| from peft import AutoPeftModelForSequenceClassification
|
| from transformers import AutoTokenizer
|
| from pathlib import Path
|
| import torch
|
| import json
|
|
|
| model_name = "oracat/bert-paper-classifier-arxiv"
|
| output_model_path = Path(f"./checkpoints/{model_name.split('/')[-1]}/checkpoints")
|
| save_path = Path("./data")
|
|
|
| device = "cuda" if torch.cuda.is_available() else "cpu"
|
|
|
|
|
| with open(save_path / "ids2cat.json", "r", encoding="utf-8") as f:
|
| ids2cat = json.load(f)
|
| ids2cat = {int(k): v for k, v in ids2cat.items()}
|
|
|
| num_labels = len(ids2cat)
|
|
|
|
|
| model = AutoPeftModelForSequenceClassification.from_pretrained(
|
| output_model_path / "final_model",
|
| num_labels=num_labels,
|
| problem_type="multi_label_classification",
|
| ignore_mismatched_sizes=True
|
| )
|
|
|
| tokenizer = AutoTokenizer.from_pretrained(model_name)
|
|
|
| model = model.to(device)
|
| model.eval()
|
|
|
|
|
| @torch.inference_mode()
|
| def predict(
|
| text: str,
|
| threshold: float = 0.5,
|
| max_length: int = 512,
|
| ):
|
| inputs = tokenizer(
|
| text,
|
| return_tensors="pt",
|
| truncation=True,
|
| padding=True,
|
| max_length=max_length,
|
| )
|
| inputs = {k: v.to(device) for k, v in inputs.items()}
|
|
|
| outputs = model(**inputs)
|
|
|
| probs = torch.sigmoid(outputs.logits[0]).cpu()
|
|
|
| pred_ids = (probs >= threshold).nonzero(as_tuple=True)[0].tolist()
|
| pred_labels = [ids2cat[i] for i in pred_ids]
|
|
|
| return {
|
| "labels": pred_labels,
|
| "scores": {ids2cat[i]: float(probs[i]) for i in range(num_labels)},
|
| }
|
|
|
|
|
| if __name__ == "__main__":
|
| text = """Macroscopic transport patterns of UAV traffic in 3D anisotropic wind fields: A constraint-preserving hybrid PINN-FVM approach""" + '\n\n' + """Macroscopic unmanned aerial vehicle (UAV) traffic organization in three-dimensional airspace faces significant challenges from static wind fields and complex obstacles. A critical difficulty lies in simultaneously capturing the strong anisotropy induced by wind while strictly preserving transport consistency and boundary semantics, which are often compromised in standard physics-informed learning approaches. To resolve this, we propose a constraint-preserving hybrid solver that integrates a physics-informed neural network for the anisotropic Eikonal value problem with a conservative finite-volume method for steady density transport. These components are coupled through an outer Picard iteration with under-relaxation, where the target condition is hard-encoded and strictly conservative no-flux boundaries are enforced during the transport step. We evaluate the framework on reproducible homing and point-to-point scenarios, effectively capturing value slices, induced-motion patterns, and steady density structures such as bands and bottlenecks. Ultimately, our perspective emphasizes the value of a reproducible computational framework supported by transparent empirical diagnostics to enable the traceable assessment of macroscopic traffic phenomena."""
|
|
|
| result = predict(text, threshold=0.7)
|
|
|
| print("Predicted labels:")
|
| for label in result["labels"]:
|
| print(label)
|
|
|
| print("\nTop-10 scores:")
|
| top_scores = sorted(result["scores"].items(), key=lambda x: x[1], reverse=True)[:10]
|
| for label, score in top_scores:
|
| print(f"{label}: {score:.4f}") |
