Deep Learning Toolbox - Normalising a Cell prior to LSTM Training

3 visualizaciones (últimos 30 días)
PB75
PB75 el 6 de Sept. de 2022
Respondida: Siraj el 6 de Sept. de 2023
Hi All,
I am attempting to normalise my training data it improve the performance of the LSTM network.
The data is collected in 10 ANSYS simulations, so 10 observations, with 5 input states (dataTrain) and 4 output states.
The code partitions the train data (90% Train 10% Test). I would like to normalise the 5 signals contained in the dataTrain cell array (1x9 cell) where each individual erray is a 5x324 double (5 signal, volume, temp, pressure, CO2, and NO each with 324 steps).
Step 1.
I have attemped to first compute the maximum value of each signal contained in the 1x9 cell, my code does find a value, however, it seems to find the last indexed value (of the 9 arrays in the cell). Which does not make sense as the values should numerically decrease from array 1 to array 9, as shown below, so my code is at fault. As an example, below shows the max pressure values returned in the arrays (and not in numerical order as they should) and the computed maximum pressure from the cell.
%Normalise the Signals contained in dataTrain cell (1x9 cell) prior to extracting predictors and targets??
for i = 1:numObservationsTrain % Find the Max value of each individual signal in the dataTrain cell
volume_max = max(dataTrain{i}(1,:));
temperature_max = max(dataTrain{i}(2,:));
pressure_max = max(dataTrain{i}(3,:))
CO2_max = max(dataTrain{i}(4,:));
NO_max = max(dataTrain{i}(5,:));
end
Step 2.
Then I attempt to index in and norm each signal (row) in the cell using the computed maximum signal value, but again the code flags an error. See below code.
for i = 1:numObservationsTrain % Normalise each signal in each array in the dataTrain cell with max value computed above
dataTrain{i} = dataTrain{i}(1,:) ./ volume_max;
dataTrain{i} = dataTrain{i}(2,:) ./ temperature_max;
dataTrain{i} = dataTrain{i}(3,:) ./ pressure_max;
dataTrain{i} = dataTrain{i}(4,:) ./ CO2_max;
dataTrain{i} = dataTrain{i}(5,:) ./ NO_max;
end
Please forgive the schoolboy questions, this is the first time I have attempted to train an LSTM network with real-time data. Any suggestions as to how to mind the max and norm each signal within the 1x9 cell would be great.
Thanks in advance,
Patrick

Iniciar sesión para responder a esta pregunta.

Respuestas (1)

Siraj
Siraj el 6 de Sept. de 2023
Ran in:
Hi! It is my understanding that you have the training data, which is a cell array that contains 9 matrices, each with dimensions 5x324.
To normalize each row of these matrices individually without altering the overall structure of the data, iterate over each matrix in the cell array, normalize the rows of each matrix, and store the normalized matrices back into the cell array.
Refer to the example code below for better understanding.
%generating random data.
dataTrain = cell(1,9);
for i = 1 : size(dataTrain,2)
%creating 5 signals with 324 steps.
