Question

所以我有一个形状h_in的张量(50, ?, 1, 100)我现在想通过在轴(50, 1, 1, 100)上取最大值来变成1形状。

我该怎么做？

我试过

h_out = max_pool(h_in)

与

def max_pool(h,ksize=[1,-1,1,1],strides=[1,1,1,1],padding='VALID'):
    return tf.nn.max_pool(h,ksize=ksize,strides=strides,padding=padding)

但这似乎并没有减小尺寸。

可运行的例子：

import tensorflow as tf
import numpy as np
import numpy.random as nprand

def _weight_variable(shape,name):
    initial = tf.truncated_normal(shape,stddev=0.1)
    v = tf.Variable(initial,name=name)
    return v

def _bias_variable(shape,name):
    initial = tf.constant(0.1,shape=shape)
    v = tf.Variable(initial,name=name)
    return v

def _embedding_variable(shape,name):
    initial = tf.truncated_normal(shape)
    v = tf.Variable(initial,name=name)
    return v

def conv2d(x,W,strides=[1,1,1,1],padding='VALID'):
    return tf.nn.conv2d(x,W,strides=strides,padding=padding)

def max_pool(h,ksize=[1,-1,1,1],strides=[1,1,1,1],padding='VALID'):
    return tf.nn.max_pool(h,ksize=ksize,strides=strides,padding=padding)

nof_embeddings= 55000
dim_embeddings = 300

batch_size = 50
filter_size = 100
x_input = tf.placeholder(tf.int32, shape=[batch_size, None])

def _model():

    embeddings = _embedding_variable([nof_embeddings,dim_embeddings],'embeddings')

    h_lookup = tf.nn.embedding_lookup(embeddings,x_input)
    h_embed = tf.reshape(h_lookup,[batch_size,-1,dim_embeddings,1])

    f = 3

    W_conv1f = _weight_variable([f,dim_embeddings,1,filter_size],f'W_conv1_{f}')
    b_conv1f = _bias_variable([filter_size],f'b_conv1_{f}')
    h_conv1f = tf.nn.relu(conv2d(h_embed,W_conv1f) + b_conv1f)

    h_pool1f = max_pool(h_conv1f)

    print("h_embed:",h_embed.get_shape())
    print()
    print(f'h_conv1_{f}:',h_conv1f.get_shape())
    print(f'h_pool1_{f}:',h_pool1f.get_shape())
    print()

    return tf.shape(h_pool1f)

if __name__ == '__main__':

    tensor_length = 35

    model = _model()
    with tf.Session() as sess:
        tf.global_variables_initializer().run()
        batch = nprand.randint(0,nof_embeddings,size=[batch_size,tensor_length])
        shape = sess.run(model,
                         feed_dict ={
                                 x_input : batch
                                 })
        print('result:',shape)

输出

h_embed: (50, ?, 300, 1)

h_conv1_3: (50, ?, 1, 100)
h_pool1_3: (50, ?, 1, 100)

result: [ 50  35   1 100]

让我说我改为硬编码我想要的尺寸：

h_pool1f = max_pool(h_conv1f,ksize=[1,35-f+1,1,1])

有效。但是，一旦我更改tensor_length（这是在运行时确定的，所以不，我不能对其进行硬编码），我现在遇到了麻烦。

一个＆＃34;解决方案＆＃34;可能是通过填充或其他东西将输入吹到固定的最大长度，但是再次，这会引入不必要的计算和人工上限，我应该非常希望避免这两种情况。

那么，有吗

一种正确制造张量流的方法＆＃34;识别-1中的k_size？
或其他计算最大值的方法？

Answer 1

我认为tf.reduce_max正是您所寻找的： https://www.tensorflow.org/api_docs/python/tf/reduce_max

用法：

tens = some tensorflow.Tensor
ax = some positive integer, or -1 or None
red_m = tf.reduce_max(tens, axis=ax)

如果数字为[shape_0, shape_1, shape_2]，则结果张量red_m的形状[shape_1, shape_2]如果ax=0，形状[shape_0, shape_2] ax=1，等等。如果ax=-1，则推断出最后的轴，而如果ax=None，则减少将沿所有轴发生。

张量流 - 从张量得到最大值

1 个答案: