If you installed VM and Linux libraries as in the tutorial, you should not get any errors. Otherwise, you may need to install wget or gunzip.

Similar documents
Deep learning using Caffe Execution Process

Accelerating Convolutional Neural Nets. Yunming Zhang

CAFFE TUTORIAL ROHIT GIRDHAR. Brewing Deep Networks With Caffe. Many slides from Xinlei Chen ( tutorial), Caffe CVPR 15 tutorial

CAFFE TUTORIAL. Brewing Deep Networks With Caffe XINLEI CHEN

Machine Learning Workshop

Image Classification using Transfer Learning from Siamese Networks based on Text Metadata Similarity

Getting started with Caffe. Jon Barker, Solutions Architect

Deep Learning with Tensorflow AlexNet

Day 1 Lecture 6. Software Frameworks for Deep Learning

NVCAFFE. DU _v April User Guide

Introduction to Neural Networks and Brief Tutorial with Caffe 10 th Set of Notes

Deep Learning and Its Applications

Pyramidal Deep Models for Computer Vision

Index. Umberto Michelucci 2018 U. Michelucci, Applied Deep Learning,

Deep Learning for Computer Vision II

Machine Learning. Deep Learning. Eric Xing (and Pengtao Xie) , Fall Lecture 8, October 6, Eric CMU,

NVIDIA FOR DEEP LEARNING. Bill Veenhuis

A Quick Guide on Training a neural network using Keras.

Caffe tutorial. Seong Joon Oh

RNN LSTM and Deep Learning Libraries

CNN Basics. Chongruo Wu

SEMANTIC COMPUTING. Lecture 8: Introduction to Deep Learning. TU Dresden, 7 December Dagmar Gromann International Center For Computational Logic

COMP9444 Neural Networks and Deep Learning 7. Image Processing. COMP9444 c Alan Blair, 2017

CIS581: Computer Vision and Computational Photography Project 4, Part B: Convolutional Neural Networks (CNNs) Due: Dec.11, 2017 at 11:59 pm

Keras: Handwritten Digit Recognition using MNIST Dataset

Keras: Handwritten Digit Recognition using MNIST Dataset

Machine Learning 13. week

MoonRiver: Deep Neural Network in C++

All You Want To Know About CNNs. Yukun Zhu

CS 6501: Deep Learning for Computer Graphics. Training Neural Networks II. Connelly Barnes

Managing Caffe Deep Learning with HTCondor

IMPLEMENTING DEEP LEARNING USING CUDNN 이예하 VUNO INC.

Deep Learning Cook Book

Perceptron: This is convolution!

Fuzzy Set Theory in Computer Vision: Example 3, Part II

Machine Learning and Algorithms for Data Mining Practical 2: Neural Networks

CPSC 340: Machine Learning and Data Mining. Deep Learning Fall 2016

Lecture 20: Neural Networks for NLP. Zubin Pahuja

Lecture : Neural net: initialization, activations, normalizations and other practical details Anne Solberg March 10, 2017

Tutorial on Machine Learning Tools

Improving the way neural networks learn Srikumar Ramalingam School of Computing University of Utah

Mocha.jl. Deep Learning in Julia. Chiyuan Zhang CSAIL, MIT

Dynamic Routing Between Capsules

Natural Language Processing CS 6320 Lecture 6 Neural Language Models. Instructor: Sanda Harabagiu

Deep neural networks II

Supervised Learning in Neural Networks (Part 2)

Multinomial Regression and the Softmax Activation Function. Gary Cottrell!

Survey of Convolutional Neural Network

Tutorial on Keras CAP ADVANCED COMPUTER VISION SPRING 2018 KISHAN S ATHREY

Machine Learning With Python. Bin Chen Nov. 7, 2017 Research Computing Center

Intro to Deep Learning. Slides Credit: Andrej Karapathy, Derek Hoiem, Marc Aurelio, Yann LeCunn

Fusion of Mini-Deep Nets

Deep Learning for Computer Vision with MATLAB By Jon Cherrie

Convolutional Neural Networks. Computer Vision Jia-Bin Huang, Virginia Tech

Deep Learning. Vladimir Golkov Technical University of Munich Computer Vision Group

Deep Learning. Practical introduction with Keras JORDI TORRES 27/05/2018. Chapter 3 JORDI TORRES

Lecture : Training a neural net part I Initialization, activations, normalizations and other practical details Anne Solberg February 28, 2018

Neural Network Compiler BNN Scripts User Guide

Distributed Training of Deep Neural Networks: Theoretical and Practical Limits of Parallel Scalability

Hello Edge: Keyword Spotting on Microcontrollers

Advanced Machine Learning

CUDNN. DU _v07 May Developer Guide

ImageNet Classification with Deep Convolutional Neural Networks

Lecture 2 Notes. Outline. Neural Networks. The Big Idea. Architecture. Instructors: Parth Shah, Riju Pahwa