dataTrain{i} = randi([1 100], 5,324);
end
disp("Before Normalization");
Before Normalization
disp(dataTrain{1});
Columns 1 through 33 61 57 58 32 97 83 59 17 32 62 93 13 48 20 65 68 14 62 93 67 89 95 95 2 88 53 88 18 56 80 67 23 71 95 67 3 70 20 79 36 77 61 69 2 89 97 22 53 88 83 50 97 2 16 51 85 12 44 74 13 77 70 62 92 14 95 96 48 99 9 35 86 32 96 27 90 67 13 23 68 46 97 11 99 86 35 73 40 98 49 61 64 9 34 37 6 57 52 8 57 47 52 5 57 8 24 47 2 76 73 44 57 68 48 18 77 22 79 21 67 76 55 11 38 15 78 39 84 65 50 76 20 38 31 79 1 17 56 5 52 29 82 88 48 52 16 81 80 60 15 86 70 81 60 50 71 72 4 16 97 24 47 18 21 37 Columns 34 through 66 100 15 96 72 89 30 98 3 93 10 46 64 94 5 87 84 18 58 70 82 37 39 85 3 56 56 23 53 64 88 45 42 3 73 13 60 37 91 76 96 48 8 84 5 67 96 100 94 37 21 51 38 13 42 96 18 8 19 28 97 17 19 59 51 4 31 23 45 88 36 17 25 84 74 53 11 45 95 77 39 90 67 81 33 52 57 86 35 88 44 83 33 24 89 42 16 77 81 60 11 51 39 3 99 19 7 90 24 95 1 65 46 83 60 97 89 27 91 75 75 64 75 90 57 73 91 79 42 47 56 6 68 32 95 86 42 91 57 50 76 22 76 100 34 93 97 91 93 71 90 85 37 8 5 3 29 73 58 90 67 76 62 4 29 27 Columns 67 through 99 99 34 23 78 15 47 81 3 92 51 21 72 28 49 4 37 86 97 41 31 14 58 12 8 20 74 64 78 73 86 34 47 55 25 35 99 21 86 39 68 88 46 34 94 33 63 24 26 54 23 5 96 38 99 90 84 72 9 11 95 66 31 80 21 24 18 18 27 87 58 81 12 57 12 2 91 37 1 42 51 11 36 6 78 84 76 1 32 12 5 57 58 69 65 67 1 90 48 55 75 50 51 54 77 18 84 78 53 77 77 73 95 2 29 34 15 30 31 53 65 99 19 77 96 88 11 79 51 74 87 76 90 61 12 75 62 32 64 92 100 93 20 94 42 27 75 84 16 95 91 55 58 90 77 81 89 19 80 90 57 53 52 39 89 92 Columns 100 through 132 19 98 37 99 42 76 1 24 2 69 40 12 11 83 68 8 46 49 37 94 64 94 64 28 17 54 1 58 46 34 34 81 29 59 34 93 88 60 45 64 9 18 39 60 83 6 66 37 92 23 40 53 24 95 28 87 8 87 78 80 29 84 91 58 17 70 53 72 86 96 10 40 57 96 45 62 63 27 39 69 57 25 90 37 93 79 56 28 34 21 89 83 30 73 55 70 53 92 63 69 25 95 72 16 23 75 21 16 67 6 69 74 50 69 47 2 53 25 42 93 3 60 41 21 34 1 37 27 89 31 14 99 100 79 35 67 67 100 90 74 93 1 23 67 39 41 86 35 38 59 43 83 78 39 29 26 70 68 45 92 35 48 89 52 61 Columns 133 through 165 82 17 50 83 3 48 85 27 100 48 84 38 68 75 83 93 24 97 63 79 13 54 40 21 96 11 23 27 13 100 48 62 48 10 93 84 99 93 88 11 98 100 87 20 27 90 80 68 29 8 62 52 37 57 70 79 43 39 14 60 47 87 9 79 43 65 1 6 79 6 27 100 75 14 68 44 2 22 82 54 13 15 48 95 29 9 73 2 80 17 45 7 70 91 84 71 75 63 91 11 27 49 96 12 14 21 9 72 74 57 39 64 58 24 23 61 51 83 40 10 78 93 69 96 22 60 19 14 17 98 79 81 15 86 53 28 53 48 21 72 33 18 6 10 90 62 84 3 