优化tf.map_fn的GPU使用率

时间:2019-02-21 13:43:37

标签: python performance tensorflow machine-learning deep-learning

我正在Tensorflow中构建一个可处理3D数据的神经网络,并应该预测输入数据中界标的位置。该策略是(针对每个体素)密集地预测球体中实际地标周围半径为 r 的类别,并预测指向地标实际位置的偏移矢量。该策略proven有效地改善了地标预测。
每对类别概率和偏移向量都是一个投票,我现在正试图在tensorflow中有效地汇总那些投票。
对于(70,70,70)的输入形状和3个不同的地标以及背景类,我从网络中得到了两个输出:

  • 形状的概率张量(70,70,70,3 + 1)
  • 偏移形状为(70,70,70,3 * 3)的向量张量

我想生成3个形状为(70,70,70)的输出热图。现在,对于热图中的每个体素,我需要汇总指向体素的偏移矢量的概率。
我试图只使用python并有3个for循环,这在我的CPU上需要7秒。这是可以接受的,但是最终输入形状将更像300x300x300,而3个for循环将为O(N ^ 3),因此不可行。
所以我尝试使用张量流和GPU加速来预过滤所有不相关的数据。不相关的偏移矢量例如是所有这些,它们在特定阈值下具有相应的类别概率,或者超出了输入形状的范围。我是这样用 tf.map_fn 实现的:

def filter_votes(probs, dists, prob_threshold, num_landmarks, sample_shape: tf.Tensor):
    f_sample_shape = tf.cast(sample_shape, tf.float32)
    probs = probs[:,:,:,1:] # probability of background is irrelevant
    indices = tf.where(tf.greater_equal(probs, prob_threshold)) # take only the indices of voxels, that have a category prediction over a certain threshold

    def get_flatvect(idx):
        f_idx    = tf.cast(idx, tf.float32)
        return tf.stack([
            f_idx[3], # this is the landmark number (goes from 0 to  2)
            probs[idx[0], idx[1], idx[2], idx[3]], # this is the predicted probability for the voxel to be the landmark
            f_idx[0] + dists[idx[0], idx[1], idx[2], idx[3]], # this is the x offset+ the actual x-position of the voxel
            f_idx[1] + dists[idx[0], idx[1], idx[2], idx[3]+3], # this is the y offset+ the actual y-position of the voxel
            f_idx[2] + dists[idx[0], idx[1], idx[2], idx[3]+6] # this is the z offset+ the actual z-position of the voxel
        ])
    res = tf.map_fn(get_flatvect, indices, dtype=tf.float32, parallel_iterations=6)

    def get_mask(idx):
        dist = idx[2:]
        return tf.reduce_all(tf.logical_and(tf.greater_equal(dist, 0.), tf.less(dist, f_sample_shape)))
    mask = tf.map_fn(get_mask, res, dtype=tf.bool, parallel_iterations=6) # get a mask that filters offsets that went out of bounds of the actual tensor shape
    res = tf.boolean_mask(res, mask)
    return res # I return a 2D-Tensor that contains along the 2nd axis [num_landmark, probability_value, x_pos, y_pos, z_pos]

然后,我将过滤后的结果汇总到纯python中,由于输入数据根本较少(大多数体素具有较低的预测分类概率),因此速度要快得多。
即使输入形状为(70,70,70),问题仍然存在,在GPU使用率较低的情况下,筛选操作仅需花费近一分钟的时间。即使我有6个并行迭代,它也比仅聚合python中的所有内容慢了将近10倍。我尝试研究 map_fn ,我读到tf可能无法将所有操作都放在GPU上。但是即使那样,我还是认为它应该更快,因为:

  • 我有6个并行迭代和6个CPU内核
  • 我在一开始就使用 tf.where 对相关数据进行了预过滤,并且仅对结果索引进行遍历,而不对所有索引进行遍历

因此,似乎我对正在发生的事情缺乏基本的了解。也许有人可以弄清楚为什么我的代码如此低效?
也许有人有更好的主意,如何以矢量化方式汇总我的选票?

1 个答案:

答案 0 :(得分:0)

您可以像这样向量化您的函数:

import tensorflow as tf

def filter_votes_vec(probs, dists, prob_threshold, num_landmarks, sample_shape: tf.Tensor):
    probs = probs[:, :, :, 1:]
    indices = tf.where(probs >= prob_threshold)
    landmark = tf.to_float(indices[:, 3])
    p = tf.gather_nd(probs, indices)
    indices_dists = tf.stack([
        indices,
        tf.concat([indices[..., :-1], indices[..., -1:] + 3], axis=-1),
        tf.concat([indices[..., :-1], indices[..., -1:] + 6], axis=-1)
    ], axis=1)
    d = tf.gather_nd(dists, indices_dists) + tf.to_float(indices[:, :3])
    res = tf.concat([tf.expand_dims(landmark, 1), tf.expand_dims(p, 1), d], axis=1)
    mask = tf.reduce_all((d >= 0) & (d < tf.cast(sample_shape, tf.float32)), axis=1)
    res =  tf.boolean_mask(res, mask)
    return res

使用IPython进行快速测试和基准测试

import tensorflow as tf
import numpy as np

with tf.Graph().as_default(), tf.Session() as sess:
    np.random.seed(100)
    probs = np.random.rand(70, 70, 70, 3 + 1).astype(np.float32)
    probs /= probs.sum(-1, keepdims=True)
    probs = tf.convert_to_tensor(probs, tf.float32)
    dists = tf.convert_to_tensor(100 * np.random.rand(70, 70, 70, 3 * 3), tf.float32)
    prob_threshold = tf.convert_to_tensor(0.5, tf.float32)
    num_landmarks = tf.convert_to_tensor(3, tf.int32)  # This is not actually used in the code
    sample_shape = tf.convert_to_tensor([50, 60, 70], tf.int32)

    result = filter_votes(probs, dists, prob_threshold, num_landmarks, sample_shape)
    result_vec = filter_votes_vec(probs, dists, prob_threshold, num_landmarks, sample_shape)
    value, value_vec = sess.run([result, result_vec])
    print(np.allclose(value, value_vec))
    # True
    %timeit sess.run(result)
    # CPU
    # 2.55 s ± 21.7 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
    # GPU
    # 54 s ± 596 ms per loop (mean ± std. dev. of 7 runs, 1 loop each)
    %timeit sess.run(result_vec)
    # CPU
    # 63.2 µs ± 781 ns per loop (mean ± std. dev. of 7 runs, 10000 loops each)
    # GPU
    # 216 µs ± 2.29 µs per loop (mean ± std. dev. of 7 runs, 1000 loops each)

大概,GPU的荒谬时间是由于TensorFlow不断在CPU和GPU之间交换数据,这是相当昂贵的。