ECE6504 β Deep Learning for Perception Introduction to CAFFE Ashwin Kalyan V
(C) Dhruv Batra 2
Logistic Regression as a Cascade (C) Dhruv Batra 3 Slide Credit: Marc'Aurelio Ranzato, Yann LeCun
Logistic Regression as a Cascade (C) Dhruv Batra 4 Slide Credit: Marc'Aurelio Ranzato, Yann LeCun
Logistic Regression as a Cascade (C) Dhruv Batra 5 Slide Credit: Marc'Aurelio Ranzato, Yann LeCun
Key Computation: Forward-Prop (C) Dhruv Batra 6 Slide Credit: Marc'Aurelio Ranzato, Yann LeCun
Key Computation: Back-Prop (C) Dhruv Batra 7 Slide Credit: Marc'Aurelio Ranzato, Yann LeCun
Training using Stochastic Gradient Descent π β π β ππΌπ
Training using Stochastic Gradient Descent Loss functions of NN are almost always non-convex π β π β ππΌL
Training using Stochastic Gradient Descent Loss functions of NN are almost always non-convex π β π β ππΌπ which makes training a little tricky. Many methods to find the optimum, like momentum update, Nesterov momentum update, Adagrad, RMSPRop, etc
Network β’ A network is a set of layers and its connections. β’ Data and gradients move along the connections. β’ Feed forward networks are Directed Acyclic graphs (DAG) i.e. they do not have any recurrent connections.
Main types of deep architectures feed-forward Feed-back Neural nets Hierar. Sparse Coding Conv Nets Deconv Nets input input Bi-directional Recurrent Stacked Recurrent Neural nets Auto-encoders Recursive Nets DBM LISTA input input (C) Dhruv Batra 12 Slide Credit: Marc'Aurelio Ranzato, Yann LeCun
Focus of this course feed-forward Feed-back Neural nets Hierar. Sparse Coding Conv Nets Deconv Nets input input Bi-directional Recurrent Stacked Recurrent Neural nets Auto-encoders Recursive Nets DBM LISTA input input (C) Dhruv Batra 13 Slide Credit: Marc'Aurelio Ranzato, Yann LeCun
Focus of this class feed-forward Feed-back Neural nets Hierar. Sparse Coding Conv Nets Deconv Nets input input Bi-directional Recurrent Stacked Recurrent Neural nets Auto-encoders Recursive Nets DBM LISTA input input (C) Dhruv Batra 14 Slide Credit: Marc'Aurelio Ranzato, Yann LeCun
Focus of this class feed-forward Feed-back Neural nets Hierar. Sparse Coding Why? Conv Nets Deconv Nets Because official CAFFE release supports DAG input input Bi-directional Recurrent Stacked Recurrent Neural nets Auto-encoders Recursive Nets DBM LISTA input input (C) Dhruv Batra 15 Slide Credit: Marc'Aurelio Ranzato, Yann LeCun
Outline β’ Caffe? β’ Installation β’ Key Ingredients β’ Example: Softmax Classifier β’ Pycaffe β’ Roasting β’ Resources β’ References 16
What is Caffe? Open framework, models, and worked examples for deep learning - 1.5 years - 450+ citations, 100+ contributors 2,500+ forks, >1 pull request / day average - - focus has been vision, but branching out: sequences, reinforcement learning, speech + text Prototype Train Deploy
What is Caffe? Open framework, models, and worked examples for deep learning Pure C++ / CUDA architecture for deep learning - - Command line, Python, MATLAB interfaces Fast, well-tested code - Tools, reference models, demos, and recipes - - Seamless switch between CPU and GPU Prototype Train Deploy
Installation
Installation
Installation β’ Strongly recommended that you use Linux (Ubuntu)/ OS X. Windows has some unofficial support though. β’ Prior to installing look at the installation page and the wiki - the wiki has more info. But all support needs to be taken with a pinch of salt - lots of dependencies β’ Suggested that you back up your data!
Installation β’ CUDA (Compute Unified Device Architecture) is a parallel computing platform and application programming interface (API) model created by NVIDIA β’ Installing CUDA β check if you have a cuda supported Graphics Processing Unit (GPU). If not, go for a cpu only installation of CAFFE. - Do not install the nvidia driver if you do not have a supported GPU
Installation β’ Clone the repo from here β’ Depending on the system configuration, make modifications to the Makefile.config file and proceed with the installation instructions. β’ We suggest that you use Anaconda python for the installation as it comes with the necessary python packages.