34 63 100 32 50 21 55 82 98 31 16 11 94 11 86 1 90 Columns 166 through 198 46 72 4 10 87 47 18 67 61 22 72 61 73 69 77 87 27 40 9 61 51 52 39 84 95 69 73 43 20 63 63 76 12 100 79 40 3 17 99 6 61 33 30 50 59 14 9 34 44 27 17 94 91 78 17 66 6 42 80 19 80 5 27 29 62 85 23 52 6 28 64 13 3 6 18 24 33 76 70 100 21 9 59 82 6 87 46 18 91 33 5 94 78 96 6 77 66 30 78 100 99 41 62 17 80 69 47 13 82 82 83 94 38 91 32 85 68 41 38 13 73 75 46 35 15 71 30 7 63 40 8 48 51 3 82 95 46 7 9 22 58 30 86 18 83 45 47 66 36 50 75 79 83 91 3 6 95 40 53 61 12 40 88 95 31 Columns 199 through 231 83 17 49 32 26 68 29 81 74 75 15 10 79 18 58 59 77 40 66 64 63 80 48 94 43 73 68 60 29 94 10 93 10 89 3 3 19 48 55 82 65 96 39 57 96 42 44 8 3 68 79 91 15 16 95 41 43 91 93 66 93 83 46 30 42 16 33 3 93 2 5 33 62 50 51 60 11 96 19 58 60 23 56 100 11 82 25 28 13 87 39 62 90 59 1 64 98 93 66 76 6 46 90 70 77 53 33 88 77 94 71 41 93 18 57 11 66 61 70 35 81 57 31 6 58 80 55 37 69 61 63 33 75 43 14 41 80 60 13 85 21 5 83 70 74 23 53 82 89 56 46 51 40 100 11 75 6 84 99 50 39 6 30 58 17 Columns 232 through 264 53 16 84 75 41 7 77 37 3 74 45 57 36 99 63 28 79 49 95 79 51 64 64 21 12 53 95 67 43 41 65 2 4 84 21 96 89 91 71 67 83 90 93 64 30 78 91 98 90 66 61 35 66 17 69 76 55 57 76 89 3 22 75 96 11 49 56 3 28 49 17 22 89 12 34 57 78 80 99 85 2 86 87 54 15 22 28 17 40 2 1 16 14 52 24 60 95 21 93 69 54 32 59 10 28 41 53 53 68 100 84 94 7 9 79 29 89 68 13 66 62 58 5 29 14 12 50 46 78 63 27 8 28 70 89 96 12 97 81 16 100 47 40 28 19 78 34 25 19 5 50 55 20 46 22 23 2 80 43 16 18 93 21 73 67 Columns 265 through 297 35 42 77 42 30 44 13 34 39 52 79 76 10 100 7 43 83 5 44 86 24 69 92 88 53 14 75 24 16 6 19 45 10 63 97 16 30 17 27 87 27 74 19 68 96 34 45 18 12 37 97 72 63 84 90 20 49 19 88 38 7 79 73 36 62 30 50 22 53 47 16 73 67 64 43 81 82 50 72 48 49 64 79 54 52 48 69 55 31 94 16 32 41 100 45 13 43 36 72 53 78 34 40 47 55 72 35 91 60 58 28 58 30 74 84 32 12 77 10 47 15 100 81 42 38 44 16 35 66 35 10 49 36 45 53 51 25 31 90 92 52 24 20 52 6 93 12 73 19 45 60 14 67 63 76 43 95 53 6 55 63 32 1 69 15 Columns 298 through 324 59 23 80 63 33 25 68 55 75 8 91 95 77 94 46 8 8 61 24 59 88 7 83 88 84 63 1 5 70 57 27 84 63 62 76 12 81 76 38 98 72 34 18 56 34 52 78 85 29 65 25 15 64 68 15 87 5 31 9 57 35 13 56 95 75 78 52 19 54 65 80 98 88 65 3 47 18 53 18 45 43 80 97 30 42 1 32 32 62 75 12 53 37 21 74 21 8 56 89 26 13 84 75 26 8 10 15 91 90 17 88 57 34 76 21 2 1 53 63 76 64 99 21 70 39 53 47 46 60 28 5 79 24 54 81
%Normalizing the training data.
for i = 1 : size(dataTrain,2)
%creating 5 signals with 324 steps.
