Convertir le tableau Numpy en tenseur
import numpy as np
import torch
numpy_array = np.array([1,3,5])
tensor_array = torch.from_numpy(numpy_array)
CodeHunter
import numpy as np
import torch
numpy_array = np.array([1,3,5])
tensor_array = torch.from_numpy(numpy_array)#Tensor that don't requires grad.
tensor.numpy()
#Tensor that requires grad.
tensor.detach().numpy()import torch
# Create PyTorch tensor
A_torch = torch.tensor([1, 2])
# Convert tensor to NumPy array
A_np = A_torch.numpy()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)