元神经网络训练train函数

function [net,tr,out3,out4,out5,out6]=train(net,varargin) %TRAIN Train a neural network. % % [NET,TR] = <a href="matlab:doc train">train</a>(NET,X,T) takes a network NET, input data X % and target data T and returns the network after training it, and a % a training record TR. % % [NET,TR] = <a href="matlab:doc train">train</a>(NET,X) takes only input data, in cases where % the network's training function is unsupervised (i.e. does not require % target data). % % [NET,TR] = <a href="matlab:doc train">train</a>(NET,X,T,Xi,Ai,EW) takes additional optional % arguments suitable for training dynamic networks and training with % error weights. Xi and Ai are the initial input and layer delays states % respectively and EW defines error weights used to indicate % the relative importance of each target value. % % <a href="matlab:doc train">train</a> calls the network training function NET.<a href="matlab:doc nnproperty.net_trainFcn">trainFcn</a> with the % parameters NET.<a href="matlab:doc nnproperty.net_trainParam">trainParam</a> to perform training. Training functions % may also be called directly. % % <a href="matlab:doc train">train</a> arguments can have two formats: matrices, for static % problems and networks with single inputs and outputs, and cell arrays % for multiple timesteps and networks with multiple inputs and outputs. % % The matrix format is as follows: % X - RxQ matrix % Y - UxQ matrix. % Where: % Q = number of samples % R = number of elements in the network's input % U = number of elements in the network's output % % The cell array format is most general: % X - NixTS cell array, each element X{i,ts} is an RixQ matrix. % Xi - NixID cell array, each element Xi{i,k} is an RixQ matrix. % Ai - NlxLD cell array, each element Ai{i,k} is an SixQ matrix. % Y - NOxTS cell array, each element Y{i,ts} is a UixQ matrix. % Xf - NixID cell array, each element Xf{i,k} is an RixQ matrix. % Af - NlxLD cell array, each element Af{i,k} is an SixQ matrix. % Where: % TS = number of time steps % Ni = NET.<a href="matlab:doc nnproperty.net_numInputs">numInputs</a> % Nl = NET.<a href="matlab:doc nnproperty.net_numLayers">numLayers</a>, % No = NET.<a href="matlab:doc nnproperty.net_numOutputs">numOutputs</a> % ID = NET.<a href="matlab:doc nnproperty.net_numInputDelays">numInputDelays</a> % LD = NET.<a href="matlab:doc nnproperty.net_numLayerDelays">numLayerDelays</a> % Ri = NET.<a href="matlab:doc nnproperty.net_inputs">inputs</a>{i}.<a href="matlab:doc nnproperty.input_size">size</a> % Si = NET.<a href="matlab:doc nnproperty.net_layers">layers</a>{i}.<a href="matlab:doc nnproperty.layer_size">size</a> % Ui = NET.<a href="matlab:doc nnproperty.net_outputs">outputs</a>{i}.<a href="matlab:doc nnproperty.output_size">size</a> % % The error weights EW can be 1, indicating all targets are equally % important. It can also be either a 1xQ vector defining relative sample % importances, a 1xTS cell array of scalar values defining relative % timestep importances, an Nox1 cell array of scalar values defining % relative network output importances, or in general an NoxTS cell array % of NixQ matrices (the same size as T) defining every target element's % relative importance. % % The training record TR is a structure whose fields depend on the network % training function (net.NET.