I am trying to predict with the NER model, as in the tutorial from huggingface (it contains only the training+evaluation part).
I am following this exact tutorial here : https://github.com/huggingface/notebooks/blob/master/examples/token_classification.ipynb
The training works flawlessly, but the problems that I have begin when I try to predict on a simple sample.
model_checkpoint = "distilbert-base-uncased"
tokenizer = AutoTokenizer.from_pretrained(model_checkpoint)
loaded_model = AutoModel.from_pretrained('./my_model_own_custom_training.pth',
from_tf=False)
input_sentence = "John Nash is a great mathematician, he lives in France"
tokenized_input_sentence = tokenizer([input_sentence],
truncation=True,
is_split_into_words=False,
return_tensors='pt')
predictions = loaded_model(tokenized_input_sentence["input_ids"])[0]
Predictions is of shape (1,13,768)
How can I arrive at the final result of the form [JOHN <-> ‘B-PER’, … France <-> “B-LOC”], where B-PER and B-LOC are two ground truth labels, representing the tag for a person and location respectively?
The result of the prediction is:
torch.Size([1, 13, 768])
If I write:
print(predictions.argmax(axis=2))
tensor([613, 705, 244, 620, 206, 206, 206, 620, 620, 620, 477, 693, 308])
I get the tensor above.
However I would have expected to get the tensor representing the ground truth [0…8] labels from the ground truth annotations.
Summary when loading the model :
loading configuration file ./my_model_own_custom_training.pth/config.json Model config DistilBertConfig { “name_or_path": “distilbert-base-uncased”, “activation”: “gelu”, “architectures”: [ “DistilBertForTokenClassification” ], “attention_dropout”: 0.1, “dim”: 768, “dropout”: 0.1, “hidden_dim”: 3072, “id2label”: { “0”: “LABEL_0”, “1”: “LABEL_1”, “2”: “LABEL_2”, “3”: “LABEL_3”, “4”: “LABEL_4”, “5”: “LABEL_5”, “6”: “LABEL_6”, “7”: “LABEL_7”, “8”: “LABEL_8” }, “initializer_range”: 0.02, “label2id”: { “LABEL_0”: 0, “LABEL_1”: 1, “LABEL_2”: 2, “LABEL_3”: 3, “LABEL_4”: 4, “LABEL_5”: 5, “LABEL_6”: 6, “LABEL_7”: 7, “LABEL_8”: 8 }, “max_position_embeddings”: 512, “model_type”: “distilbert”, “n_heads”: 12, “n_layers”: 6, “pad_token_id”: 0, “qa_dropout”: 0.1, “seq_classif_dropout”: 0.2, “sinusoidal_pos_embds”: false, "tie_weights”: true, “transformers_version”: “4.8.1”, “vocab_size”: 30522 }
The answer is a bit trickier than expected[Huge credits to Niels Rogge].
Firstly, loading models in huggingface-transformers can be done in (at least) two ways:
AutoModel.from_pretrained('./my_model_own_custom_training.pth', from_tf=False)AutoModelForTokenClassification.from_pretrained('./my_model_own_custom_training.pth', from_tf=False)It seems that, according to the task at hand, different AutoModels subclasses need to be used. In this scenario I posted, it is the AutoModelForTokenClassification() that has to be used.
After that, a solution to obtain the predictions would be to do the following:
# forward pass
outputs = model(**encoding)
logits = outputs.logits
predictions = logits.argmax(-1)