raw_data = dataTrain{i};
normalized_data = normalize(raw_data,2,"range");
dataTrain{i} = normalized_data;
end
disp("After Normalization");
After Normalization
disp(dataTrain{1});
Columns 1 through 19 0.6061 0.5657 0.5758 0.3131 0.9697 0.8283 0.5859 0.1616 0.3131 0.6162 0.9293 0.1212 0.4747 0.1919 0.6465 0.6768 0.1313 0.6162 0.9293 0.9490 0.6633 0.0102 0.6939 0.1837 0.7857 0.3469 0.7653 0.6020 0.6837 0 0.8878 0.9694 0.2041 0.5204 0.8776 0.8265 0.4898 0.9694 0.9596 0.4747 0.9899 0.0808 0.3434 0.8586 0.3131 0.9596 0.2626 0.8990 0.6667 0.1212 0.2222 0.6768 0.4545 0.9697 0.1010 0.9899 0.8586 0.5657 0.4646 0.5152 0.0404 0.5657 0.0707 0.2323 0.4646 0.0101 0.7576 0.7273 0.4343 0.5657 0.6768 0.4747 0.1717 0.7677 0.2121 0.7879 0.3737 0.3030 0.7879 0 0.1616 0.5556 0.0404 0.5152 0.2828 0.8182 0.8788 0.4747 0.5152 0.1515 0.8081 0.7980 0.5960 0.1414 0.8586 Columns 20 through 38 0.6667 0.8889 0.9495 0.9495 0.0101 0.8788 0.5253 0.8788 0.1717 0.5556 0.7980 0.6667 0.2222 0.7071 1.0000 0.1414 0.9596 0.7172 0.8889 0 0.1429 0.5000 0.8469 0.1020 0.4286 0.7347 0.1122 0.7653 0.6939 0.6122 0.9184 0.1224 0.9490 0.7245 0.1122 0.5918 0.3571 0.9082 0.3434 0.7273 0.3939 0.9798 0.4848 0.6061 0.6364 0.0808 0.3333 0.3636 0.0505 0.5657 0.5152 0.0707 0.2222 0.4444 0.8788 0.3535 0.1616 0.2020 0.6667 0.7576 0.5455 0.1010 0.3737 0.1414 0.7778 0.3838 0.8384 0.6465 0.4949 0.7576 0.1919 0.1010 0.5051 0.3838 0.0202 0.9899 0.6970 0.8081 0.5960 0.4949 0.7071 0.7172 0.0303 0.1515 0.9697 0.2323 0.4646 0.1717 0.2020 0.3636 0.3131 0.9495 0.8586 0.4141 0.9091 Columns 39 through 57 0.2929 0.9798 0.0202 0.9293 0.0909 0.4545 0.6364 0.9394 0.0404 0.8687 0.8384 0.1717 0.5758 0.6970 0.8182 0.3636 0.3838 0.8485 0.0202 0.7551 0.9592 0.4694 0.0612 0.8367 0.0306 0.6633 0.9592 1.0000 0.9388 0.3571 0.1939 0.5000 0.3673 0.1122 0.4082 0.9592 0.1633 0.0612 0.2424 0.8384 0.7374 0.5253 0.1010 0.4444 0.9495 0.7677 0.3838 0.8990 0.6667 0.8081 0.3232 0.5152 0.5657 0.8586 0.3434 0.8788 0.4343 0.1818 0.0606 0.8990 0.2323 0.9495 0 0.6465 0.4545 0.8283 0.5960 0.9697 0.8889 0.2626 0.9091 0.7475 0.7475 0.6364 0.7475 0.8990 0.5657 0.4949 0.7576 0.2121 0.7576 1.0000 0.3333 0.9293 0.9697 0.9091 0.9293 0.7071 0.8990 0.8485 0.3636 0.0707 0.0404 0.0202 0.2828 Columns 58 through 76 0.5556 0.5556 0.2222 0.5253 0.6364 0.8788 0.4444 0.4141 0.0202 0.9899 0.3333 0.2222 0.7778 0.1414 0.4646 0.8081 0.0202 0.9192 0.5051 0.1735 0.2653 0.9694 0.1531 0.1735 0.5816 0.5000 0.0204 0.2959 0.2347 0.3367 0.9898 0.1939 0.8571 0.3776 0.6735 0.8776 