有没有办法在TensorFlow会话中调用Numpy函数?

时间:2019-07-27 23:41:30

标签: python tensorflow tensorflow-probability

我正在尝试使用TensorFlow和TensorFlow概率实现期望最大化算法。直到我尝试实现“丢失数据”(数据可以在某些随机维度上包含NaN值)之前,它的效果都很好。

问题在于,由于缺少数据,我无法再将所有操作作为矢量操作进行操作,因此必须使用索引和for循环,如下所示:

    # Here we iterate through all the data samples
    for i in range(n):
        # x_i is the sample i
        x_i = tf.expand_dims(x[:, i], 1)
        gamma.append(estimate_gamma(x_i, pi, norm, ber))
        est_x_n_i = []
        est_xx_n_i = []
        est_x_b_i = []
        for j in range(k):
            mu_k = norm.mean()[j, :]
            sigma_k = norm.covariance()[j, :, :]
            rho_k = ber.mean()[j, :]
            est_x_n_i.append(estimate_x_norm(x_i[:d, :], mu_k, sigma_k))
            est_xx_n_i.append(estimate_xx_norm(x_i[:d, :], mu_k, sigma_k))
            est_x_b_i.append(estimate_x_ber(x_i[d:, :], rho_k))
        est_x_n.append(tf.convert_to_tensor(est_x_n_i))
        est_xx_n.append(tf.convert_to_tensor(est_xx_n_i))
        est_x_b.append(tf.convert_to_tensor(est_x_b_i))

我发现这些操作不是很有效。虽然第一个样本每个样本花费的时间少于1秒,但在50个样本之后,每个样本花费了3秒的时间。我想这是因为我在会话内部创建了不同的张量,这使内存或其他东西混乱了。

我使用TensorFlow还是一个新手,很多人只将TensorFlow用于深度学习和神经网络,所以我找不到解决方案。

然后,我尝试仅使用numpy数组和numpy操作来实现先前的for循环以及在该循环内调用的函数。但这返回了以下错误:

  

您必须使用以下格式输入占位符张量'Placeholder_4'的值   dtype double和shape [8,18]

发生此错误的原因是,当它尝试在循环内执行numpy函数时,尚未提供占位符。

pi_k, mu_k, sigma_k, rho_k, gamma_ik, exp_loglik = exp_max_iter(x, pi, dist_norm, dist_ber)
pi, mu, sigma, rho, responsability, NLL[i + 1] = sess.run([pi_k, mu_k, sigma_k, rho_k, gamma_ik, exp_loglik],{x: samples})

有什么办法解决这个问题?谢谢。

2 个答案:

答案 0 :(得分:0)

要回答您的标题问题“是否可以在TensorFlow会话中调用Numpy函数?”,我已经在一些示例代码下面放置了执行“ numpy函数”(sklearn.mixture.GaussianMixture)的位置通过直接调用函数或通过Tensorflow的py_function丢失数据。我感觉这可能不是您要寻找的100%。。。如果您只是尝试实现EM ..? Tensorflow中现有的高斯混合模型实现可能会有所帮助:

关于tf.contrib.factorization.gmm

文档: https://www.tensorflow.org/api_docs/python/tf/contrib/factorization/gmm

实现: https://github.com/tensorflow/tensorflow/blob/r1.14/tensorflow/contrib/factorization/python/ops/gmm_ops.py#L462-L506

在Tensorflow图中直接调用'numpy函数'的示例代码:

import numpy as np
np.set_printoptions(2)
import tensorflow as tf
from sklearn.mixture import GaussianMixture as GMM

def myfunc(x,istf=True):
    #strip nans
    if istf:
        mask = ~tf.is_nan(x)
        x = tf.boolean_mask(x,mask)
    else:
        ind=np.where(~np.isnan(x))
        x = x[ind]
    x = np.expand_dims(x,axis=-1)
    gmm = GMM(n_components=2)
    gmm.fit(x)
    m0,m1 = gmm.means_[:,0]    
    return np.array([m0,m1])
# create data with nans
np.random.seed(42)
x = np.random.rand(5,28,1)
c = 5
x.ravel()[np.random.choice(x.size, c, replace=False)] = np.nan

# directly call "numpy function"
for ind in range(x.shape[0]):
    val = myfunc(x[ind,:],istf=False)
    print(val)
    [0.7  0.26]
    [0.15 0.72]
    [0.77 0.2 ]
    [0.65 0.23]
    [0.35 0.87]
# initialization
sess = tf.InteractiveSession()
tf.global_variables_initializer().run()

# create graph
X = tf.placeholder(tf.float32, [28,1])
Y = tf.py_function(myfunc,[X],[tf.float32],name='myfunc')

# call "numpy function" in tensorflow graph
for ind in range(x.shape[0]):
    val = sess.run(Y, feed_dict={X: x[ind,:],})
    print(val)
    [array([0.29, 0.76], dtype=float32)]
    [array([0.72, 0.15], dtype=float32)]
    [array([0.77, 0.2 ], dtype=float32)]
    [array([0.23, 0.65], dtype=float32)]
    [array([0.35, 0.87], dtype=float32)]

答案 1 :(得分:0)

您可以将 numpy 函数转换为 tensorflow 函数,然后在会话内部调用一个简单的函数时可能不会产生问题。在 numpy 中创建一个 IOU 函数,然后通过 tf.numpy_functionhere

调用它
def IOU(Pred, GT, NumClasses, ClassNames):
    ClassIOU=np.zeros(NumClasses)#Vector that Contain IOU per class
    ClassWeight=np.zeros(NumClasses)#Vector that Contain Number of pixel per class Predicted U Ground true (Union for this class)
    for i in range(NumClasses): # Go over all classes
        Intersection=np.float32(np.sum((Pred==GT)*(GT==i)))# Calculate class intersection
        Union=np.sum(GT==i)+np.sum(Pred==i)-Intersection # Calculate class Union
        if Union>0:
            ClassIOU[i]=Intersection/Union# Calculate intesection over union
            ClassWeight[i]=Union
            
    # b/c we will only take the mean over classes that are actually present in the GT
    present_classes = np.unique(GT) 
    mean_IOU = np.mean(ClassIOU[present_classes])
    # append it in final results
    ClassNames = np.append(ClassNames, 'Mean')
    ClassIOU = np.append(ClassIOU, mean_IOU)
    ClassWeight = np.append(ClassWeight, np.sum(ClassWeight))
    
    return mean_IOU
# an now call as
NumClasses=6
ClassNames=['Background', 'Class_1', 'Class_1',
            'Class_1 ', 'Class_1', 'Class_1 ']
x = tf.numpy_function(Strict_IOU, [y_pred, y_true, NumClasses, ClassNames], 
                        tf.float64, name=None)