Global Optimality in Neural Network Training

Deep Learning. Volker Tresp Summer 2014

Multi-Task Self-Supervised Visual Learning

CNN Visualizations. Seoul AI Meetup Martin Kersner, 2018/01/06

Reverse Engineering AI Models

INTRODUCTION TO DEEP LEARNING

Additive Manufacturing Defect Detection using Neural Networks

Deep Neural Networks Optimization

Introduction to Neural Networks

Convolutional Networks in Scene Labelling

CIS680: Vision & Learning Assignment 2.b: RPN, Faster R-CNN and Mask R-CNN Due: Nov. 21, 2018 at 11:59 pm

Deep Learning For Video Classification. Presented by Natalie Carlebach & Gil Sharon

Code Mania Artificial Intelligence: a. Module - 1: Introduction to Artificial intelligence and Python:

Multi-layer Perceptron Forward Pass Backpropagation. Lecture 11: Aykut Erdem November 2016 Hacettepe University

Deep Learning Explained Module 4: Convolution Neural Networks (CNN or Conv Nets)

Know your data - many types of networks

Inception and Residual Networks. Hantao Zhang. Deep Learning with Python.

Convolutional Neural Networks and Supervised Learning

Convolutional Neural Networks

Deep Learning. Visualizing and Understanding Convolutional Networks. Christopher Funk. Pennsylvania State University.

Research on Pruning Convolutional Neural Network, Autoencoder and Capsule Network

CSE 559A: Computer Vision

CMU Lecture 18: Deep learning and Vision: Convolutional neural networks. Teacher: Gianni A. Di Caro

Predicting Goal-Scoring Opportunities in Soccer by Using Deep Convolutional Neural Networks. Master s Thesis

CS 2750: Machine Learning. Neural Networks. Prof. Adriana Kovashka University of Pittsburgh April 13, 2016

Convolutional Neural Networks

Introduction to Deep Learning

CS230: Deep Learning Winter Quarter 2018 Stanford University

Convolutional Neural Network Layer Reordering for Acceleration

Everything you wanted to know about Deep Learning for Computer Vision but were afraid to ask

arxiv: v3 [cs.lg] 30 Dec 2016

Deep Convolutional Neural Networks. Nov. 20th, 2015 Bruce Draper

Real-time Hand Tracking under Occlusion from an Egocentric RGB-D Sensor Supplemental Document

Como funciona o Deep Learning

CENG 783. Special topics in. Deep Learning. AlchemyAPI. Week 11. Sinan Kalkan

CS231N Course Project Report Classifying Shadowgraph Images of Planktons Using Convolutional Neural Networks

Transcription:

MNIST 1- Prepare Dataset cd $CAFFE_ROOT./data/mnist/get_mnist.sh./examples/mnist/create_mnist.sh If you installed VM and Linux libraries as in the tutorial, you should not get any errors. Otherwise, you may need to install wget or gunzip. 2-Open Text Editor cd $CAFFE_ROOT cd examples cd mnist gedit Now, you have a text editor that waits for you to configure the deep architecture. 3-Define Network Name name: "LeNet" 3-Define Trian Data Layer name: "mnist" type: "Data" top: "data" top: "label" include { phase: TRAIN transform_ scale: 0.00390625 data_ source: "examples/mnist/mnist_train_lmdb" batch_size: 64 backend: LMDB

Let s look at what the code refers. mnist is the layer name. DATA is the layer type. Data is read from the lmdb source. Batch size is 64. Scale is set to 1/256 to set the pixel value range to [0,1). This layers produces two blobs as data and label. The naming is self-explanatory so the layer definitions can easily be understood. 3-Define Test Data Layer name: "mnist" type: "Data" top: "data" top: "label" include { phase: TEST transform_ scale: 0.00390625 data_ source: "examples/mnist/mnist_test_lmdb" batch_size: 100 backend: LMDB 4 Define Convolutional Layer name: "conv1" type: "Convolution" bottom: "data" top: "conv1" lr_mult: 1 lr_mult: 2 convolution_ num_output: 20 kernel_size: 5 stride: 1 weight_filler { type: "xavier" bias_filler { type: "constant"

This layer takes the data blob as input and generates conv1 layer. Output has 20 channels, kernel size is set to 5 and stride is 1. Weights and bias values are randomly initialized. xavier is the algorithm to adjust the scale of the initialization based on number of input and output neurons. lr_mult are the learning rate adjustments. It means the weight learning rate is set to the same value given by the solver and bias learning rate is set to the double. 5- Define Pooling Layer name: "pool1" type: "Pooling" bottom: "conv1" top: "pool1" pooling_ pool: MAX kernel_size: 2 stride: 2 We defined a non-overlapping max pooling operation with block size and stride of 2. Let s add another convolutional and pooling layer to increase the abstraction in the network. 6- Define another Pooling and Convolutional Layer name: "conv2" type: "Convolution" bottom: "pool1" top: "conv2" lr_mult: 1 lr_mult: 2 convolution_ num_output: 50 kernel_size: 5 stride: 1 weight_filler { type: "xavier" bias_filler { type: "constant" name: "pool2" type: "Pooling" bottom: "conv2"

