The custom loss function, which is trained with the dlarray structure, reports an error when using sgdmupdate to update, and cannot be assigned, because this type of variable
% 定义 LSTM 网络结构
numFeatures = size(X_train, 2); % 特征数量，这里是 3
numHiddenUnits = 100; % LSTM 隐藏单元数量
layers = [ …
sequenceInputLayer(numFeatures)
lstmLayer(numHiddenUnits)
fullyConnectedLayer(numFeatures)
];
maxEpochs = 50;
miniBatchSize = 3;
learningRate = 0.01;
% 初始化 LSTM 模型
net = dlnetwork(layers); % 在 CPU 上训练
% 训练循环
numObservations = size(X_train, 1);
numMiniBatches = floor(numObservations / miniBatchSize);
averageGrad = [];
averageSqGrad = [];
iteration = 0;
Velocities = zeros(size(net));
momentum = 0.9;
for epoch = 1:maxEpochs
% 打乱训练数据
idx = randperm(numObservations);
X_train_shuffled = X_train(idx, :);
Y_train_shuffled = Y_train(idx, :);
totalLoss = 0;
for i = 1:numMiniBatches
idxBatch = (i – 1) * miniBatchSize + 1 : i * miniBatchSize;
X_batch = X_train_shuffled(idxBatch, :);
Y_batch = Y_train_shuffled(idxBatch, :);
iteration = iteration + 1;
% 前向传播计算预测
Y_pred = predict(net, X_batch’);
Y_pred = Y_pred’;
Y_pred = dlarray(Y_pred, ‘TS’);
Y_batch = dlarray(Y_batch, ‘TS’);
%loss = mean(( Y_batch – Y_pred).^2, ‘all’);
[loss_1, gradients] = dlfeval(@customLoss, Y_batch, Y_pred);
gradients = extractdata(gradients);
[net, Velocities] = sgdmupdate(net, gradients, Velocities,learningRate,momentum);
% 计算损失
% loss = customLoss(Y_batch, Y_pred);
% totalLoss = totalLoss + loss;
% 反向传播更新梯度
%dL_dY = 2 * (Y_pred – Y_batch) / miniBatchSize;
%gradients = dlgradient(loss, net.LearnableParameters);
%net = updateParameters(net, gradients, learningRate);
end
% 显示每个 epoch 的平均损失
avgLoss = totalLoss / numMiniBatches;
fprintf(‘Epoch %d, Average Loss: %.4fn’, epoch, avgLoss);
end
无法执行赋值，因为此类型的变量不支持使用点进行索引。
出错 deep.internal.recording.containerfeval>iProcessNetwork_Nout_Nin (第 382 行)
protoTable.Value = zeros(height(protoTable),0);
出错 deep.internal.recording.containerfeval>iDispatch_Nout_Nin (第 214 行)
outputs = iProcessNetwork_Nout_Nin(fun, paramFun, numOut, …
出错 deep.internal.recording.containerfeval (第 38 行)
outputs = iDispatch_Nout_Nin(allowNetInput, fun, paramFun, numOut, …
出错 deep.internal.networkContainerFixedArgsFun (第 29 行)
varargout = deep.internal.recording.containerfeval(…
出错 sgdmupdate (第 126 行)
[p, vel] = deep.internal.networkContainerFixedArgsFun(func, …% 定义 LSTM 网络结构
numFeatures = size(X_train, 2); % 特征数量，这里是 3
numHiddenUnits = 100; % LSTM 隐藏单元数量
layers = [ …
sequenceInputLayer(numFeatures)
lstmLayer(numHiddenUnits)
fullyConnectedLayer(numFeatures)
];
maxEpochs = 50;
miniBatchSize = 3;
learningRate = 0.01;
% 初始化 LSTM 模型
net = dlnetwork(layers); % 在 CPU 上训练
% 训练循环
numObservations = size(X_train, 1);
numMiniBatches = floor(numObservations / miniBatchSize);
averageGrad = [];
averageSqGrad = [];
iteration = 0;
Velocities = zeros(size(net));
momentum = 0.9;
for epoch = 1:maxEpochs
% 打乱训练数据
idx = randperm(numObservations);
X_train_shuffled = X_train(idx, :);
Y_train_shuffled = Y_train(idx, :);
totalLoss = 0;
for i = 1:numMiniBatches
idxBatch = (i – 1) * miniBatchSize + 1 : i * miniBatchSize;
X_batch = X_train_shuffled(idxBatch, :);
Y_batch = Y_train_shuffled(idxBatch, :);
iteration = iteration + 1;
% 前向传播计算预测
Y_pred = predict(net, X_batch’);
Y_pred = Y_pred’;
Y_pred = dlarray(Y_pred, ‘TS’);
Y_batch = dlarray(Y_batch, ‘TS’);
%loss = mean(( Y_batch – Y_pred).^2, ‘all’);
