Deep convolution networks with caffe

download Deep convolution networks with caffe

of 14

  • date post

  • Category


  • view

  • download


Embed Size (px)


“Deep neural networks. Tool set. Qick start”

Transcript of Deep convolution networks with caffe

  • 1. .. .. -

2. Deep learning1. deep learning. , , , .[1]2. 3. ?4. Deep convolutional neural networks, CAFFE implementation 3. Deep convolutional neural networksConvNet configuration by Krizhevsky [2] 4. (Features sets:)Convolution Neural Network Architecture Model[3] ? ? 5. : [4] , 6. Pooling pooling [5] . 7. deep learning deep convolutional neural network frameworkhttp://caffe.berkeleyvision.orgConvNetJS JS based deep learning framework - Java based deep learning framework CPU/GPU symbolic expression compiler in python A fast C++/CUDA implementation of convolutional(or more generally, feed-forward) neural networks provides a Matlab-like environment for state-of-the-art machinelearning algorithms in lua - C# deep learning,tutorial: 8. .. - apratster@gmail.comCAFFE1. GPU (CUDA) and CPU support2. Caffe can be accelerated by NVIDIA cuDNN3. Python and/or MATLAB wrappers4. Config paradigm vs Coding paradigm. Command line tools.*CPU-only Caffe:Uncomment the CPU_ONLY := 1 flag in Makefile.config 9. CAFFE :build/tools MNIST $CAFFE_ROOT./data/mnist/ $CAFFE_ROOT./examples/mnist/ 10. ?- databases (LevelDB or LMDB)- directly from memory- from files on disk in HDF5- common image formats. dataOutput data-snapshot file with mode-snapshot file with solver stateSolver? Yes, we can continue breacked training from snapshot 11. CAFFECaffe stores and communicates data in 4-dimensional arrays called blobsname: "LogReg"layers {name: "mnist"type: DATAtop: "data"top: "label"data_param {source: "input_leveldb"batch_size: 64}} layers {name: "ip"type: INNER_PRODUCTbottom: "data"top: "ip"inner_product_param {num_output: 2}} layers {name: "loss"type: SOFTMAX_LOSSbottom: "ip"bottom: "label"top: "loss"} 12. Convolutional layerRequired fieldnum_output (c_o): the number of filterskernel_size (or kernel_h and kernel_w): specifies height and width of each filterPooling layerRequiredkernel_size (or kernel_h and kernel_w): specifies height and width of each filterLoss Layers, Activation / Neuron Layers, Data Layers, Common LayersHow to configure?Ready to use models in folder: examples 13. 1. , .2. Caffe GPU.3. , .4. , .5. - 6. C++, Python Mathlab. 14. 1. L. Deng and D. Yu, "Deep Learning: Methods and Applications ConvNet configuration by Krizhevsky et al Efficient mapping of the training of Convolutional Neural Networks to a CUDA-basedcluster !