<a href="matlab:doc nnproperty.net_trainFcn">trainFcn</a>). It may include fields such as: % * Training, data division, and performance functions and parameters % * Data division indices for training, validation and test sets % * Data division masks for training validation and test sets % * Number of epochs (num_epochs) and the best epoch (best_epoch). % * A list of training state names (states). % * Fields for each state name recording its value throughout training % * Performances of the best network (best_perf, best_vperf, best_tperf) % % Here a static feedforward network is created, trained on some data, then % simulated using SIM and network notation. % % [x,t] = <a href="matlab:doc simplefit_dataset">simplefit_dataset</a>; % net = <a href="matlab:doc feedforwardnet">feedforwardnet</a>(10); % net = <a href="matlab:doc train">train</a>(net,x,t); % y1 = <a href="matlab:doc sim">sim</a>(net,x) % y2 = net(x) % % Here a dynamic NARX network is created, trained, and simulated on % time series data. % % [X,T] = <a href="matlab:doc simplenarx_dataset">simplenarx_dataset</a>; % net = <a href="matlab:doc narxnet">narxnet</a>(1:2,1:2,10); % <a href="matlab:doc view">view</a>(net) % [Xs,Xi,Ai,Ts] = <a href="matlab:doc preparets">preparets</a>(net,X,{},T); % net = <a href="matlab:doc train">train</a>(net,Xs,Ts,Xi,Ai); % Y = net(Xs,Xi,Ai) % % <strong>Training with Parallel Computing</strong> % % Parallel Computing Toolbox allows Neural Network Toolbox to train % networks faster and on larger datasets than can fit on one PC. % % (Parallel and GPU training are currently supported for backpropagation % training only, i.e. not Self-Organizing Maps. % % Here training automatically happens across MATLAB parallel workers. % % parpool % [X,T] = vinyl_dataset; % net = feedforwardnet(140,'trainscg'); % net = <a href="matlab:doc train">train</a>(net,X,T,'UseParallel','yes'); % Y = net(X,'UseParallel','yes'); % % Use Composite values to distribute the data manually, and get back % the results as a Composite value. If the data is loaded as it is % distributed then while each piece of the dataset must fit in RAM, the % entire dataset is only limited by the number of workers RAM. Use % the function <a href="matlab:doc configure">configure</a> to prepare a network for training % with parallel data. % % net = feedforwardnet(140,'trainscg'); % net = configure(net,X,T); % Xc = Composite; % Tc = Composite; % for i=1:numel(Xc) % Xc{i} = X+rand(size(X))*0.1; % (Use real data instead % Tc{i} = T+rand(size(T))*0.1; % instead of random data) % end % net = <a href="matlab:doc train">train</a>(net,Xc,Tc); % Yc = net(Xc); % Y = cat(2,Yc{:}); % % Networks can be trained using the current GPU device, if it is % supported by the Parallel Computing Toolbox. This is efficient for % large static problems or dynamic problems with many series. % % net = feedforwardnet(140,'trainscg'); % net = <a href="matlab:doc train">train</a>(net,X,T,'UseGPU','yes'); % Y = net(X,'UseGPU','yes'); % % If a network is static (no delays) and has a single input and output, % then training can be done with data already converted to gpuArray form, % if the network is configured with MATLAB data first. % % net = feedforwardnet(140,'trainscg'); % net = configure(net,X,T); % Xgpu = gpuArray(X); % Tgpu = gpuArray(T); % net = <a href="matlab:doc train">train</a>(net,Xgpu,Tgpu); % Ygpu = net(Xgpu); % Y = gather(Ygpu); % % To run in parallel, with workers associated with unique GPUs taking % advantage of that hardware, while the rest of the workers use CPUs: % % net = feedforwardnet(140,'trainscg'); % net = <a href="matlab:doc train">train</a>(net,X,T,'UseParallel','yes','UseGPU','yes'); % Y = net(X,'UseParallel','yes','UseGPU','yes'); % % Only using workers with unique GPUs may result in higher speed, as CPU % workers may not keep up. % % net = feedforwardnet(140,'trainscg'); % net = <a href="matlab:doc train">train</a>(net,X,T,'UseParallel','yes','UseGPU','only'); % Y = net(X,'UseParallel','yes','UseGPU','only'); % % Use the 'ShowResources' option to verify the computing resources used. % % net = train(...,'ShowResources','yes'); % % <strong>Training Safely with Checkpoint Files</strong> % % The optional parameter CheckpointFile allows