如何重塑张量并获得 Tensorflow 中的第一个维度？

Question

I have a tensor. Lets say its dimension is [2, 999]. How to reshape it to [999, 2] and obtain the first dimension, ie, 999 in Tensorflow?

Answer 1

Reshape:

new_tensor = tensor.reshape((999,2))

Find first dimension:

first_dimension = tensor.shape[0]

Answer 2

Hi here's how you can do it:

Btw tensor objects dont have a reshape function u have to call it as such with the tf.reshape function

import tensorflow as tf 
tensor = tf.range(999 * 2) # create a tensor
reshaped_tensor = tf.reshape(tensor, (2, 999))

# this doesn't work
tensor = tensor.reshape(999, 2)

U can switch axis with the transpose command since u have the same dimensions

switched_axis = tf.transpose(tensor) # assuming tensor has a shape of 999, 2

To print the first dimensions

print(tensor.shape[0])