【Pytorch】学习记录分享1——Tensor张量初始化与基本操作,德州电锯杀人狂5

文件名：【Pytorch】学习记录分享1——Tensor张量初始化与基本操作,德州电锯杀人狂5 【Pytorch】学习记录分享1——Tensor张量初始化与基本操作 1. 基础资料汇总

资料汇总 pytroch中文版本教程 PyTorch入门教程 B站强推！2023公认最通俗易懂的【PyTorch】教程，200集付费课程（附代码）人工智能_机器 视频 1.PyTorch简介 2.PyTorch环境搭建 basic: python numpy pandas pytroch

theory: study mlp cnn transform rnn

model: AlexNet VGG ResNet Yolo SSD

2. Tensor张量初始化与基本操作（numpy对比） 2.1 tensor 创建的集中基本方式 import numpy as npimport torchnp_a = np.array([1,2,3]) #ndarraystensor_a = torch.tensor([1,2,3]) #tensor# tensor function and computertensor_b = torch.empty(5,3)tensor_c = torch.randn(5,3) #用于确定模型的输入维度，做数据头尾tensor_d = torch.zeros(5,3) #用于 x->y 训练的一个映射 神经网络y truth_label one_hot表示tensor_e = torch.zeros(5,3,dtype= torch.long) # dtype 数据格式print("np_a",np_a)print("tensor_a", tensor_a)print("tensor_b", tensor_b)print("tensor_c", tensor_c)print("tensor_d", tensor_d)print("tensor_e", tensor_e)

import torch#通过数据直接创建张量：data = [[1, 2, 3], [4, 5, 6]]tensor1 = torch.tensor(data)print("tensor1",tensor1)#使用特定形状的全零张量：import torchtensor2 = torch.zeros(2, 3)print("tensor2",tensor2)#使用特定形状的全一张量：import torchtensor3 = torch.ones(2, 3)print("tensor3",tensor3)#利用随机数创建张量：import torchtensor4 = torch.rand(2, 3)print("tensor4",tensor4)

2.2 修改tensor/numpy长度与维度 # 基于已经存在的 tensor进行操作x = torch.tensor([1,2,3]) x.new_ones(5,3) # 修改 x 的维度tensor_f = torch.randn_like(x,dtype=torch.float) # 修改x 的类型与维度print("tensor_f = ", tensor_f)# 维度查看 np shape | tensor size 层到另外一个层 矩阵相乘np.array([1, 2, 3]).shapetorch.tensor([1,2,3]).size()

# 更改维度 np reshape y.size()y.view(15)y.view(15,1)y.view(-1,5) # -1 表示自动计算，根据总维度/5得到

2.3 取 tensor/numpy 元素 y = np.array([[1,2,3],[4,5,6]])np.array([[1,2,3],[4,5,6]])[0]np.array([[1,2,3],[4,5,6]])[0,:] #":"表示不指定行，默认为该行所有np.array([[1,2,3],[4,5,6]])[:,0]print(y[:,0]) # 取第一列print(y[0,:]) # 取第一行y[3,0].item() # 常用 loss 反向传导 日志 打印查看 loss 是否减少 查看具体数值

2.4 numpy 对象的基本运算 import numpy as np# 加法result_array_add = np.array([1, 2]) + np.array([3, 4])# 减法result_array_sub = np.array([1, 2]) - np.array([3, 4])# 乘法result_array_mul = np.array([1, 2]) * np.array([3, 4])# 除法result_array_div = np.array([1, 2]) / np.array([3, 4])# 数乘result_array_scalar_mul = 2 * np.array([3, 4])# 内积result_array_dot = np.dot(np.array([1, 2]), np.array([3, 4]))# 外积result_array_outer = np.outer(np.array([1, 2]), np.array([3, 4]))print("add = ", result_array_add)print("sub = ", result_array_sub)print("mul = ", result_array_mul)print("div = ", result_array_div)print("scalar_mul = ", result_array_scalar_mul)print("dot = ", result_array_dot)print("outer = ", result_array_outer)

2.5 tensor 对象的基本运算 import torch# 加法result_tensor_add = torch.tensor([1, 2]) + torch.tensor([3, 4])# 减法result_tensor_sub = torch.tensor([1, 2]) - torch.tensor([3, 4])# 乘法result_tensor_mul = torch.tensor([1, 2]) * torch.tensor([3, 4])# 除法result_tensor_div = torch.tensor([1, 2], dtype=torch.float) / torch.tensor([3, 4], dtype=torch.float)# 数乘result_tensor_scalar_mul = 2 * torch.tensor([3, 4])# 内积result_tensor_dot = torch.dot(torch.tensor([1, 2]), torch.tensor([3, 4]))# 外积result_tensor_outer = torch.ger(torch.tensor([1, 2]), torch.tensor([3, 4]))print("add = ", result_tensor_add)print("sub = ", result_tensor_sub)print("mul = ", result_tensor_mul)print("div = ", result_tensor_div)print("scalar_mul = ", result_tensor_scalar_mul)print("dot = ", result_tensor_dot)print("outer = ", result_tensor_outer)