我試圖在張量流中實(shí)現(xiàn)倒角距離.

但是,我的代碼將輸入視為numpy數(shù)組.要將numpy轉(zhuǎn)換為張量,我們需要運(yùn)行一個(gè)會(huì)話,但該過程已經(jīng)在另一個(gè)會(huì)話中.我認(rèn)為兩個(gè)會(huì)話不能并行運(yùn)行.

那么,任何人都可以幫我在tensorflow中實(shí)現(xiàn)倒角距離或幫助我解決這兩個(gè)同步會(huì)話的問題嗎？

我的代碼是：

def chamfer_distance(array1,array2):
    # final = 0
    # final = tf.cast(final,tf.float32)
    batch_size = array1.get_shape()[0].value
    num_point = array1.get_shape()[1].value
    sess = tf.Session()
    arr1,arr2 = sess.run([array1,array2])
    del sess
    dist = 0
    for i in range(batch_size):
        tree1 = KDTree(arr1[i], leafsize=num_point 1)
        tree2 = KDTree(arr2[i], leafsize=num_point 1)
        distances1, _ = tree1.query(arr2[i])
        distances2, _ = tree2.query(arr1[i])
        distances1 = tf.convert_to_tensor(distances1)
        distances2 = tf.convert_to_tensor(distances2)
        av_dist1 = tf.reduce_mean(distances1)
        av_dist2 = tf.reduce_mean(distances2)
        dist = dist   (av_dist1 av_dist2)/batch_size
    return dist

解決方法:

我已經(jīng)實(shí)現(xiàn)了TF版倒角距離：

def distance_matrix(array1, array2):
    """
    arguments: 
        array1: the array, size: (num_point, num_feature)
        array2: the samples, size: (num_point, num_feature)
    returns:
        distances: each entry is the distance from a sample to array1
            , it's size: (num_point, num_point)
    """
    num_point, num_features = array1.shape
    expanded_array1 = tf.tile(array1, (num_point, 1))
    expanded_array2 = tf.reshape(
            tf.tile(tf.expand_dims(array2, 1), 
                    (1, num_point, 1)),
            (-1, num_features))
    distances = tf.norm(expanded_array1-expanded_array2, axis=1)
    distances = tf.reshape(distances, (num_point, num_point))
    return distances

def av_dist(array1, array2):
    """
    arguments:
        array1, array2: both size: (num_points, num_feature)
    returns:
        distances: size: (1,)
    """
    distances = distance_matrix(array1, array2)
    distances = tf.reduce_min(distances, axis=1)
    distances = tf.reduce_mean(distances)
    return distances

def av_dist_sum(arrays):
    """
    arguments:
        arrays: array1, array2
    returns:
        sum of av_dist(array1, array2) and av_dist(array2, array1)
    """
    array1, array2 = arrays
    av_dist1 = av_dist(array1, array2)
    av_dist2 = av_dist(array2, array1)
    return av_dist1 av_dist2

def chamfer_distance_tf(array1, array2):
    batch_size, num_point, num_features = array1.shape
    dist = tf.reduce_mean(
               tf.map_fn(av_dist_sum, elems=(array1, array2), dtype=tf.float64)
           )
    return dist

為了驗(yàn)證目的,我還實(shí)現(xiàn)了一個(gè)sklearn版本：

def chamfer_distance_sklearn(array1,array2):
    batch_size, num_point = array1.shape[:2]
    dist = 0
    for i in range(batch_size):
        tree1 = KDTree(array1[i], leaf_size=num_point 1)
        tree2 = KDTree(array2[i], leaf_size=num_point 1)
        distances1, _ = tree1.query(array2[i])
        distances2, _ = tree2.query(array1[i])
        av_dist1 = np.mean(distances1)
        av_dist2 = np.mean(distances2)
        dist = dist   (av_dist1 av_dist2)/batch_size
    return dist

也是一個(gè)numpy版本：

def array2samples_distance(array1, array2):
    """
    arguments: 
        array1: the array, size: (num_point, num_feature)
        array2: the samples, size: (num_point, num_feature)
    returns:
        distances: each entry is the distance from a sample to array1 
    """
    num_point, num_features = array1.shape
    expanded_array1 = np.tile(array1, (num_point, 1))
    expanded_array2 = np.reshape(
            np.tile(np.expand_dims(array2, 1), 
                    (1, num_point, 1)),
            (-1, num_features))
    distances = LA.norm(expanded_array1-expanded_array2, axis=1)
    distances = np.reshape(distances, (num_point, num_point))
    distances = np.min(distances, axis=1)
    distances = np.mean(distances)
    return distances

def chamfer_distance_numpy(array1, array2):
    batch_size, num_point, num_features = array1.shape
    dist = 0
    for i in range(batch_size):
        av_dist1 = array2samples_distance(array1[i], array2[i])
        av_dist2 = array2samples_distance(array2[i], array1[i])
        dist = dist   (av_dist1 av_dist2)/batch_size
    return dist

您可以使用以下腳本驗(yàn)證結(jié)果：

batch_size = 8
num_point = 20
num_features = 4
np.random.seed(1)
array1 = np.random.randint(0, high=4, size=(batch_size, num_point, num_features))
array2 = np.random.randint(0, high=4, size=(batch_size, num_point, num_features))

print('sklearn: ', chamfer_distance_sklearn(array1, array2))
print('numpy: ', chamfer_distance_numpy(array1, array2))

array1_tf = tf.constant(array1, dtype=tf.float64)
array2_tf = tf.constant(array2, dtype=tf.float64)
dist_tf = chamfer_distance_tf(array1_tf, array2_tf)

with tf.Session() as sess:
    print('tf: ', sess.run(dist_tf))