Text Classification
Transformers
Safetensors
English
proto
medical
prototypical-networks
Eval Results (legacy)
Instructions to use row56/ProtoPatient with libraries, inference providers, notebooks, and local apps. Follow these links to get started.
- Libraries
- Transformers
How to use row56/ProtoPatient with Transformers:
# Use a pipeline as a high-level helper from transformers import pipeline pipe = pipeline("text-classification", model="row56/ProtoPatient")# pip install -U transformers accelerate # Load model directly from transformers import ProtoForMultiLabelClassification model = ProtoForMultiLabelClassification.from_pretrained("row56/ProtoPatient", device_map="auto") - Notebooks
- Google Colab
- Kaggle
Upload README.md with huggingface_hub
Browse files
README.md
ADDED
|
@@ -0,0 +1,69 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
---
|
| 2 |
+
tags:
|
| 3 |
+
- text-classification
|
| 4 |
+
- medical
|
| 5 |
+
- prototypical-networks
|
| 6 |
+
- transformers
|
| 7 |
+
library_name: transformers
|
| 8 |
+
language: en
|
| 9 |
+
license: mit
|
| 10 |
+
datasets:
|
| 11 |
+
- your_dataset_name_here
|
| 12 |
+
model-index:
|
| 13 |
+
- name: ProtoPatient
|
| 14 |
+
results:
|
| 15 |
+
- task:
|
| 16 |
+
type: multi-label-classification
|
| 17 |
+
dataset:
|
| 18 |
+
name: your_dataset_name_here
|
| 19 |
+
type: text
|
| 20 |
+
metrics:
|
| 21 |
+
- name: Accuracy
|
| 22 |
+
type: accuracy
|
| 23 |
+
value: 0.XX # Update with real value
|
| 24 |
+
- name: F1-score
|
| 25 |
+
type: f1
|
| 26 |
+
value: 0.XX # Update with real value
|
| 27 |
+
---
|
| 28 |
+
|
| 29 |
+
|
| 30 |
+
|
| 31 |
+
# ProtoPatient Model for Multi-Label Classification
|
| 32 |
+
|
| 33 |
+
This repository contains the implementation of the ProtoPatient model, designed for multi-label classification tasks. It is based on a transformer model and integrates a prototype-based learning approach.
|
| 34 |
+
|
| 35 |
+
ProtoPatient is a novel method using prototypical networks and label-wise attention for diagnosis prediction from clinical text, ensuring both accuracy and interpretability by making predictions based on text segments similar to prototypical patients. Evaluated on two clinical datasets, it outperforms existing baselines and provides explanations that are understandable and valuable for doctors.
|
| 36 |
+
|
| 37 |
+
## **Repository Structure**
|
| 38 |
+
```
|
| 39 |
+
ProtoPatient/
|
| 40 |
+
│── proto_model/
|
| 41 |
+
│ ├── proto.py
|
| 42 |
+
│ ├── utils.py
|
| 43 |
+
│ ├── metrics.py
|
| 44 |
+
│ ├── __init__.py
|
| 45 |
+
│── config.json
|
| 46 |
+
│── model.safetensors
|
| 47 |
+
│── tokenizer.json
|
| 48 |
+
│── tokenizer_config.json
|
| 49 |
+
│── vocab.txt
|
| 50 |
+
│── README.md
|
| 51 |
+
│── .gitattributes
|
| 52 |
+
```
|
| 53 |
+
|
| 54 |
+
## **How to Use the Model**
|
| 55 |
+
|
| 56 |
+
### **1. Install Dependencies**
|
| 57 |
+
Ensure you have `transformers` and `torch` installed:
|
| 58 |
+
```bash
|
| 59 |
+
pip install transformers torch
|
| 60 |
+
```
|
| 61 |
+
|
| 62 |
+
### **2. Load the Model**
|
| 63 |
+
You can load the model as follows:
|
| 64 |
+
```python
|
| 65 |
+
from transformers import AutoModel
|
| 66 |
+
|
| 67 |
+
model = AutoModel.from_pretrained("row56/ProtoPatient")
|
| 68 |
+
print("✅ Model with weights loaded successfully!")
|
| 69 |
+
```
|