CODEWITHSUNDEEP
tensorflow
MBZ
MBZ

Reputation: 27592

get the size of a variable batch dimension

assuming the input to the network is a placeholder with variable batch size, i.e.:

x = tf.placeholder(..., shape=[None, ...])

is it possible to get the shape of x after it has been fed? tf.shape(x)[0] still returns None.

Upvotes: 6

Views: 18945

Answers (2)

mrry
mrry

Reputation: 126154

If x has a variable batch size, the only way to get the actual shape is to use the tf.shape() operator. This operator returns a symbolic value in a tf.Tensor, so it can be used as the input to other TensorFlow operations, but to get a concrete Python value for the shape, you need to pass it to Session.run().

x = tf.placeholder(..., shape=[None, ...])
batch_size = tf.shape(x)[0]  # Returns a scalar `tf.Tensor`

print x.get_shape()[0]  # ==> "?"

# You can use `batch_size` as an argument to other operators.
some_other_tensor = ...
some_other_tensor_reshaped = tf.reshape(some_other_tensor, [batch_size, 32, 32])

# To get the value, however, you need to call `Session.run()`.
sess = tf.Session()
x_val = np.random.rand(37, 100, 100)
batch_size_val = sess.run(batch_size, {x: x_val})
print x_val  # ==> "37"

Upvotes: 21

user3192082
user3192082

Reputation: 346

You can get the shape of the tensor x using x.get_shape().as_list(). For getting the first dimension (batch size) you can use x.get_shape().as_list()[0].

Upvotes: 0

Related Questions