So I have my X_Train data as 5000×800 . Each column represent 1 second of time and each row represent a time stance which means i have 5000 time instances in each second.. for my Y_Train I have 800×1 labels, (for binary classification) each given label is for 1 second of data. Now the problem is I am contiously getting errors of mismatch in predictions and target 5000(T) and (800T). Each second is a single channel with 5000 instances, so i have to enter it in this format each input 1 channel(1second) with 5000 instances and the label has to match. I am using 1D Conv layer and SequenceInputLayer. Please help me how I can reshape my data or take input dimensions?So I have my X_Train data as 5000×800 . Each column represent 1 second of time and each row represent a time stance which means i have 5000 time instances in each second.. for my Y_Train I have 800×1 labels, (for binary classification) each given label is for 1 second of data. Now the problem is I am contiously getting errors of mismatch in predictions and target 5000(T) and (800T). Each second is a single channel with 5000 instances, so i have to enter it in this format each input 1 channel(1second) with 5000 instances and the label has to match. I am using 1D Conv layer and SequenceInputLayer. Please help me how I can reshape my data or take input dimensions? So I have my X_Train data as 5000×800 . Each column represent 1 second of time and each row represent a time stance which means i have 5000 time instances in each second.. for my Y_Train I have 800×1 labels, (for binary classification) each given label is for 1 second of data. Now the problem is I am contiously getting errors of mismatch in predictions and target 5000(T) and (800T). Each second is a single channel with 5000 instances, so i have to enter it in this format each input 1 channel(1second) with 5000 instances and the label has to match. I am using 1D Conv layer and SequenceInputLayer. Please help me how I can reshape my data or take input dimensions? sequence layer input, 1d cnn MATLAB Answers — New Questions

​