pipeline.py

from typing import Dict, List, Any
from fastai.learner import load_learner
from PIL import Image
import os
import json
import numpy as np

print('PIPELINE')

class ImageClassificationPipeline:
    def __init__(self, path=""):
        # IMPLEMENT_THIS
        # Preload all the elements you are going to need at inference.
        # For instance your model, processors, tokenizer that might be needed.
        # This function is only called once, so do all the heavy processing I/O here"""
        print('init')
        self.model = load_learner(os.path.join(path, "model.pkl"))
        with open(os.path.join(path, "config.json")) as config:
            config = json.load(config)
        self.labels = config["labels"]

    def __call__(self, inputs: "Image.Image") -> List[Dict[str, Any]]:
        print('call')
        """
        Args:
            inputs (:obj:`PIL.Image`):
                The raw image representation as PIL.
                No transformation made whatsoever from the input. Make all necessary transformations here.
        Return:
            A :obj:`list`:. The list contains items that are dicts should be liked {"label": "XXX", "score": 0.82}
                It is preferred if the returned list is in decreasing `score` order
        """
        # IMPLEMENT_THIS
        # FastAI expects a np array, not a PIL Image.
        _, _, preds = self.model.predict(np.array(inputs))
        preds = preds.tolist()
        return [{"label": label, "score": preds[idx]} for idx, label in enumerate(self.labels)]