Question

在使用TFLearn创建卷积神经网络时，如何解决混淆矩阵时遇到问题。我到目前为止的代码如下：

 from __future__ import division, print_function, absolute_import

    import tflearn
    from tflearn.layers.core import input_data, dropout, fully_connected
    from tflearn.layers.conv import conv_2d, max_pool_2d
    from tflearn.layers.normalization import local_response_normalization
    from tflearn.layers.estimator import regression

    from sklearn.metrics import confusion_matrix
    import h5py

    hdf5Test = h5py.File('/path', 'r')

    X = hdf5Test['X']
    Y = hdf5Test['Y']

    # Building convolutional network
    network = input_data(shape=[None, 240, 320, 3], name='input')
    network = conv_2d(network, 32, 3, activation='relu', regularizer="L2")
    network = max_pool_2d(network, 2)
    network = local_response_normalization(network)
    network = conv_2d(network, 64, 3, activation='relu', regularizer="L2")
    network = max_pool_2d(network, 2)
    network = local_response_normalization(network)
    network = fully_connected(network, 128, activation='tanh')
    network = dropout(network, 0.8)
    network = fully_connected(network, 256, activation='tanh')
    network = dropout(network, 0.8)
    network = fully_connected(network, 2, activation='softmax')
    network = regression(
      network,
      optimizer='sgd',
      learning_rate=0.01,
      loss='categorical_crossentropy',
      name='target'
    )

    # Training
    model = tflearn.DNN(network, tensorboard_verbose=0)
    model.load('/path.tflearn')

    predictions = model.predict(X)
    print(confusion_matrix(Y, predictions))

每次我尝试运行此代码时，都会收到以下错误消息：

在抛出＆＃39; std :: bad_alloc＆＃39;的实例后终止调用 what（）：std :: bad_alloc 中止（核心倾销）

对TFLearn来说，任何建议都会很棒。

Answer 1

最后，它发现这是由于我试图预测的数据大小。我通过在循环中插入它来解决这个问题：

# Predict Classes
predictions = []
count = 0
length = len(X)
for line in X:
  print('Line ' + str(count) + ' of ' + str(length))
  tmp = model.predict_label([line])
  predictions.append(tmp[0])
  count += 1

通过一些格式化，我可以使用Sklearn生成混淆矩阵：

predictedClasses = np.argmin(predictions, axis=1)
actualClasses = np.argmax(Y, axis=1)
print(confusion_matrix(actualClasses, predictedClasses))

这种方法对我有用，可能对你有用......我认为TFLearn应该考虑采用简化的方法来制作混淆矩阵，以便其他人不会遇到同样的问题。

TfLearn混淆矩阵训练在std :: bad_alloc上终止

1 个答案: