and self.is_encoder_decoder:
pt_inputs_dict["input_ids"] = pt_inputs_dict.pop("inputs")
with torch.no_grad():
pto = pt_model(**pt_inputs_dict)
tfo = tf_model(inputs_dict, training=False)
@@ -201,6 +205,10 @@ class TFModelTesterMixin:
pt_inputs_dict = dict(
(name, torch.from_numpy(key.numpy()).to(torch.long)) for name, key in inputs_dict.items()
)
# need to rename encoder-decoder "inputs" for PyTorch
if "inputs" in pt_inputs_dict and self.is_encoder_decoder:
pt_inputs_dict["input_ids"] = pt_inputs_dict.pop("inputs")
with torch.no_grad():
pto = pt_model(**pt_inputs_dict)
tfo = tf_model(inputs_dict)
@@ -223,7 +231,7 @@ class TFModelTesterMixin:
if self.is_encoder_decoder:
input_ids = {
"decoder_input_ids": tf.keras.Input(batch_shape=(2, 2000), name="decoder_input_ids", dtype="int32"),
"input_ids": tf.keras.Input(batch_shape=(2, 2000), name="input_ids", dtype="int32"),
"inputs": tf.keras.Input(batch_shape=(2, 2000), name="inputs", dtype="int32"),
}
else:
input_ids = tf.keras.Input(batch_shape=(2, 2000), name="input_ids", dtype="int32")
@@ -259,7 +267,7 @@ class TFModelTesterMixin:
outputs_dict = model(inputs_dict)
inputs_keywords = copy.deepcopy(inputs_dict)
input_ids = inputs_keywords.pop("input_ids" if not self.is_encoder_decoder else "decoder_input_ids", None,)
input_ids = inputs_keywords.pop("input_ids" if not self.is_encoder_decoder else "inputs", None,)
outputs_keywords = model(input_ids, **inputs_keywords)
output_dict = outputs_dict[0].numpy()
@@ -395,9 +403,9 @@ class TFModelTesterMixin:
input_ids = inputs_dict["input_ids"]
del inputs_dict["input_ids"]
else:
encoder_input_ids = inputs_dict["input_ids"]
encoder_input_ids = inputs_dict["inputs"]
decoder_input_ids = inputs_dict["decoder_input_ids"]
del inputs_dict["input_ids"]
del inputs_dict["inputs"]
del inputs_dict["decoder_input_ids"]
for model_class in self.all_model_classes:
@@ -415,7 +423,7 @@ class TFModelTesterMixin:
def test_lm_head_model_random_generate(self):
config, inputs_dict = self.model_tester.prepare_config_and_inputs_for_common()
input_ids = inputs_dict["input_ids"]
input_ids = inputs_dict["input_ids"] if "input_ids" in inputs_dict else inputs_dict["inputs"]
if self.is_encoder_decoder:
config.output_past = True # needed for Bart TODO: might have to update for other encoder-decoder models