- 博客(58)
- 资源 (1)
- 收藏
- 关注
原创 OpenCL - OpenCL Reference Pages
OpenCL - OpenCL Reference PagesOpenCLhttps://www.khronos.org/opencl/Khronos OpenCL Registryhttps://www.khronos.org/registry/OpenCL/OpenCL Reference Pageshttps://www.khronos.org/registry/OpenCL/sdk/1.2/docs/man/xhtml/
2020-06-30 23:32:30 428
原创 Heterogeneous Computing with OpenCL 2.0 - OpenCL 2.0 异构计算 - 书中源代码
Heterogeneous Computing with OpenCL 2.0 - OpenCL 2.0 异构计算 - 书中源代码1. OpenCL 2.0 异构计算 (第三版)1.1 GitHubhttps://github.com/xiaoweiChen/Heterogeneous-Computing-with-OpenCL-2.0Heterogeneour Computing with OpenCL 2.0 (Thrid Edition) 中文翻译。1.2 书栈网https://www.b
2020-06-30 22:47:52 834 2
原创 Windows 10 - Visual Studio 2015 - OpenCL - CUDA Toolkit 10.1 - OpenCL 编程环境配置
Windows 10 - Visual Studio 2015 - OpenCL - CUDA Toolkit 10.1 - OpenCL 编程环境配置
2020-06-30 00:22:31 3669
原创 CUDA 并行计算
CUDA 并行计算并行计算可以被定义为同时使用许多计算资源 (核心或计算机) 来执行并发计算,一个大的问题可以被分解成多个小问题,然后在不同的计算资源上并行处理这些小问题。所有包含并发执行任务的程序都是并行程序。在应用程序中有两种基本的并行类型:任务并行和数据并行。当许多任务或函数可以独立地、大规模地并行执行时,这就是任务并行。任务并行的重点在于利用多核系统对任务进行分配。当可以同时处理许多数据时,这就是数据并行。数据并行的重点在于利用多核系统对数据进行分配。CUDA 编程非常适合解决数据并行计
2020-06-25 23:40:18 1167
原创 tf.to_int32
tf.to_int32https://github.com/tensorflow/docs/tree/r1.4/site/en/api_docs/api_docs/python/tfsite/en/api_docs/api_docs/python/tf/to_int32.mdto_int32( x, name='ToInt32')Defined in tensorflow/python/ops/math_ops.py.See the guide: Tensor Transfor
2020-06-25 23:35:31 1698
原创 tf.equal (API r1.3)
tf.equal (API r1.3)https://github.com/tensorflow/docs/tree/r1.3/site/en/api_docs/api_docs/python/tfsite/en/api_docs/api_docs/python/tf/equal.mdequal( x, y, name=None)Defined in tensorflow/python/ops/gen_math_ops.py.See the guide: Control
2020-06-25 23:27:59 349
原创 torch.unsqueeze() - torch.unsqueeze_() - v1.5.0
torch.unsqueeze() - torch.unsqueeze_() - v1.5.0torch.unsqueeze (Python function, in torch)torch.Tensor.unsqueeze (Python method, in torch.Tensor)torch.Tensor.unsqueeze_ (Python method, in torch.Tensor)torch.Tensorhttps://pytorch.org/docs/stable/tens
2020-06-25 21:44:34 950
原创 Power and logarithmic functions - 幂函数与对数函数
Power and logarithmic functions - 幂函数与对数函数math - Mathematical functions - 数学函数https://docs.python.org/3/library/math.html1. math.exp(x)Return e raised to the power x, where e = 2.718281… is the base of natural logarithms. This is usually more accurate
2020-06-25 20:44:37 804
原创 masked_fill_() - masked_fill() - v1.5.0
masked_fill_() - masked_fill() - v1.5.0torch.Tensorhttps://pytorch.org/docs/stable/tensors.htmltorch.Tensor.masked_fill (Python method, in torch.Tensor)torch.Tensor.masked_fill_ (Python method, in torch.Tensor)masked_fill_(mask, value) - 函数名后面加下划线。i
2020-06-25 18:50:41 5154
原创 OSVR - Open-Source Virtual Reality - 开源虚拟现实
OSVR - Open-Source Virtual Reality - 开源虚拟现实http://www.osvr.org/http://www.osvr.org/cn-zh/虚拟现实是一种重现实际或虚构环境,模拟用户在其中真实存在的沉浸式数字娱乐形式。这种体验还模拟感觉体验,可包括视觉、触觉和听觉。1. OSVR Organizationhttps://github.com/OSVR2. OSVR Developer Portalhttps://osvr.github.io/...
2020-06-25 10:10:01 2467
原创 PyTorch softmax - torch.nn - torch.nn.functional
PyTorch softmax - torch.nn - torch.nn.functionalPyTorch documentationhttps://pytorch.org/docs/stable/index.html0. softmax - torch.nn - torch.nn.functionaltorch.nn.functional.softmax (Python function, in torch.nn.functional)定义的是一个函数。torch.nn.functio.
