Answers for "convert tensors to numpy"

tf tensor from numpy

tf.convert_to_tensor(my_np_array, dtype=tf.float32)

convert numpy array to tensor

import numpy as np
import torch

numpy_array = np.array([1,3,5])
tensor_array = torch.from_numpy(numpy_array)

convert tensor to numpy array

import tensorflow as tf

a = tf.constant([[1, 2], [3, 4]])                 
b = tf.add(a, 1)

a.numpy()
# array([[1, 2],
#        [3, 4]], dtype=int32)

b.numpy()
# array([[2, 3],
#        [4, 5]], dtype=int32)

tf.multiply(a, b).numpy()
# array([[ 2,  6],
#        [12, 20]], dtype=int32)