[loss_1, gradients] = dlfeval(@customLoss, Y_batch, Y_pred);
gradients = extractdata(gradients);
[net, Velocities] = sgdmupdate(net, gradients, Velocities,learningRate,momentum);
% 计算损失
% loss = customLoss(Y_batch, Y_pred);
% totalLoss = totalLoss + loss;
% 反向传播更新梯度
%dL_dY = 2 * (Y_pred – Y_batch) / miniBatchSize;
%gradients = dlgradient(loss, net.LearnableParameters);
%net = updateParameters(net, gradients, learningRate);
end
% 显示每个 epoch 的平均损失
avgLoss = totalLoss / numMiniBatches;
fprintf(‘Epoch %d, Average Loss: %.4fn’, epoch, avgLoss);
end
无法执行赋值，因为此类型的变量不支持使用点进行索引。
出错 deep.internal.recording.containerfeval>iProcessNetwork_Nout_Nin (第 382 行)
protoTable.Value = zeros(height(protoTable),0);
出错 deep.internal.recording.containerfeval>iDispatch_Nout_Nin (第 214 行)
outputs = iProcessNetwork_Nout_Nin(fun, paramFun, numOut, …
出错 deep.internal.recording.containerfeval (第 38 行)
outputs = iDispatch_Nout_Nin(allowNetInput, fun, paramFun, numOut, …
出错 deep.internal.networkContainerFixedArgsFun (第 29 行)
varargout = deep.internal.recording.containerfeval(…
出错 sgdmupdate (第 126 行)
[p, vel] = deep.internal.networkContainerFixedArgsFun(func, … % 定义 LSTM 网络结构
numFeatures = size(X_train, 2); % 特征数量，这里是 3
numHiddenUnits = 100; % LSTM 隐藏单元数量
layers = [ …
sequenceInputLayer(numFeatures)
lstmLayer(numHiddenUnits)
fullyConnectedLayer(numFeatures)
];
maxEpochs = 50;
miniBatchSize = 3;
learningRate = 0.01;
% 初始化 LSTM 模型
net = dlnetwork(layers); % 在 CPU 上训练
% 训练循环
numObservations = size(X_train, 1);
numMiniBatches = floor(numObservations / miniBatchSize);
averageGrad = [];
averageSqGrad = [];
iteration = 0;
Velocities = zeros(size(net));
momentum = 0.9;
for epoch = 1:maxEpochs
% 打乱训练数据
idx = randperm(numObservations);
X_train_shuffled = X_train(idx, :);
Y_train_shuffled = Y_train(idx, :);
totalLoss = 0;
for i = 1:numMiniBatches
idxBatch = (i – 1) * miniBatchSize + 1 : i * miniBatchSize;
X_batch = X_train_shuffled(idxBatch, :);
Y_batch = Y_train_shuffled(idxBatch, :);
iteration = iteration + 1;
% 前向传播计算预测
Y_pred = predict(net, X_batch’);
Y_pred = Y_pred’;
Y_pred = dlarray(Y_pred, ‘TS’);
Y_batch = dlarray(Y_batch, ‘TS’);
%loss = mean(( Y_batch – Y_pred).^2, ‘all’);
[loss_1, gradients] = dlfeval(@customLoss, Y_batch, Y_pred);
gradients = extractdata(gradients);
[net, Velocities] = sgdmupdate(net, gradients, Velocities,learningRate,momentum);
% 计算损失
% loss = customLoss(Y_batch, Y_pred);
% totalLoss = totalLoss + loss;
% 反向传播更新梯度
%dL_dY = 2 * (Y_pred – Y_batch) / miniBatchSize;
%gradients = dlgradient(loss, net.LearnableParameters);
%net = updateParameters(net, gradients, learningRate);
end
% 显示每个 epoch 的平均损失
avgLoss = totalLoss / numMiniBatches;
fprintf(‘Epoch %d, Average Loss: %.4fn’, epoch, avgLoss);
end
无法执行赋值，因为此类型的变量不支持使用点进行索引。
出错 deep.internal.recording.containerfeval>iProcessNetwork_Nout_Nin (第 382 行)
protoTable.Value = zeros(height(protoTable),0);
出错 deep.internal.recording.containerfeval>iDispatch_Nout_Nin (第 214 行)
outputs = iProcessNetwork_Nout_Nin(fun, paramFun, numOut, …
出错 deep.internal.recording.containerfeval (第 38 行)
outputs = iDispatch_Nout_Nin(allowNetInput, fun, paramFun, numOut, …
出错 deep.internal.networkContainerFixedArgsFun (第 29 行)
varargout = deep.internal.recording.containerfeval(…
出错 sgdmupdate (第 126 行)
[p, vel] = deep.internal.networkContainerFixedArgsFun(func, … sgdmupdate, deeplearning, lstm, dlarray MATLAB Answers — New Questions