2020-06-22 00:09:47 1878 1
原创 Linux cp 命令 - copy files and directories (拷贝文件或目录)
Linux cp 命令 - copy files and directories (拷贝文件或目录)
2020-06-20 22:31:01 1652 2
原创 torch.triu() - torch.triu_() - v1.5.0
torch.triu() - torch.triu_() - v1.5.0torch.triu (Python function, in torch)torch.Tensor.triu (Python method, in torch.Tensor)torch.Tensor.triu_ (Python method, in torch.Tensor)torch.Tensorhttps://pytorch.org/docs/stable/tensors.htmltriu(k=0) ->
2020-06-20 20:20:13 5909
原创 PyTorch model - optimizer - state_dict() - torch.save(config, save_path) - torch.load(load_path)
PyTorch model - optimizer - state_dict() - torch.save(config, save_path) - torch.load(load_path)1. state_dict()#!/usr/bin/env python# -*- coding: utf-8 -*-# yongqiang chengfrom __future__ import absolute_importfrom __future__ import divisionfrom __
2020-06-20 19:48:21 2841
原创 RuntimeError: OrderedDict mutated during iteration
RuntimeError: OrderedDict mutated during iteration
2020-06-20 19:41:10 2399
原创 Keras style model.summary() in PyTorch - 打印 PyTorch 模型结构
Keras style model.summary() in PyTorch - 打印 PyTorch 模型结构https://github.com/sksq96/pytorch-summaryhttps://pypi.org/project/torchsummary/Model summary in PyTorch similar to model.summary() in Keras.Keras has a neat API to view the visualization of the mo
2020-06-20 14:33:54 1456 1
原创 tf.transpose (API r1.3)
tf.transpose (API r1.3)https://github.com/tensorflow/docs/tree/r1.3/site/en/api_docs/api_docs/python/tfsite/en/api_docs/api_docs/python/tf/transpose.mdtranspose( a, perm=None, name='transpose')Defined in tensorflow/python/ops/array_ops.py
2020-06-20 09:41:38 668
原创 GPU 核心和 CPU 核心
GPU 核心和 CPU 核心费林分类法 (Flynn’s Taxonomy)单指令单数据 (single instruction, single data,SISD)单指令多数据 (single instruction, multiple data,SIMD)多指令单数据 (multiple instruction, single data,MISD)多指令多数据 (multiple instruction, multiple data,MIMD)SIMD 最大的优势或许就是,在 CPU 上编写
2020-06-20 09:02:43 3073
原创 saving and loading models - 保存和读取模型
saving and loading models - 保存和读取模型https://pytorch.org/tutorials/beginner/saving_loading_models.htmlhttps://github.com/pytorch/tutorials/blob/master/beginner_source/saving_loading_models.pyhttps://pytorch.org/tutorials/index.htmlThis document provides
2020-06-19 00:47:21 1061
原创 batch normalization - layer normalization - instance normalization - group normalization
batch normalization - layer normalization - instance normalization - group normalizationfeature normalization (batch normalization - layer normalization - instance normalization - group normalization)1. 4D tensor (N×C×H×WN \times C \times H \times WN×C×H
2020-06-14 21:46:40 789
原创 torch.squeeze() - torch.squeeze_() - v1.5.0
torch.squeeze() - torch.squeeze_() - v1.5.0torch.squeeze (Python function, in torch)torch.Tensor.squeeze (Python method, in torch.Tensor)torch.Tensor.squeeze_ (Python method, in torch.Tensor)torch.Tensorhttps://pytorch.org/docs/stable/tensors.htmls
2020-06-14 19:21:42 1336
原创 弧度制 - 角度制
弧度制 - 角度制1. 弧度制 (radian measure)弧度制是使用弧长与半径之比度量对应圆心角角度的方式,单位是 rad,读作弧度。1 弧度的角等于半径长的圆弧所对的圆心角。由于圆弧长短与圆半径之比,不因为圆的大小而改变,所以弧度数是一个与圆的半径无关的量。角度以弧度给出时,通常不写弧度单位。弧度制的精髓就在于统一了度量弧与角的单位。2π rad=360°2\pi \ rad = 360°2π rad=360°1π rad=180°1\pi \ rad = 1
2020-06-14 18:00:55 10847 1
原创 torch.sin() - torch.cos() - v1.5.0
torch.sin() - torch.cos() - v1.5.0TORCHhttps://pytorch.org/docs/stable/torch.htmltorch.sin() - torch.cos() 的 input (Tensor) 都是弧度制数据,不是角度制数据。torch.sin (Python function, in torch)torch.Tensor.sin (Python method, in torch.Tensor)torch.Tensor.sin_
2020-06-14 17:29:18 8701
