script.py

import os
import pickle
import cv2
import pandas as pd
import numpy as np
from utils.utils import extract_features_from_image


def run_inference(TEST_IMAGE_PATH, pipeline_model, SUBMISSION_CSV_SAVE_PATH):
    test_images = sorted(os.listdir(TEST_IMAGE_PATH))
    
    image_feature_list = []

    for test_image in test_images:
        path_to_image = os.path.join(TEST_IMAGE_PATH, test_image)
        image = cv2.imread(path_to_image)
        features = extract_features_from_image(image)
        image_feature_list.append(features)

    features_multiclass = np.array(image_feature_list)

    multiclass_predictions = pipeline_model.predict(features_multiclass)

    df_predictions = pd.DataFrame({
        "file_name": test_images,
        "category_id": multiclass_predictions
    })

    df_predictions.to_csv(SUBMISSION_CSV_SAVE_PATH, index=False)
    
    


if __name__ == "__main__":

    current_directory = os.path.dirname(os.path.abspath(__file__))
    TEST_IMAGE_PATH = "/tmp/data/test_images"
    
    MODEL_NAME = "multiclass_model.pkl"
    MODEL_PATH = os.path.join(current_directory, MODEL_NAME)
    
    k = 100
    SUBMISSION_CSV_SAVE_PATH = os.path.join(current_directory, "submission.csv")

    # load the model
    with open(MODEL_PATH, 'rb') as file:
        svm_model = pickle.load(file)
        
    
    run_inference(TEST_IMAGE_PATH, svm_model, k, SUBMISSION_CSV_SAVE_PATH)