0.4490 0.3265 0.8283 0.3232 0.2323 0.8889 0.4141 0.1515 0.7677 0.8081 0.5960 0.1717 0.2626 0.8687 0.5758 0.8081 0.1111 0.5657 0.1111 0.0101 0.9091 0.5657 0.7273 0.9091 0.7879 0.4141 0.4646 0.5556 0.0505 0.6768 0.7475 0.4949 0.5051 0.5354 0.7677 0.1717 0.8384 0.7778 0.5253 0.7677 0.7273 0.5758 0.8990 0.6667 0.7576 0.6162 0.0303 0.2828 0.2626 0.6061 0.1111 0.7475 0.6162 0.3131 0.6364 0.9192 1.0000 0.9293 0.1919 Columns 77 through 95 0.2020 0.7172 0.2727 0.4848 0.0303 0.3636 0.8586 0.9697 0.4040 0.3030 0.1313 0.5758 0.1111 0.0707 0.1919 0.7374 0.6364 0.7778 0.7273 0.9388 0.3163 0.6224 0.2245 0.2449 0.5306 0.2143 0.0306 0.9592 0.3673 0.9898 0.8980 0.8367 0.7143 0.0714 0.0918 0.9490 0.6531 0.2959 0.3636 0 0.4141 0.5051 0.1010 0.3535 0.0505 0.7778 0.8384 0.7576 0 0.3131 0.1111 0.0404 0.5657 0.5758 0.6869 0.6465 0.6667 0.7677 0.7273 0.9495 0.0101 0.2828 0.3333 0.1414 0.2929 0.3030 0.5253 0.6465 0.9899 0.1818 0.7677 0.9596 0.8788 0.1010 0.7879 0.5051 0.9394 0.4141 0.2626 0.7475 0.8384 0.1515 0.9495 0.9091 0.5455 0.5758 0.8990 0.7677 0.8081 0.8889 0.1818 0.7980 0.8990 0.5657 0.5253 Columns 96 through 114 0.8586 0.3333 0.4646 0.5455 0.1818 0.9798 0.3636 0.9899 0.4141 0.7576 0 0.2323 0.0101 0.6869 0.3939 0.1111 0.1010 0.8283 0.6768 0.7959 0.1939 0.2245 0.1633 0.5816 0.3265 0.9286 0.8776 0.5918 0.4388 0.6327 0.0714 0.1633 0.3776 0.5918 0.8265 0.0408 0.6531 0.3571 0 0.8990 0.4747 0.5455 0.5253 0.7172 0.8586 0.9596 0.0909 0.3939 0.5657 0.9596 0.4444 0.6162 0.6263 0.2626 0.3838 0.6869 0.5657 0.7374 0.8687 0.7576 0.8990 0.6869 0.2424 0.9495 0.7172 0.1515 0.2222 0.7475 0.2020 0.1515 0.6667 0.0505 0.6869 0.7374 0.4949 0.6869 0.5152 0.3838 0.8889 0.9192 1.0000 0.7879 0.3434 0.6667 0.6667 1.0000 0.8990 0.7374 0.9293 0 0.2222 0.6667 0.3838 0.4040 0.8586 Columns 115 through 133 0.0707 0.4545 0.4848 0.3636 0.9394 0.6364 0.9394 0.6364 0.2727 0.1616 0.5354 0 0.5758 0.4545 0.3333 0.3333 0.8081 0.2828 0.8182 0.9184 0.2143 0.3878 0.5204 0.2245 0.9490 0.2653 0.8673 0.0612 0.8673 0.7755 0.7959 0.2755 0.8367 0.9082 0.5714 0.1531 0.6939 0.0816 0.2424 0.8990 0.3636 0.9293 0.7879 0.5556 0.2727 0.3333 0.2020 0.8889 0.8283 0.2929 0.7273 0.5455 0.6970 0.5253 0.9192 0.6263 0 0.4646 0.0101 0.5253 0.2424 0.4141 0.9293 0.0202 0.5960 0.4040 0.2020 0.3333 0 0.3636 0.2626 0.8889 0.3030 0.1313 0.9899 0.1010 0.3434 0.3737 0.5859 0.4242 0.8283 0.7778 0.3838 0.2828 0.2525 0.6970 0.6768 0.4444 0.9192 0.3434 0.4747 0.8889 0.5152 0.6061 0.1414 Columns 134 through 152 0.1616 0.4949 0.8283 0.0202 