Merge remote-tracking branch 'refs/remotes/huggingface/master'

README.md

@@ -58,7 +58,7 @@ Choose the right framework for every part of a model's lifetime
 | [Quick tour: Fine-tuning/usage scripts](#quick-tour-of-the-fine-tuningusage-scripts) | Using provided scripts: GLUE, SQuAD and Text generation |
 | [Migrating from pytorch-transformers to transformers](#Migrating-from-pytorch-transformers-to-transformers) | Migrating your code from pytorch-transformers to transformers |
 | [Migrating from pytorch-pretrained-bert to pytorch-transformers](#Migrating-from-pytorch-pretrained-bert-to-transformers) | Migrating your code from pytorch-pretrained-bert to transformers |
-| [Documentation][(v2.2.0/v2.2.1)](https://huggingface.co/transformers/v2.2.0) [(v2.1.1)](https://huggingface.co/transformers/v2.1.1) [(v2.0.0)](https://huggingface.co/transformers/v2.0.0) [(v1.2.0)](https://huggingface.co/transformers/v1.2.0) [(v1.1.0)](https://huggingface.co/transformers/v1.1.0) [(v1.0.0)](https://huggingface.co/transformers/v1.0.0) [(master)](https://huggingface.co/transformers) | Full API documentation and more |
+| [Documentation][(v2.2.0/v2.2.1/v2.2.2)](https://huggingface.co/transformers/v2.2.0) [(v2.1.1)](https://huggingface.co/transformers/v2.1.1) [(v2.0.0)](https://huggingface.co/transformers/v2.0.0) [(v1.2.0)](https://huggingface.co/transformers/v1.2.0) [(v1.1.0)](https://huggingface.co/transformers/v1.1.0) [(v1.0.0)](https://huggingface.co/transformers/v1.0.0) [(master)](https://huggingface.co/transformers) | Full API documentation and more |
 
 ## Installation
 

docs/source/conf.py

@@ -26,7 +26,7 @@ author = u'huggingface'
 # The short X.Y version
 version = u''
 # The full version, including alpha/beta/rc tags
-release = u'2.2.1'
+release = u'2.2.2'
 
 
 # -- General configuration ---------------------------------------------------

examples/run_squad.py

@@ -580,10 +580,16 @@ def main():
     # Evaluation - we can ask to evaluate all the checkpoints (sub-directories) in a directory
     results = {}
     if args.do_eval and args.local_rank in [-1, 0]:
-        checkpoints = [args.output_dir]
-        if args.eval_all_checkpoints:
-            checkpoints = list(os.path.dirname(c) for c in sorted(glob.glob(args.output_dir + '/**/' + WEIGHTS_NAME, recursive=True)))
-            logging.getLogger("transformers.modeling_utils").setLevel(logging.WARN)  # Reduce model loading logs
+
+        if args.do_train:
+            logger.info("Loading checkpoints saved during training for evaluation")
+            checkpoints = [args.output_dir]
+            if args.eval_all_checkpoints:
+                checkpoints = list(os.path.dirname(c) for c in sorted(glob.glob(args.output_dir + '/**/' + WEIGHTS_NAME, recursive=True)))
+                logging.getLogger("transformers.modeling_utils").setLevel(logging.WARN)  # Reduce model loading logs
+        else:
+            logger.info("Loading checkpoint %s for evaluation", args.model_name_or_path)
+            checkpoints = [args.model_name_or_path]
 
         logger.info("Evaluate the following checkpoints: %s", checkpoints)
 

