输出MLP预测评分

Question

按照keras教程，MLP分类在这里：分类/分类。

我能够成功地训练一个模型，并使用下面的代码打印出3种预测标签。我也想打印预测分数。在文档中，我似乎找不到如何做到这一点。

# Create a model for inference.
model_for_inference = keras.Sequential([text_vectorizer, shallow_mlp_model])

# Create a small dataset just for demoing inference.
inference_dataset = make_dataset(test_df.sample(100), is_train=False)
text_batch, label_batch = next(iter(inference_dataset))
predicted_probabilities = model_for_inference.predict(text_batch)

# Perform inference.
for i, text in enumerate(text_batch[:5]):
    label = label_batch[i].numpy()[None, ...]
    print(f"Abstract: {text}")
    predicted_proba = [proba for proba in predicted_probabilities[i]]
    top_3_labels = [
        x
        for _, x in sorted(
            zip(predicted_probabilities[i], lookup.get_vocabulary()),
            key=lambda pair: pair[0],
            reverse=True,
        )
    ][:3]
    print(f"Predicted Label(s): ({', '.join([label for label in top_3_labels])})")
    print(" ")

Answer 1

若要获取概率，请更改此部分：

top_3_labels = [
        x
        for _, x in sorted(
            zip(predicted_probabilities[i], lookup.get_vocabulary()),
            key=lambda pair: pair[0],
            reverse=True,
        )
    ][:3]
    print(f"Predicted Label(s): ({', '.join([label for label in top_3_labels])})")
    print(" ")

对此：

top_3_labels = [
        (p, x)
        for p, x in sorted(
            zip(predicted_probabilities[i], lookup.get_vocabulary()),
            key=lambda pair: pair[0],
            reverse=True,
        )
    ][:3]
    print(f"Predicted Label(s): ({', '.join([l[1] for l in top_3_labels])})")
    print(f"Predicted Probabilities(s): ({', '.join([l[0] for l in top_3_labels])})")
    print(" ")

Answer 2

您可以预测最有可能的标签(将[:3]更改为[0])，并使用一些学习函数来获得标准的准确性。

此外，您还可以获取标签的所有概率，并使用滑雪板的顶K精度