0.4747 0.8485 0.2626 1.0000 0.4747 0.8384 0.3737 0.6768 0.7475 0.8283 0.9293 0.2323 0.9697 0.6263 0.7879 0.9286 0.8367 0.9898 0.9286 0.8776 0.0918 0.9796 1.0000 0.8673 0.1837 0.2551 0.8980 0.7959 0.6735 0.2755 0.0612 0.6122 0.5102 0.3571 0.0505 0.7879 0.0505 0.2626 1.0000 0.7475 0.1313 0.6768 0.4343 0.0101 0.2121 0.8182 0.5354 0.1212 0.1414 0.4747 0.9495 0.2828 0.0808 0.2626 0.4848 0.9596 0.1111 0.1313 0.2020 0.0808 0.7172 0.7374 0.5657 0.3838 0.6364 0.5758 0.2323 0.2222 0.6061 0.5051 0.8283 0.3939 0.8586 0.5253 0.2727 0.5253 0.4747 0.2020 0.7172 0.3232 0.1717 0.0505 0.0909 0.8990 0.6162 0.8384 0.0202 0.3333 0.6263 1.0000 0.3131 Columns 153 through 171 0.1212 0.5354 0.3939 0.2020 0.9596 0.1010 0.2222 0.2626 0.1212 1.0000 0.4747 0.6162 0.4747 0.4545 0.7172 0.0303 0.0909 0.8687 0.4646 0.5612 0.6939 0.7857 0.4184 0.3776 0.1224 0.5918 0.4592 0.8673 0.0714 0.7857 0.4184 0.6429 1.0000 0.7857 0.3878 0.0102 0.1531 0.9898 0.7273 0.0101 0.7980 0.1616 0.4444 0.0606 0.6970 0.9091 0.8384 0.7071 0.7475 0.6263 0.9091 0.2222 0.5152 0.0505 0.2727 0.6364 0.1212 0.0909 0.7778 0.9293 0.6869 0.9596 0.2121 0.5960 0.1818 0.1313 0.1616 0.9798 0.7879 0.8081 1.0000 0.9899 0.4040 0.6162 0.1616 0.7980 0.4949 0.2020 0.5455 0.8182 0.9798 0.3030 0.1515 0.1010 0.9394 0.1010 0.8586 0 0.8990 0.5051 0.0202 0.8182 0.9495 0.4545 0.0606 Columns 172 through 190 0.1717 0.6667 0.6061 0.2121 0.7172 0.6061 0.7273 0.6869 0.7677 0.8687 0.2626 0.3939 0.0808 0.6061 0.5051 0.5152 0.3838 0.8384 0.9495 0.0408 0.6020 0.3163 0.2857 0.4898 0.5816 0.1224 0.0714 0.3265 0.4286 0.2551 0.1531 0.9388 0.9082 0.7755 0.1531 0.6531 0.0408 0.4082 0.0202 0.0505 0.1717 0.2323 0.3232 0.7576 0.6970 1.0000 0.2020 0.0808 0.5859 0.8182 0.0505 0.8687 0.4545 0.1717 0.9091 0.3232 0.0404 0.6869 0.4646 0.1212 0.8182 0.8182 0.8283 0.9394 0.3737 0.9091 0.3131 0.8485 0.6768 0.4040 0.3737 0.1212 0.7273 0.7475 0.4545 0.3434 0.0808 0.2121 0.5758 0.2929 0.8586 0.1717 0.8283 0.4444 0.4646 0.6566 0.3535 0.4949 0.7475 0.7879 0.8283 0.9091 0.0202 0.0505 0.9495 Columns 191 through 209 0.6869 0.7273 0.4242 0.1919 0.6263 0.6263 0.7576 0.1111 0.8283 0.1616 0.4848 0.3131 0.2525 0.6768 0.2828 0.8081 0.7374 0.7475 0.1414 0.7959 0.1735 0.7959 0.0306 0.2551 0.2755 0.6122 0.8469 0.8878 0.0102 0.0102 0.1735 0.4694 0.5408 0.8163 0.6429 0.9592 0.3776 0.5612 0.9394 0.7778 0.9596 0.0505 0.7677 0.6566 0.2929 0.7778 0.3232 0.0202 0.9293 0.0101 0.0404 0.3232 0.6162 0.4949 0.5051 0.5960 0.1010 0.1414 0.7071 0.2929 0.0606 0.6263 0.3939 0.0707 0.4747 