Question

我对tensorflow和python还是很陌生，我正在研究一种能够对Urban Sound数据集（https://urbansounddataset.weebly.com/urbansound8k.html）的声音进行分类的神经网络。

我使用了机器学习教程（https://colab.research.google.com/notebooks/mlcc/multi-class_classification_of_handwritten_digits.ipynb?utm_source=mlcc&utm_campaign=colab-external&utm_medium=referral&utm_content=multiclass-colab&hl=en）中的速成课程作为我的程序的基础，该模型相当不错，但是现在我想分析不同音频文件的预测。

首先，我在文件中创建分类器，然后（下面的代码）调用模型并计算对遗留的测试数据集的检查

import pandas as pd
import numpy as np
import time
import matplotlib.pyplot as plt
import seaborn as sns
import tensorflow as tf
from tensorflow.python.data import Dataset
from sklearn import metrics 

urbansound_dataframe = pd.read_csv("C:\\Users\\UrbanSound8K\\metadata\\dataset_train_fin.csv", sep=',')

urbansound_dataframe_test = pd.read_csv("C:\\Users\\UrbanSound8K\\metadata\\dataset_test_fin.csv", sep=',')


def construct_feature_columns(input_features):
    return set([tf.feature_column.numeric_column(my_feature)
                for my_feature in input_features])

def parse_labels_and_features(dataset):
    """Args:
      dataset: A Pandas `Dataframe`, containing the label on the last column
    Returns:
      A `tuple` `(labels, features)`:
        labels: A Pandas `Series`.
        features: A Pandas `DataFrame`.
    """
    labels = dataset['classID']
    features = dataset[[                               ###metto i nomi delle features che voglio utilizzare
        "mfcc_1", "mfcc_2", "mfcc_3", "mfcc_4", "mfcc_5", "mfcc_6", "mfcc_7", "mfcc_8", "mfcc_9", "mfcc_10", "mfcc_11",
        "mfcc_12", "mfcc_13", "mfcc_14", "mfcc_15", "mfcc_16", "mfcc_17", "mfcc_18", "mfcc_19", "mfcc_20", "mfcc_21",
        "mfcc_22", "mfcc_23", "mfcc_24", "mfcc_25", "mfcc_26", "mfcc_27", "mfcc_28", "mfcc_29", "mfcc_30", "mfcc_31",
        "mfcc_32", "mfcc_33", "mfcc_34", "mfcc_35", "mfcc_36", "mfcc_37", "mfcc_38", "mfcc_39", "mfcc_40"
    ]]    
    return labels, features

def create_predict_input_fn(features, labels, batch_size):
    """Args:
      features: The features to base predictions on.
      labels: The labels of the prediction examples.

    Returns:
      A function that returns features and labels for predictions.
    """

    def _input_fn():
        raw_features = {key: np.array(value) for key, value in dict(features).items()}
        raw_targets = np.array(labels)

        ds = Dataset.from_tensor_slices((raw_features, raw_targets))  
        ds = ds.batch(batch_size)

        # Return the next batch of data.
        feature_batch, label_batch = ds.make_one_shot_iterator().get_next()
        return feature_batch, label_batch

    return _input_fn


percentage = 75   
training_targets, training_examples = parse_labels_and_features(urbansound_dataframe.head(int(((len(urbansound_dataframe)*percentage)/100))))

validation_targets, validation_examples = parse_labels_and_features(urbansound_dataframe.tail(len(urbansound_dataframe)-int(((len(urbansound_dataframe)*percentage)/100))))



learning_rate=0.004

my_optimizer = tf.train.AdagradOptimizer(learning_rate=learning_rate)
my_optimizer = tf.contrib.estimator.clip_gradients_by_norm(my_optimizer, 5.0)

hidden_units=[2000,2000,2000]



my_classifier = tf.estimator.DNNClassifier(feature_columns=construct_feature_columns(training_examples),
                                            n_classes=11,
                                            hidden_units=hidden_units,
                                            optimizer=my_optimizer,
                                            config=tf.contrib.learn.RunConfig(keep_checkpoint_max=1),
                                            model_dir="C:\\Users\\PycharmProjects\\MODEL_UrbanSound_05_NN")




###test on unused directories
test_targets, test_examples = parse_labels_and_features(urbansound_dataframe_test)

predict_test_input_fn = create_predict_input_fn(test_examples, test_targets, batch_size=400)

test_predictions = my_classifier.predict(input_fn=predict_test_input_fn)
test_predictions = np.array([item['class_ids'][0] for item in test_predictions])

accuracy = metrics.accuracy_score(test_targets, test_predictions)

print("Accuracy on test data: ", (accuracy*100),"%")
print("fine test")

# Output a plot of the confusion matrix.
cm = metrics.confusion_matrix(test_targets, test_predictions)
# Normalize the confusion matrix by row (i.e by the number of samples
# in each class).
cm_normalized = cm.astype("float") / cm.sum(axis=1)[:, np.newaxis]
ax = sns.heatmap(cm_normalized, cmap="bone_r")
ax.set_aspect(1)
plt.title("Confusion matrix on test data")
plt.ylabel("True label")
plt.xlabel("Predicted label")
plt.show()

我在这里的主要问题是如何将代码转换为单个文件，以使文件的特征由程序的另一部分提取。我认为_我需要在input_fn上工作

 def _input_fn():
    raw_features = {key: np.array(value) for key, value in dict(features).items()}
    raw_targets = np.array(labels)

    ds = Dataset.from_tensor_slices((raw_features, raw_targets)) 
    ds = ds.batch(batch_size)

    # Return the next batch of data.
    feature_batch, label_batch = ds.make_one_shot_iterator().get_next()
    return feature_batch, label_batch

return _input_fn

但是我不知道如何更改它。欢迎任何帮助，谢谢。

神经网络的单个预测（张量流，渴望执行）

0 个答案: