![](https://img-blog.csdnimg.cn/20201014180756923.png?x-oss-process=image/resize,m_fixed,h_64,w_64)
Pytorch学习
Chiaquin
本人熟悉机器学习、深度学习、图像处理专业知识,熟悉常用深度学习框架Pytorch,熟练运用Shell/Python脚本语言,有Linux环境下编程经验,熟悉C/C++,具有强烈的好奇心及学习能力,有很强的可塑性。
硕士期间,研究计算机视觉方向在农业上的应用问题,学习了多种计算机视觉方向的算法:如图像分类,目标检
测、语义分割、实例分割等;同时关注新的自动驾驶方面的知识,拥有1作SCI二区论文1篇,二作SCI二区论文1
篇,以及多项发明专利。
本人本科期间为车辆工程,对汽车结构比较有着比较深入的联系;从机械结构到电气、从物联网到智能化研究都有
比较基础的接触。
展开
-
CIFAR10数据集使用笔记
CIFAR10数据集 1. 数据集下载并转换为张量 train_set = torchvision.datasets.CIFAR10(root=data_path, train=True, download=True, transform=transforms.Compose([ transforms.ToTensor()原创 2020-10-08 15:25:24 · 2036 阅读 · 1 评论 -
(4)学习机制---Training, validation, and overfitting
The mechanics of learning No.4 Training, validation, and overfitting On one hand, you need to model to have enough capacity for it to fit the training set. On the other hand, you need the model to avoid overfitting. Therefore, the process for choosing the原创 2020-10-04 16:06:12 · 268 阅读 · 1 评论 -
(3)学习机制---Optimizers a la carte, Nits in autograd and switching it off
The mechanics of learning No.3 Optimizers a la carte Every optimizer constructor takes a list of parameters (aka PyTorch tensors, typically with requires_grad set to True) as the first input. All parameters passed to the optimizer are retained inside the o原创 2020-10-04 12:00:21 · 166 阅读 · 0 评论 -
(2)学习机制---PyTorch’s autograd: Backpropagate all things
The mechanics of learning No.2 PyTorch’s autograd: Backpropagate all things PyTorch tensors can remember where they come from in terms of the operations and parent tensors that originated them, and they can provide the chain of derivatives of such operatio原创 2020-10-03 16:42:40 · 142 阅读 · 0 评论 -
(1) 学习机制---Learning is parameter estimation
The mechanics of learning NO.1 Learning is parameter estimation A hot problem import torch t_c = [0.5, 14.0, 15.0, 28.0, 11.0, 8.0, 3.0, -4.0, 6.0, 13.0, 21.0] t_u = [35.7, 55.9, 58.2, 81.9, 56.3, 48.9, 33.9, 21.8, 48.4, 60.4, 68.4] t_c = torch.tensor(t原创 2020-09-30 16:25:10 · 173 阅读 · 0 评论 -
(3) 用张量表示实际数据---Images
Real-world data representation with tensors NO. 3 Images Following the same strategy that you used for earlier data types, to create a data set of multiple images to use as an input for your neural networks, you store the images in a batch along the first原创 2020-09-28 16:19:54 · 213 阅读 · 0 评论 -
(2) 用张量表示实际数据---Time series
Real-world data representation with tensors NO. 2 Time series In the meantime, we’ll switch to another interesting data set: data from a Washington, D.C., bike sharing system reporting the hourly count of rental bikes between 2011 and 2012 in the Capital原创 2020-09-27 19:48:27 · 303 阅读 · 0 评论 -
(1) 用张量表示实际数据---Tabular data
Real-world data representation with tensors NO. 1 Tabular data Python offers several options for loading a CSV file quickly. Start with the Wine Quality data set: csv Load your file and turn the resulting NumPy array into a PyTorch tensor. import csv im原创 2020-09-27 11:58:37 · 1401 阅读 · 0 评论 -
(4) 张量
It starts with a tensor NO.6 Numeric types The data type specifies the possible values that the tensor can hold (integers versus floating-point numbers) and the number of bytes per value ???? torch.float32 or torch.float—32-bit floating-point ???? torch原创 2020-09-26 11:13:54 · 142 阅读 · 0 评论 -
(3)张量
It starts with a tensor NO.4 Size, storage offset, and strides To index into a storage, tensors rely on a few pieces of information that, together with their storage, unequivocally define them: size, storage offset, and stride. The storage offset is the原创 2020-09-23 17:12:09 · 150 阅读 · 0 评论 -
(2) 张量
It starts with a tensor NO.3 Tensors and storages Values are allocated in contiguous chunks of memory, managed by <torch.Storage> instances. A PyTorch Tensor is a view over such a Storage that’s capable of indexing into that storage by using an offs原创 2020-09-23 11:28:07 · 113 阅读 · 0 评论 -
(1) 张量
It starts with a tensor NO.1 Preface The first step of this process is converting the input into floating-point numbers. PyTorch introduces a fundamental data structure: the tensor. NO.2 Tensor fundamentals A tensor is an array—that is, a data structu原创 2020-09-23 10:59:14 · 130 阅读 · 0 评论