0.7576 0.0505 0.4545 0.8990 0.6970 0.7677 0.5253 0.3232 0.8788 0.7677 0.9394 0.3939 0.5253 0.6061 0.1111 0.3939 0.8788 0.9495 0.3030 0.7475 0.4242 0.1313 0.4040 0.7980 0.5960 0.1212 0.8485 0.2020 0.0404 0.8283 Columns 210 through 228 0.0909 0.7879 0.1717 0.5758 0.5859 0.7677 0.3939 0.6566 0.6364 0.6263 0.7980 0.4747 0.9394 0.4242 0.7273 0.6768 0.5960 0.2828 0.9394 0.9592 0.4082 0.4286 0.0612 0.0102 0.6735 0.7857 0.9082 0.1327 0.1429 0.9490 0.3980 0.4184 0.9082 0.9286 0.6531 0.9286 0.8265 0.4490 0.9596 0.1818 0.5758 0.5960 0.2222 0.5556 1.0000 0.1010 0.8182 0.2424 0.2727 0.1212 0.8687 0.3838 0.6162 0.8990 0.5859 0 0.6364 0.7071 0.4040 0.9293 0.1717 0.5657 0.1010 0.6566 0.6061 0.6970 0.3434 0.8081 0.5657 0.3030 0.0505 0.5758 0.7980 0.5455 0.3636 0.6869 0.6970 0.7374 0.2222 0.5253 0.8182 0.8889 0.5556 0.4545 0.5051 0.3939 1.0000 0.1010 0.7475 0.0505 0.8384 0.9899 0.4949 0.3838 0.0505 Columns 229 through 247 0.0909 0.9293 0.0909 0.5253 0.1515 0.8384 0.7475 0.4040 0.0606 0.7677 0.3636 0.0202 0.7374 0.4444 0.5657 0.3535 0.9899 0.6263 0.2727 0.2857 0.4082 0.1429 0.8367 0.1939 0.9592 0.8878 0.9082 0.7041 0.6633 0.8265 0.8980 0.9286 0.6327 0.2857 0.7755 0.9082 0.9796 0.8980 0.9798 0.9293 0.6566 0.5556 0.0202 0.2727 0.4848 0.1616 0.2121 0.8889 0.1111 0.3333 0.5657 0.7778 0.7980 0.9899 0.8485 0.0101 0.8586 0.6061 0.6263 0.3232 0.6869 0.5354 0.3131 0.5859 0.0909 0.2727 0.4040 0.5253 0.5253 0.6768 1.0000 0.8384 0.9394 0.0606 0.0808 0.7879 0.2929 0.5758 0.1616 0.2727 0.6970 0.8889 0.9596 0.1111 0.9697 0.8081 0.1515 1.0000 0.4646 0.3939 0.2727 0.1818 0.7778 0.3333 0.2424 Columns 248 through 266 0.7879 0.4848 0.9495 0.7879 0.5051 0.6364 0.6364 0.2020 0.1111 0.5253 0.9495 0.6667 0.4242 0.4040 0.6465 0.0101 0.0303 0.3434 0.4141 0.6531 0.6020 0.3367 0.6531 0.1531 0.6837 0.7551 0.5408 0.5612 0.7551 0.8878 0.0102 0.2041 0.7449 0.9592 0.0918 0.4796 0.6224 0.9694 0.8687 0.5354 0.1414 0.2121 0.2727 0.1616 0.3939 0.0101 0 0.1515 0.1313 0.5152 0.2323 0.5960 0.9495 0.2020 0.9293 0.4949 0.2121 0.2828 0.8889 0.6768 0.1212 0.6566 0.6162 0.5758 0.0404 0.2828 0.1313 0.1111 0.4949 0.4545 0.7778 0.6263 0.2626 0.0707 0.5253 0.7778 0.1818 0.0404 0.4949 0.5455 0.1919 0.4545 0.2121 0.2222 0.0101 0.7980 0.4242 0.1515 0.1717 0.9293 0.2020 0.7273 0.6667 0.3535 0.4444 Columns 267 through 285 0.7677 0.4141 0.2929 0.4343 0.1212 0.3333 0.3838 0.5152 0.7879 0.7576 0.0909 1.0000 0.0606 0.4242 0.8283 0.0404 0.4343 0.8586 0.2323 0.1429 0.2857 0.1531 0.2551 0.8673 0.2551 0.7347 0.1735 0.6735 0.9592 