Quick Questions?
Key Ingredients
DAG SDS two-stream net Many current deep models have linear structure GoogLeNet Inception Module Caffe nets can have any directed acyclic graph (DAG) structure. LRCN joint vision-sequence model
name : "conv1" Blob type : CONVOLUTION bottom : "data" top : "conv1" β¦ definition β¦ Blobs are N-D arrays for storing and communicating information. top β hold data, derivatives, and parameters blob β lazily allocate memory β shuttle between CPU and GPU Data N umber x K Channel x H eight x W idth 256 x 3 x 227 x 227 for ImageNet train input Parameter: Convolution Weight N Output x K Input x H eight x W idth 96 x 3 x 11 x 11 for CaffeNet conv1 bottom Parameter: Convolution Bias blob 96 x 1 x 1 x 1 for CaffeNet conv1
Layer Protocol Setup : run once for initialization. Forward : make output given input. Backward : make gradient of output - w.r.t. bottom - w.r.t. parameters (if needed) Reshape : set dimensions. Compositional Modeling The Netβs forward and backward passes are Layer Development Checklist composed of the layersβ steps.
Layers β’ Caffe divides layers into - neuron layers (eg: Inner product), - Vision layers (Convolutional, pooling,etc) - Data layers (to read in input) - Loss layers β’ You can write your own layers. More development guidelines are here
Loss Classification loss (LOSS_TYPE) What kind of model is this? SoftmaxWithLoss HingeLoss Linear Regression EuclideanLoss Attributes / Multiclassification SigmoidCrossEntropyLoss Others⦠New Task Define the task by the loss . NewLoss
Protobuf Model Format layer { - Strongly typed format name: "ip" - Auto-generates code type: "InnerProduct" - Developed by Google bottom: "data" top: "ip" - Defines Net / Layer / Solver inner_product_param { schemas in caffe.proto num_output: 2 } message ConvolutionParameter { } // The number of outputs for the layer optional uint32 num_output = 1; // whether to have bias terms optional bool bias_term = 2 [default = true]; }
Softmax Classifier π§ πππ‘π‘(π, π§) π π¦ ππ¦ + π
Neural Network
Activation function Rectified Linear Unit (ReLU) Activation
Recipe for brewing a net β’ Convert the data to caffe-supported format LMDB, HDF5, list of images β’ Define the net β’ Configure the solver β’ Start train from supported interface (command line, python, etc)
Layers β Data Layers β’ Data Layers : gets data into the net - Data: LMDB/LEVELDB efficient way to input data, only for 1-of-k classification tasks - HDF5Data: takes in HDF5 format - easy to create custom non-image datasets but supports only float32/float64 - Data can be written easily in the above formats using python support. ( using lmdb and h5py respectively). We will see how to write hdf5 data shortly - Image Data: Reads in directly from images. Can be a little slow. - All layers (except hdf5) support standard data augmentation tasks
Recipe for brewing a net β’ Convert the data to caffe-supported format LMDB, HDF5, list of images β’ Define the network/architecture β’ Configure the solver β’ Start train from supported interface (command line, python, etc)
Example: Softmax Classifier Architecture file name: "LogReg" layer { name: "mnist" type: "Data" top: "data" top: "label" data_param { source: "input_leveldb" batch_size: 64 } }
Example: Softmax Classifier Architecture file name: "LogReg" layer { name: "mnist" type: "Data" top: "data" top: "label" data_param { source: "input_leveldb" batch_size: 64 } } layer { name: "ip" type: "InnerProduct" bottom: "data" top: "ip" inner_product_param { num_output: 2 } }
Example: Softmax Classifier Architecture file name: "LogReg" layer { name: "mnist" type: "Data" top: "data" top: "label" data_param { source: "input_leveldb" batch_size: 64 } } layer { name: "ip" type: "InnerProduct" bottom: "data" top: "ip" inner_product_param { num_output: 2 } } layer { name: "loss" type: "SoftmaxWithLoss" bottom: "ip" bottom: "label" top: "loss" }
Recipe for brewing a net β’ Convert the data to caffe-supported format LMDB, HDF5, list of images β’ Define the net β’ Configure the solver β’ Start train from supported interface (command line, python, etc)
Recommend
More recommend