原创 torch.Tensor - v1.5.0
torch.Tensor - v1.5.0torch.Tensorhttps://pytorch.org/docs/stable/tensors.htmlA torch.Tensor is a multi-dimensional matrix containing elements of a single data type.torch.Tensor 是一种包含单一数据类型元素的多维矩阵。Torch defines nine CPU tensor types and nine GPU tensor
2020-06-14 16:20:22 652
原创 torch.arange() - v1.5.0
torch.arange() - v1.5.0torchhttps://pytorch.org/docs/stable/torch.htmltorch.arange(start=0, end, step=1, out=None, dtype=None, layout=torch.strided, device=None, requires_grad=False) -> TensorReturns a 1-D tensor of size ⌈end−startstep⌉\left\lceil \
2020-06-14 14:27:21 2128
原创 torch.zeros() - v1.5.0
torch.zeros() - v1.5.0torchhttps://pytorch.org/docs/stable/torch.htmltorch.zeros(*size, out=None, dtype=None, layout=torch.strided, device=None, requires_grad=False) -> TensorReturns a tensor filled with the scalar value 0, with the shape defined by
2020-06-14 13:18:55 1513
原创 Linux du 命令 - estimate file space usage (计算文件空间使用情况)
Linux du 命令 - estimate file space usage (计算文件空间使用情况)
2020-06-14 10:59:11 640 2
原创 df - report file system disk space usage - 文件系统磁盘空间使用情况
df - report file system disk space usage - 文件系统磁盘空间使用情况df displays the amount of disk space available on the file system containing each file name argument. If no file name is given, the space available on all currently mounted file systems is shown. Di
2020-06-14 09:36:28 718
原创 Positional Encoding - 位置编码
Positional Encoding - 位置编码1. Positional EncodingSince our model contains no recurrence and no convolution, in order for the model to make use of the order of the sequence, we must inject some information about the relative or absolute position of the tok
2020-06-12 22:16:10 5264 2
原创 基础背包问题 - 多维有界背包问题 - 深度优先搜索 (递归)
基础背包问题 - 多维有界背包问题 - 深度优先搜索 (递归)1. 基础背包问题背包问题 (Knapsack problem) 是一种组合优化的 NP 完全问题。给定一组物品,每种物品都有自己的重量和价格,在限定的总重量内,我们如何选择,才能使得物品的总价值最高。如果限定每种物品只能选择 0 个或 1 个,则问题称为 0-1 背包问题 (0-1 knapsack problem) 。如果限定物品 j 最多只能选择 maxj 个,则问题称为有界背包问题 (bounded knapsack proble
2020-06-11 23:16:57 1304
原创 OpenJDK 64-Bit Server VM warning - Option UseConcMarkSweepGC was deprecated in version 9.0
OpenJDK 64-Bit Server VM warning - Option UseConcMarkSweepGC was deprecated in version 9.0
2020-06-10 23:38:10 28655 21
原创 基础背包问题 - 无界背包问题或完全背包问题 - 深度优先搜索 (递归)
基础背包问题 - 无界背包问题或完全背包问题 - 深度优先搜索 (递归)1. 基础背包问题有 N 种物品和一个承受最大重量为 W 的背包。第 i 种物品的重量是 w[i],价值是 v[i]。求解将哪些物品装入背包可使这些物品的重量总和不超过背包容量,且价值总和最大。背包问题 (Knapsack problem) 是一种组合优化的 NP 完全问题。给定一组物品,每种物品都有自己的重量和价格,在限定的总重量内,我们如何选择,才能使得物品的总价格最高。如果限定每种物品只能选择 0 个或 1 个,则问题称为
2020-06-09 23:32:54 1073
原创 torchaudio - Python wave 读取音频数据对比
torchaudio - Python wave 读取音频数据对比1. torchaudio: an audio library for PyTorchhttps://github.com/pytorch/audioData manipulation and transformation for audio signal processing, powered by PyTorch.torchaudio: an audio library for PyTorchhttps://github.com
2020-06-07 22:50:12 6804 13
原创 end2end-asr-pytorch - audio processing - speech signal processing
end2end-asr-pytorch - audio processing - speech signal processinghttps://github.com/gentaiscool/end2end-asr-pytorch采样频率/取样频率是每秒钟采集声音样本的次数。采样频率越高,声音质量越好,声音还原越真实,同时占用资源越多。采样位数/量化精度/采样值/取样值是采样样本幅度量化,用来衡量声音波动变化的一个参数。数值越大,分辨率越高,发出声音的能力越强。采样数据记录的是振幅,采样精度取决于采
2020-06-07 22:14:13 1260
原创 PyTorch 中文文档 - 教程
PyTorch 中文文档 - 教程PyTorch 中文文档https://www.pytorchtutorial.com/docs/https://pytorch-cn.readthedocs.io/zh/latest/PyTorch 中文文档 & 教程https://pytorch.apachecn.org/
2020-06-07 22:07:47 423
Migrating Unity applications from Oculus to OSVR
2016-08-07
空空如也
TA创建的收藏夹 TA关注的收藏夹
TA关注的人