Kunndoiii/IS361-03-Multi-Label-Classification

1import gradio as gr2import numpy as np3import torch4from transformers import AutoTokenizer, AutoModelForSequenceClassification5 6id2label = {0: 'anger', 1: 'anticipation', 2: 'disgust', 3: 'fear', 4: 'joy', 5: 'love', 6: 'optimism', 7: 'pessimism', 8: 'sadness', 9: 'surprise', 10: 'trust'}7tokenizer = AutoTokenizer.from_pretrained("winain7788/bert-finetuned-sem_eval-english")8model = AutoModelForSequenceClassification.from_pretrained("winain7788/bert-finetuned-sem_eval-english")9 10async def get_sentiment(text):11    encoding = tokenizer(text, return_tensors="pt")12    encoding = {k: v.to(model.device) for k,v in encoding.items()}13 14    outputs = model(**encoding)15    logits = outputs.logits16    logits.shape17    # apply sigmoid + threshold18    sigmoid = torch.nn.Sigmoid()19    probs = sigmoid(logits.squeeze().cpu())20    predictions = np.zeros(probs.shape)21    predictions[np.where(probs >= 0.5)] = 122 23    # turn predicted id's into actual label names24    predicted_labels = [id2label[idx] for idx, label in enumerate(predictions) if label == 1.0]25    return predicted_labels26 27demo = gr.Interface(fn=get_sentiment, inputs="text", outputs="json")28 29demo.launch()