examples/summarization/README.md

@@ -29,7 +29,7 @@ And move all the stories to the same folder. We will refer as `$DATA_PATH` the p
 python run_summarization.py \
     --documents_dir $DATA_PATH \
     --summaries_output_dir $SUMMARIES_PATH \ # optional
-    --to_cpu false \
+    --no_cuda false \
     --batch_size 4 \
     --min_length 50 \
     --max_length 200 \
@@ -39,7 +39,7 @@ python run_summarization.py \
     --compute_rouge true
 ```
 
-The scripts executes on GPU if one is available and if `to_cpu` is not set to `true`. Inference on multiple GPUs is not suported yet. The ROUGE scores will be displayed in the console at the end of evaluation and written in a `rouge_scores.txt` file. The script takes 30 hours to compute with a single Tesla V100 GPU and a batch size of 10 (300,000 texts to summarize).
+The scripts executes on GPU if one is available and if `no_cuda` is not set to `true`. Inference on multiple GPUs is not suported yet. The ROUGE scores will be displayed in the console at the end of evaluation and written in a `rouge_scores.txt` file. The script takes 30 hours to compute with a single Tesla V100 GPU and a batch size of 10 (300,000 texts to summarize).
 
 ## Summarize any text
 
@@ -49,7 +49,7 @@ Put the documents that you would like to summarize in a folder (the path to whic
 python run_summarization.py \
     --documents_dir $DATA_PATH \
     --summaries_output_dir $SUMMARIES_PATH \ # optional
-    --to_cpu false \
+    --no_cuda false \
     --batch_size 4 \
     --min_length 50 \
     --max_length 200 \

setup.py

@@ -44,7 +44,7 @@ extras['all'] = [package for package in extras.values()]
 
 setup(
     name="transformers",
-    version="2.2.1",
+    version="2.2.2",
     author="Thomas Wolf, Lysandre Debut, Victor Sanh, Julien Chaumond, Google AI Language Team Authors, Open AI team Authors, Facebook AI Authors, Carnegie Mellon University Authors",
     author_email="thomas@huggingface.co",
     description="State-of-the-art Natural Language Processing for TensorFlow 2.0 and PyTorch",

transformers/__init__.py

-__version__ = "2.2.1"
+__version__ = "2.2.2"
 
 # Work around to update TensorFlow's absl.logging threshold which alters the
 # default Python logging output behavior when present.

transformers/commands/user.py

@@ -19,8 +19,8 @@ class UserCommands(BaseTransformersCLICommand):
         list_parser.set_defaults(func=lambda args: ListObjsCommand(args))
         # upload
         upload_parser = parser.add_parser('upload')
-        upload_parser.add_argument('file', type=str, help='Local filepath of the file to upload.')
-        upload_parser.add_argument('--filename', type=str, default=None, help='Optional: override object filename on S3.')
+        upload_parser.add_argument('path', type=str, help='Local path of the folder or individual file to upload.')
+        upload_parser.add_argument('--filename', type=str, default=None, help='Optional: override individual object filename on S3.')
         upload_parser.set_defaults(func=lambda args: UploadCommand(args))
 
 
@@ -138,28 +138,57 @@ class ListObjsCommand(BaseUserCommand):
 
 
 class UploadCommand(BaseUserCommand):
+    def walk_dir(self, rel_path):
+        """
+        Recursively list all files in a folder.
+        """
+        entries: List[os.DirEntry] = list(os.scandir(rel_path))
+        files = [
+            (
+                os.path.join(os.getcwd(), f.path),  # filepath
+                f.path  # filename
+            )
+            for f in entries if f.is_file()
+        ]
+        for f in entries:
+            if f.is_dir():
+                files += self.walk_dir(f.path)
+        return files
+
     def run(self):
         token = HfFolder.get_token()
         if token is None:
             print("Not logged in")
             exit(1)
-        filepath = os.path.join(os.getcwd(), self.args.file)
-        filename = self.args.filename if self.args.filename is not None else os.path.basename(filepath)
-        print(
-            "About to upload file {} to S3 under filename {}".format(
-                ANSI.bold(filepath), ANSI.bold(filename)
+        local_path = os.path.abspath(self.args.path)
+        if os.path.isdir(local_path):
+            if self.args.filename is not None:
+                raise ValueError("Cannot specify a filename override when uploading a folder.")
+            rel_path = os.path.basename(local_path)
+            files = self.walk_dir(rel_path)
+        elif os.path.isfile(local_path):
+            filename = self.args.filename if self.args.filename is not None else os.path.basename(local_path)
+            files = [(local_path, filename)]
+        else:
+            raise ValueError("Not a valid file or directory: {}".format(local_path))
+
+        for filepath, filename in files:
+            print(
+                "About to upload file {} to S3 under filename {}".format(
+                    ANSI.bold(filepath), ANSI.bold(filename)
+                )
             )
-        )
 
         choice = input("Proceed? [Y/n] ").lower()
