Spaces:
Runtime error
Runtime error
| import gradio as gr | |
| from transformers import ( | |
| AutoTokenizer, | |
| AutoModelForSequenceClassification, | |
| ) | |
| ### Loading models and tokenizers as global variables | |
| tokenizer_title = AutoTokenizer.from_pretrained("./model_title") | |
| model_title = AutoModelForSequenceClassification.from_pretrained("./model_title") | |
| tokenizer_summary = AutoTokenizer.from_pretrained("./model_summary") | |
| model_summary = AutoModelForSequenceClassification.from_pretrained("./model_summary") | |
| categories = [ | |
| 'biology', | |
| 'computer_science', | |
| 'economics', | |
| 'electrical_engineering', | |
| 'finance', | |
| 'mathematics', | |
| 'physics', | |
| 'statistics', | |
| 'unknown' | |
| ] | |
| ### Auxiliary functions | |
| def classify_title(input_text): | |
| input_tokens = tokenizer_title.encode( | |
| input_text, | |
| truncation=True, | |
| padding=True, | |
| return_tensors='pt' | |
| ) | |
| preds = model_title(input_tokens) | |
| [probs] = preds.logits.softmax(dim=-1).tolist() | |
| return {cat: p for (cat, p) in zip(categories, probs)} | |
| def classify_summary(input_text): | |
| input_tokens = tokenizer_summary.encode( | |
| input_text, | |
| truncation=True, | |
| padding=True, | |
| return_tensors='pt' | |
| ) | |
| preds = model_summary(input_tokens) | |
| [probs] = preds.logits.softmax(dim=-1).tolist() | |
| return {cat: prob for (cat, prob) in zip(categories, probs)} | |
| def classify_title_summary(title, summary, weight_title=3, weight_summary=1): | |
| clsf_title = classify_title(title) | |
| clsf_summary = classify_summary(summary) | |
| clsf_both = dict() | |
| for cat in categories: | |
| clsf_p = clsf_title[cat] * weight_title + clsf_summary[cat] * weight_summary | |
| clsf_both[cat] = clsf_p / (weight_title + weight_summary) | |
| return clsf_both | |
| def get_top_classifications(clsf, p_top=0.95): | |
| clsf_top = dict() | |
| p_total = 0 | |
| clsf_sorted = sorted(clsf.items(), key=lambda x: x[1], reverse=True) | |
| for cat, p in clsf_sorted: | |
| if p_total >= p_top: | |
| break | |
| clsf_top[cat] = p | |
| p_total += p | |
| return clsf_top | |
| ### Gradio interface | |
| def process_input(title, summary): | |
| if not title: | |
| return None, "Title cannot be empty" | |
| if len(title.split()) < 3: | |
| return None, "Title should be at least three words long" | |
| clsf = classify_title(title) if not summary else classify_title_summary(title, summary) | |
| clsf = get_top_classifications(clsf, p_top=0.95) | |
| return clsf, None | |
| title_box = gr.inputs.Textbox(lines=2, placeholder="Your title...", optional=False, label='Article Title') | |
| summary_box = gr.inputs.Textbox(lines=12, placeholder="Your summary...", optional=True, label='Article Summary') | |
| label_widget = gr.outputs.Label(label='Top-95% Predicted Topics') | |
| message_box = gr.outputs.Textbox(label='Errors') | |
| iface = gr.Interface( | |
| fn=process_input, | |
| inputs=[title_box, summary_box], | |
| outputs=[label_widget, message_box], | |
| title="Article Classifier", | |
| description="A transformer-based classifier that infers the topic of scientific articles based on a title and summary.", | |
| allow_flagging="never" | |
| ) | |
| iface.launch() | |