top: "pool2" pooling_ pool: MAX kernel_size: 2 stride: 2 7 Define the Fully Connected Layer name: "ip1" type: "InnerProduct" bottom: "pool2" top: "ip1" lr_mult: 1 lr_mult: 2 inner_product_ num_output: 500 weight_filler { type: "xavier" bias_filler { type: "constant" This layers take the input from the pooling layer and outputs 500 nodes. 8- Define the Activation Layer name: "relu1" type: "ReLU" bottom: "ip1" top: "ip1" Note that the bottom and top layers are defined as the same. This kind of configuration corresponds to the in-place operation which can be used for element-wise operations to save some memory. 8- Define another Fully Connected Layer

name: "ip2" type: "InnerProduct" bottom: "ip1" top: "ip2" lr_mult: 1 lr_mult: 2 inner_product_ num_output: 10 weight_filler { type: "xavier" bias_filler { type: "constant" 9- Define the Accuracy layer name: "accuracy" type: "Accuracy" bottom: "ip2" bottom: "label" top: "accuracy" include { phase: TEST This layer is just to show the accuracy of the output with respect to the target and it does not have a backward step. 10 - Define the Loss Layer name: "loss" type: "SoftmaxWithLoss" bottom: "ip2" bottom: "label" top: "loss" - Save the file as msl_lenet_train_test.prototxt

Loss layer takes the predictions and labels as the input. This layer does not have any outputs but it initiates the gradient and calculates the loss when backpropagation starts. 11 Define Solver - Go to $CAFFE_ROOT/examples/mnist - Open text editor and type the following: # The train/test net protocol buffer definition net: "examples/mnist/lenet_train_test.prototxt" # test_iter specifies how many forward passes the test should carry out. # In the case of MNIST, we have test batch size 100 and 100 test iterations, # covering the full 10,000 testing images. test_iter: 100 # Carry out testing every 500 training iterations. test_interval: 500 # The base learning rate, momentum and the weight decay of the network. base_lr: 0.01 momentum: 0.9 weight_decay: 0.0005 # The learning rate policy lr_policy: "inv" gamma: 0.0001 power: 0.75 # Display every 100 iterations display: 100 # The maximum number of iterations max_iter: 10000 # snapshot intermediate results snapshot: 5000 snapshot_prefix: "examples/mnist/lenet" # solver mode: CPU or GPU solver_mode: CPU - Save the file as msl_lenet_solver.prototxt: 12 - Write the test script - Go to $CAFFE_ROOT/examples/mnist - Open text editor and type the following: #!/usr/bin/env sh./build/tools/caffe train --solver=examples/mnist/msl_lenet_solver.prototxt - Save the file as msl_lenet.sh - Go to $CAFFE_ROOT/examples/mnist chmod +x msl_lenet.sh

13 Run the test script cd $CAFFE_ROOT./examples/mnist/msl_lenet.sh Layer Writing Rules: layers { //...layer definition... include: { phase: TRAIN Layers can have rules about when and how they are included in the network. For example, if the layer definition includes the above statement, that layer is only included in the training phase. Layer Types in Caffe Vision Layers [KEYWORD] PS: Keywords can change from version to the version - Convolution [CONVOLUTION] - Pooling [POOLING] - Local Response Normalization [LRN] Loss Layers - Softmax [SOFTMAX_LOSS] - Sum-of-Squares / Euclidean [EUCLIDEAN_LOSS] - Hinge/Margin [HINGE_LOSS] - Sigmoid Cross Entropy [SIGMOID_CROSS_ENTROPY_LOSS] - Infogain [INFOGAIN_LOSS] - Accuracy and Top-k: [ACCURACY]: accuracy of the output with respect to the target, no backward steps Activation / Neuron Layers

- ReLU / Rectifies-Linear and Leaky-ReLU [RELU] - Sigmoid [SIGMOID] - TanH / Hyperbolic Tangent [TANH] - Absolute Value [ABSVAL] - Power [POWER] - Binomial Normal Log Likelihood [BNLL] Data Layers - Database [DATA] - Memory [In-Memory]: Reads data directly from memory without copying it - HDF5 Output [HDF5_OUTPUT]: Write input blobs to disk - Images [IMAGE_DATA] - Windows [WINDOWS_DATA] - Dummy [DUMMY_DATA] Common Layers - Inner Product [INNER_PRODUCT] - Splitting [SPLIT]: input blob -> multiple output blobs - Flattening [FLATTEN]: Blob to vector conversion - Concatenation [CONCAT] - Slicing [SLICE]: input layer -> multiple output layer - Element-wise operations [ELTWISE] - Argmax [ARGMAX] - Softmax [SOFTMAX] - Mean-Variance Normalization [MVN]

2024 © technodocbox.com Privacy Policy | Terms of Service | Feedback