6.2.3. PyTorch¶

https://pytorch.org/tutorials/index.html

Learning PyTorch¶

PyTorch is a Python-based scientific computing package serving two broad purposes:

A replacement for NumPy to use the power of GPUs and other accelerators.
An automatic differentiation library that is useful to implement neural networks.

Tensors¶

张量是一种特殊的数据结构，与数组和矩阵非常相似。在 PyTorch 中，我们使用张量来编码模型的输入和输出，以及模型的参数。
张量类似于 NumPy 的 ndarray，但它们可以在 GPU 或其他专用硬件上运行以加速计算。

Tensor Initialization¶

# Directly from data
data = [[1, 2], [3, 4]]
x_data = torch.tensor(data)

# From a NumPy array
np_array = np.array(data)
x_np = torch.from_numpy(np_array)

# From another tensor
x_ones = torch.ones_like(x_data) # retains the properties of x_data
print(f"Ones Tensor: \n {x_ones} \n")

x_rand = torch.rand_like(x_data, dtype=torch.float) # overrides the datatype of x_data
print(f"Random Tensor: \n {x_rand} \n")

# With random or constant values:
shape = (2, 3,)
rand_tensor = torch.rand(shape)
ones_tensor = torch.ones(shape)
zeros_tensor = torch.zeros(shape)

print(f"Random Tensor: \n {rand_tensor} \n")
print(f"Ones Tensor: \n {ones_tensor} \n")
print(f"Zeros Tensor: \n {zeros_tensor}")

Tensor Attributes¶

tensor = torch.rand(3, 4)

print(f"Shape of tensor: {tensor.shape}")
print(f"Datatype of tensor: {tensor.dtype}")
print(f"Device tensor is stored on: {tensor.device}")

Tensor Operations¶

超过 100 种张量操作，包括转置、索引、切片、数学运算、线性代数、随机采样等

# We move our tensor to the GPU if available
if torch.cuda.is_available():
  tensor = tensor.to('cuda')
  print(f"Device tensor is stored on: {tensor.device}")

备注

其他函数参见 demo-python 项目