Adding the LXMERT pretraining model (MultiModal languageXvision) to HuggingFace's suite of models (#5793)

* added template files for LXMERT and competed the configuration_lxmert.py * added modeling, tokization, testing, and finishing touched for lxmert [yet to be tested] * added model card for lxmert * cleaning up lxmert code * Update src/transformers/modeling_lxmert.py Co-authored-by: Lysandre Debut <lysandre@huggingface.co> * Update src/transformers/modeling_tf_lxmert.py Co-authored-by: Lysandre Debut <lysandre@huggingface.co> * Update src/transformers/modeling_tf_lxmert.py Co-authored-by: Lysandre Debut <lysandre@huggingface.co> * Update src/transformers/modeling_lxmert.py Co-authored-by: Lysandre Debut <lysandre@huggingface.co> * tested torch lxmert, changed documtention, updated outputs, and other small fixes * Update src/transformers/convert_pytorch_checkpoint_to_tf2.py Co-authored-by: Lysandre Debut <lysandre@huggingface.co> * Update src/transformers/convert_pytorch_checkpoint_to_tf2.py Co-authored-by: Lysandre Debut <lysandre@huggingface.co> * Update src/transformers/convert_pytorch_checkpoint_to_tf2.py Co-authored-by: Lysandre Debut <lysandre@huggingface.co> * renaming, other small issues, did not change TF code in this commit * added lxmert question answering model in pytorch * added capability to edit number of qa labels for lxmert * made answer optional for lxmert question answering * add option to return hidden_states for lxmert * changed default qa labels for lxmert * changed config archive path * squshing 3 commits: merged UI + testing improvments + more UI and testing * changed some variable names for lxmert * TF LXMERT * Various fixes to LXMERT * Final touches to LXMERT * AutoTokenizer order * Add LXMERT to index.rst and README.md * Merge commit test fixes + Style update * TensorFlow 2.3.0 sequential model changes variable names Remove inherited test * Update src/transformers/modeling_tf_pytorch_utils.py * Update docs/source/model_doc/lxmert.rst Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com> * Update docs/source/model_doc/lxmert.rst Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com> * Update src/transformers/modeling_tf_lxmert.py Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com> * added suggestions * Fixes * Final fixes for TF model * Fix docs Co-authored-by: Lysandre Debut <lysandre@huggingface.co> Co-authored-by: Lysandre <lysandre.debut@reseau.eseo.fr> Co-authored-by: Sylvain Gugger <35901082+sgugger@users.noreply.github.com>
2020-09-03 04:02:25 -04:00
parent 4ebb52afdb
commit ea2c6f1afc
23 changed files with 4798 additions and 12 deletions
--- a/tests/test_tokenization_lxmert.py
+++ b/tests/test_tokenization_lxmert.py
@@ -0,0 +1,65 @@
+# coding=utf-8
+# Copyright 2018 LXMERT Authors.
+#
+# Licensed under the Apache License, Version 2.0 (the "License");
+# you may not use this file except in compliance with the License.
+# You may obtain a copy of the License at
+#
+#     http://www.apache.org/licenses/LICENSE-2.0
+#
+# Unless required by applicable law or agreed to in writing, software
+# distributed under the License is distributed on an "AS IS" BASIS,
+# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
+# See the License for the specific language governing permissions and
+# limitations under the License.
+
+
+import os
+import unittest
+
+from transformers.tokenization_bert import VOCAB_FILES_NAMES
+from transformers.tokenization_lxmert import LxmertTokenizer
+
+from .test_tokenization_common import TokenizerTesterMixin
+
+
+class LxmertTokenizationTest(TokenizerTesterMixin, unittest.TestCase):
+
+    tokenizer_class = LxmertTokenizer
+
+    def setUp(self):
+        super().setUp()
+
+        vocab_tokens = [
+            "[UNK]",
+            "[CLS]",
+            "[SEP]",
+            "want",
+            "##want",
+            "##ed",
+            "wa",
+            "un",
+            "runn",
+            "##ing",
+            ",",
+            "low",
+            "lowest",
+        ]
+        self.vocab_file = os.path.join(self.tmpdirname, VOCAB_FILES_NAMES["vocab_file"])
+        with open(self.vocab_file, "w", encoding="utf-8") as vocab_writer:
+            vocab_writer.write("".join([x + "\n" for x in vocab_tokens]))
+
+    def get_tokenizer(self, **kwargs):
+        return LxmertTokenizer.from_pretrained(self.tmpdirname, **kwargs)
+
+    def get_input_output_texts(self, tokenizer):
+        input_text = "UNwant\u00E9d,running"
+        output_text = "unwanted, running"
+        return input_text, output_text
+
+    def test_full_tokenizer(self):
+        tokenizer = self.tokenizer_class(self.vocab_file)
+
+        tokens = tokenizer.tokenize("UNwant\u00E9d,running")
+        self.assertListEqual(tokens, ["un", "##want", "##ed", ",", "runn", "##ing"])
+        self.assertListEqual(tokenizer.convert_tokens_to_ids(tokens), [7, 4, 5, 10, 8, 9])