Yen-Chen Lin yenchenlin

Caffe Installation

Note on how to install caffe on Ubuntu. Sucessfully install using CPU, more information for GPU see this link

###Installation

verify all the preinstallation according to CUDA guide e.g.

lspci | grep -i nvidia

Videos

Introduction to Functional Programming Johannes Weiß - https://vimeo.com/100786088
ReactiveCocoa at MobiDevDay Andrew Sardone - https://vimeo.com/65637501
The Future Of ReactiveCocoa Justin Spahr-Summers - https://www.youtube.com/watch?v=ICNjRS2X8WM
Enemy of the State Justin Spahr-Summers - https://www.youtube.com/watch?v=7AqXBuJOJkY
WWDC 2014 Session 229 - Advanced iOS Application Architecture and Patterns Andy Matuschak - https://developer.apple.com/videos/play/wwdc2014/229/
Functioning as a Functionalist Andy Matuschak - https://www.youtube.com/watch?v=rJosPrqBqrA
Controlling Complexity in Swift Andy Matuschak - https://realm.io/news/andy-matuschak-controlling-complexity/

For each machine running xmodmap will give you the mapping and keycode, take a look first then write the script. I use ubuntu and mac keyboard. The below maps both left and right control and super.

Create an .Xmodmap file in your Linux home directory, with the following contents, then execute xmodmap .Xmodmap

clear control
clear mod4

keycode 37 = Super_L
keycode 105 = Super_R

Tutorial: PyTorch Gradient Checkpointing with Detailed Torch Background and Implementation

In this tutorial, we'll dive deep into gradient checkpointing in PyTorch, a memory optimization technique for neural network training. We'll cover its purpose, mechanics, and provide detailed insights into PyTorch's internal implementation, including advanced features like early stopping and selective checkpointing. Additionally, we'll address the user's specific requests for background on Torch operations, Torch dispatch, and detailed implementation analysis. Practical examples, flowcharts, and comprehensive explanations are included to ensure clarity.

Introduction to Gradient Checkpointing

Gradient checkpointing reduces memory consumption during the training of deep neural networks. Normally, during the forward pass, all intermediate activations are stored in memory for gradient computation in the backward pass. This can lead to high memory usage, especially for large models. Gradient checkpointing addresses t

	#!/bin/bash

	# Script for installing tmux on systems where you don't have root access.
	# tmux will be installed in $HOME/local/bin.
	# It's assumed that wget and a C/C++ compiler are installed.

	# exit on error
	set -e

	TMUX_VERSION=1.8