         if not(choice == "" or choice == "y" or choice == "yes"):
             print("Abort")
             exit()
         print(
-            ANSI.bold("Uploading... This might take a while if file is large")
+            ANSI.bold("Uploading... This might take a while if files are large")
         )
-        access_url = self._api.presign_and_upload(
-            token=token, filename=filename, filepath=filepath
-        )
-        print("Your file now lives at:")
-        print(access_url)
+        for filepath, filename in files:
+            access_url = self._api.presign_and_upload(
+                token=token, filename=filename, filepath=filepath
+            )
+            print("Your file now lives at:")
+            print(access_url)

transformers/data/processors/glue.py

@@ -133,7 +133,7 @@ def glue_convert_examples_to_features(examples, tokenizer,
     if is_tf_available() and is_tf_dataset:
         def gen():
             for ex in features:
-                yield  ({'input_ids': ex.input_ids,
+                yield ({'input_ids': ex.input_ids,
                          'attention_mask': ex.attention_mask,
                          'token_type_ids': ex.token_type_ids},
                         ex.label)

transformers/tests/tokenization_bert_test.py

@@ -139,5 +139,6 @@ class BertTokenizationTest(CommonTestCases.CommonTokenizerTester):
         assert encoded_sentence == [101] + text + [102]
         assert encoded_pair == [101] + text + [102] + text_2 + [102]
 
+
 if __name__ == '__main__':
     unittest.main()

transformers/tests/tokenization_gpt2_test.py

@@ -67,6 +67,5 @@ class GPT2TokenizationTest(CommonTestCases.CommonTokenizerTester):
         self.assertListEqual(
             tokenizer.convert_tokens_to_ids(input_tokens), input_bpe_tokens)
 
-
 if __name__ == '__main__':
     unittest.main()

transformers/tests/tokenization_tests_commons.py

@@ -232,6 +232,15 @@ class CommonTestCases:
             self.assertNotEqual(len(tokens_2), 0)
             self.assertIsInstance(text_2, (str, unicode))
 
+        def test_encode_decode_with_spaces(self):
+            tokenizer = self.get_tokenizer()
+
+            new_toks = ['[ABC]', '[DEF]', 'GHI IHG']
+            tokenizer.add_tokens(new_toks)
+            input = "[ABC] [DEF] [ABC] GHI IHG [DEF]"
+            encoded = tokenizer.encode(input, add_special_tokens=False)
+            decoded = tokenizer.decode(encoded)
+            self.assertEqual(decoded, input)
 
         def test_pretrained_model_lists(self):
             weights_list = list(self.tokenizer_class.max_model_input_sizes.keys())

transformers/tokenization_utils.py

@@ -637,9 +637,11 @@ class PreTrainedTokenizer(object):
             text: The sequence to be encoded.
             **kwargs: passed to the child `self.tokenize()` method
         """
+        all_special_tokens = self.all_special_tokens
+
         def lowercase_text(t):
             # convert non-special tokens to lowercase
-            escaped_special_toks = [re.escape(s_tok) for s_tok in self.all_special_tokens]
+            escaped_special_toks = [re.escape(s_tok) for s_tok in all_special_tokens]
             pattern = r'(^' + r'|'.join(escaped_special_toks) + r')|' + \
                       r'(.+?)'
             return re.sub(
@@ -680,17 +682,17 @@ class PreTrainedTokenizer(object):
                 tokenized_text = []
                 for sub_text in text_list:
                     if sub_text not in self.added_tokens_encoder \
-                            and sub_text not in self.all_special_tokens:
+                            and sub_text not in all_special_tokens:
                         tokenized_text += split_on_token(tok, sub_text)
                     else:
                         tokenized_text += [sub_text]
                 text_list = tokenized_text
 
             return list(itertools.chain.from_iterable((self._tokenize(token, **kwargs) if token not \
-                    in self.added_tokens_encoder and token not in self.all_special_tokens \
+                    in self.added_tokens_encoder and token not in all_special_tokens \
                     else [token] for token in tokenized_text)))
 
-        added_tokens = list(self.added_tokens_encoder.keys()) + self.all_special_tokens
+        added_tokens = list(self.added_tokens_encoder.keys()) + all_special_tokens
         tokenized_text = split_on_tokens(added_tokens, text)
         return tokenized_text
 
@@ -1178,12 +1180,12 @@ class PreTrainedTokenizer(object):
                 if current_sub_text:
                     sub_texts.append(self.convert_tokens_to_string(current_sub_text))
                     current_sub_text = []
-                sub_texts.append(" " + token)
+                sub_texts.append(token)
             else:
                 current_sub_text.append(token)
         if current_sub_text:
             sub_texts.append(self.convert_tokens_to_string(current_sub_text))
-        text = ''.join(sub_texts)
+        text = ' '.join(sub_texts)
 
         if clean_up_tokenization_spaces:
             clean_text = self.clean_up_tokenization(text)