Metadata-Version: 2.4
Name: transformers_knn_adapter
Version: 0.2.0
Summary: Hugging Face Transformers image embedding adapter with a scikit-learn KNN classification head.
Author: transformers-knn-adapter contributors
License: MIT
License-File: LICENSE
Requires-Python: >=3.10
Requires-Dist: datasets
Requires-Dist: joblib
Requires-Dist: numpy
Requires-Dist: pillow
Requires-Dist: scikit-learn
Requires-Dist: torch
Requires-Dist: tqdm
Requires-Dist: transformers
Description-Content-Type: text/markdown

# transformers-knn-adapter

`transformers_knn_adapter` extends Hugging Face image models by attaching a scikit-learn KNN classifier on top of transformer embeddings.

## Requirements

- Python 3.11+
- `uv`

## Setup

```bash
uv sync --dev
```

## Run Tests

```bash
uv run pytest
```

## Train

```bash
uv run python -m transformers_knn_adapter.knn_image_pipeline train \
  --model microsoft/resnet-50 \
  --knn-model-path /tmp/knn/dinov2_small_mini_imagenet_full.joblib \
  --dataset timm/mini-imagenet \
  --split train \
  --max-samples 1000 \
  --shuffle \
  --grid-search \
  --grid-search-splits 3 \
  --grid-search-repeats 2 \
  --grid-search-scoring f1_macro
```

## Evaluate

```bash
uv run python -m transformers_knn_adapter.knn_image_pipeline eval \
  --model microsoft/resnet-50 \
  --knn-model-path /tmp/knn/dinov2_small_mini_imagenet_full.joblib \
  --dataset timm/mini-imagenet \
  --split test \
  --stratified \
  --max-samples 100 \
  --shuffle \
  --batch-size 100
```

## Inference

```bash
uv run python -m transformers_knn_adapter.knn_image_pipeline infer \
  --model microsoft/resnet-50 \
  --knn-model-path /tmp/knn/dinov2_small_mini_imagenet_full.joblib \
  --image https://picsum.photos/200 \
  --inference-batch-size 5
```

## Python API

```python
from transformers_knn_adapter.knn_image_pipeline import pipeline

clf = pipeline(
    "image-classification",
    model_path="microsoft/resnet-50",
    knn_model_path="/tmp/knn/model.joblib",
)
```

## Notes

Real train/eval runs can download model and dataset artifacts from Hugging Face.
