在 skflow 中使用 batch_size in model_fn

Question

我需要在 model_fn() 中创建一个随机变量，其形状为 [batch_size, 20].

我不想将 batch_size 作为参数传递，因为这样我就无法使用不同的批量大小进行预测。

去掉与这个问题无关的部分，我的model_fn()是：

def model(inp, out):
    eps = tf.random_normal([batch_size, 20], 0, 1, name="eps"))) # batch_size is the 
    # value I do not want to hardcode

    # dummy example
    predictions = tf.add(inp, eps)
    return predictions, 1

如果我用 inp.get_shape() 替换 [batch_size, 20]，我得到

ValueError: Cannot convert a partially known TensorShape to a Tensor: (?, 20)

当运行 myclf.setup_training()。

如果我尝试

def model(inp, out):
    batch_size = tf.placeholder("float", [])
    eps = tf.random_normal([batch_size.eval(), 20], 0, 1, name="eps")))

    # dummy example
    predictions = tf.add(inp, eps)
    return predictions, 1

我用 sess.as_default()or pass an explicit session to eval(session=sess) 得到 ValueError: Cannot evaluate tensor using eval(): No default session is registered. Use（可以理解，因为我没有提供 feed_dict）

如何在 model_fn() 中访问 batch_size 的值，同时仍然能够在预测期间更改它？

Answer 1

我不知道 Tensor.get_shape() 和 tf.shape(Tensor) 之间的区别。后者有效：

eps = tf.random_normal(tf.shape(inp), 0, 1, name="eps")))

如 Tensorflow 0.8 常见问题解答中所述：

How do I build a graph that works with variable batch sizes?

It is often useful to build a graph that works with variable batch sizes, for example so that the same code can be used for (mini-)batch training, and single-instance inference. The resulting graph can be saved as a protocol buffer and imported into another program.

When building a variable-size graph, the most important thing to remember is not to encode the batch size as a Python constant, but instead to use a symbolic Tensor to represent it. The following tips may be useful:

Use batch_size = tf.shape(input)[0] to extract the batch dimension from a Tensor called input, and store it in a Tensor called batch_size.

Use tf.reduce_mean() instead of tf.reduce_sum(...) / batch_size.

If you use placeholders for feeding input, you can specify a variable batch dimension by creating the placeholder with tf.placeholder(..., shape=[None, ...]). The None element of the shape corresponds to a variable-sized dimension.

在 skflow 中使用 batch_size in model_fn

Use batch_size in model_fn in skflow

python

tensorflow

skflow