0.3265 0.4388 0.1633 0.1020 0.3571 0.9694 0.7143 0.6224 0.8367 0.5253 0.4646 0.1515 0.7273 0.6667 0.6364 0.4242 0.8081 0.8182 0.4949 0.7172 0.4747 0.4848 0.6364 0.7879 0.5354 0.5152 0.4747 0.6869 0.3333 0.3939 0.4646 0.5455 0.7172 0.3434 0.9091 0.5960 0.5758 0.2727 0.5758 0.2929 0.7374 0.8384 0.3131 0.1111 0.7677 0.0909 0.4646 0.5253 0.5051 0.2424 0.3030 0.8990 0.9192 0.5152 0.2323 0.1919 0.5152 0.0505 0.9293 0.1111 0.7273 0.1818 0.4444 0.5960 0.1313 0.6667 Columns 286 through 304 0.6869 0.9192 0.8788 0.5253 0.1313 0.7475 0.2323 0.1515 0.0505 0.1818 0.4444 0.0909 0.5859 0.2222 0.7980 0.6263 0.3232 0.2424 0.6768 0.8980 0.1837 0.4796 0.1735 0.8776 0.3673 0.0510 0.7857 0.7245 0.3469 0.6122 0.2857 0.0306 0.6939 0.5612 0.2551 0.8367 0.6224 0.6122 0.5455 0.3030 0.9394 0.1515 0.3131 0.4040 1.0000 0.4444 0.1212 0.4242 0.3535 0.7172 0.1414 0.8687 0.0404 0.3030 0.0808 0.5657 0.3434 0.1414 1.0000 0.8081 0.4141 0.3737 0.4343 0.1515 0.3434 0.6566 0.3434 0.0909 0.4848 0.7980 0.9697 0.2929 0.4141 0 0.3131 0.3131 0.6263 0.7576 0.4242 0.9495 0.5253 0.0505 0.5455 0.6263 0.3131 0 0.6869 0.1414 0.8990 0.1616 0.8788 0.5657 0.3333 0.7576 0.2020 Columns 305 through 323 0.5455 0.7475 0.0707 0.9091 0.9495 0.7677 0.9394 0.4545 0.0707 0.0707 0.6061 0.2323 0.5859 0.8788 0.0606 0.8283 0.8788 0.8384 0.6263 0.7551 0.1020 0.8061 0.7551 0.3673 0.9796 0.7143 0.3265 0.1633 0.5510 0.3265 0.5102 0.7755 0.8469 0.2755 0.6429 0.2347 0.1327 0.6327 0.1212 0.5556 0.9495 0.7475 0.7778 0.5152 0.1818 0.5354 0.6465 0.7980 0.9798 0.8788 0.6465 0.0202 0.4646 0.1717 0.5253 0.1717 0.4444 0.6162 0.7475 0.1111 0.5253 0.3636 0.2020 0.7374 0.2020 0.0707 0.5556 0.8889 0.2525 0.1212 0.8384 0.7475 0.2525 0.0707 0.0909 0.1414 0.0101 0 0.5253 0.6263 0.7576 0.6364 0.9899 0.2020 0.6970 0.3838 0.5253 0.4646 0.4545 0.5960 0.2727 0.0404 0.7879 0.2323 0.5354 Column 324 0 0.6735 0.4242 0.9091 0.8081
To learn about the "normalize" function and its different parameter options, please refer to the link provided below. It will provide detailed information on how to use the "normalize" function with different parameter settings to achieve different types of normalization.
https://www.mathworks.com/help/matlab/ref/double.normalize.html
Hope this helps.

Categorías

Más información sobre Deep Learning Toolbox en Help Center y File Exchange.

Etiquetas

Productos


Versión

R2022a

Community Treasure Hunt

Find the treasures in MATLAB Central and discover how the community can help you!

Start Hunting!

Translated by