Running and Verification

Write an inference script to check whether the model can be used properly for inference.

Create and compile the test script dlrm_test.py.

Create dlrm_test.py.
```
vi dlrm_test.py
```

Press i to enter the insert mode and add the following content to the dlrm_test.py file:

import logging
import numpy as np
import tensorflow as tf
from tensorflow.data import Dataset
from noddlrm.recommenders import DLRM
def load_criteo(dataset_folder='dataset/'):
    
    with np.load(dataset_folder + 'criteo/kaggle_processed.npz') as data:
        X_int = data["X_int"]
        X_cat = data["X_cat"]
        y = data["y"]
        counts = data["counts"]
    
    indices = np.arange(len(y))
    indices = np.array_split(indices, 7)
    
    test_indices = indices[-1]
    val_indices, test_indices = np.array_split(test_indices, 2)
   
    raw_data = dict()
    raw_data['counts'] = counts
    
    raw_data['X_cat_test'] = X_cat[test_indices]
    raw_data['X_int_test'] = np.log(X_int[test_indices]+1).astype(np.float32)
    raw_data['y_test'] = y[test_indices]
    
    return raw_data
@tf.function
def eval_step(dense_features, sparse_features, label):
    pred = dlrm_model.inference(dense_features, sparse_features)
    auc.update_state(y_true=label, y_pred=pred)
if __name__ == "__main__":
    logging.basicConfig(level=logging.INFO, format='%(message)s')
    batch_size = 1024
    raw_data = load_criteo('../../dataset/')
    test_dataset = Dataset.from_tensor_slices({
                    'dense_features': raw_data['X_int_test'][:],
                    'sparse_features': raw_data['X_cat_test'][:],
                    'label': raw_data['y_test'][:]
    }).batch(batch_size).prefetch(1)
    dlrm_model = DLRM(
                    m_spa=4,
                    ln_emb=raw_data['counts'],
                    ln_bot=[8, 4],
                    ln_top=[128, 64, 1]
    )
    dlrm_model.load_weights('mymodel')
    auc = tf.keras.metrics.AUC()
    for _, batch_data in enumerate(test_dataset):
        eval_step(**batch_data)
    logging.info('auc: %s', auc.result().numpy())

Press Esc, type :wq, and press Enter to save the file and exit.

Run the test.
```
python dlrm_test.py
```
If the test program does not report an error and the AUC value is displayed, DLRM inference is normal. The AUC value is related to the effect of the model trained in Training the DLRM. If the trained AUC value is different from that provided in this document, the actual command line information does not need to be the same as that in the figure. However, if the same model is used for inference for multiple times, the inference results must remain the same.