You can extract the data from the surface waves by removing extra points before and after. You can find the Extract Signals option in the Region of Interest section.

TASK
Extract the selected region from the harp, pax, and wanc signals. Make sure that the extracted signals are named harp_ROI, pax_ROI, and wanc_ROI respectively and display them.

Error I’m getting:
Have all three signals been cropped?You can extract the data from the surface waves by removing extra points before and after. You can find the Extract Signals option in the Region of Interest section.

TASK
Extract the selected region from the harp, pax, and wanc signals. Make sure that the extracted signals are named harp_ROI, pax_ROI, and wanc_ROI respectively and display them.

Error I’m getting:
Have all three signals been cropped? You can extract the data from the surface waves by removing extra points before and after. You can find the Extract Signals option in the Region of Interest section.

TASK
Extract the selected region from the harp, pax, and wanc signals. Make sure that the extracted signals are named harp_ROI, pax_ROI, and wanc_ROI respectively and display them.

Error I’m getting:
Have all three signals been cropped? signal processing, matlab MATLAB Answers — New Questions

​

Please help me I am new to Matlab and Aspen Plus but have basic knowledge so please guide in detail. Please tell me what steps do I follow to link Aspen file and Matlab.
The Matlab cod file is:
%% Created by Ing. Andrés Felipe Abril. Universidad Nacional de Colombia. Departamento de Ingeniería Química.
%% Linking
Aspen = actxserver(‘Apwn.Document.36.0’); %34.0 —> V8.8; 35.0 —> V9.0; and 36.0 —> V10.0
[stat,mess]=fileattrib; % get attributes of folder (Necessary to establish the location of the simulation)
Simulation_Name = ‘Reactive_Distillation’;% Aspeen Plus Simulation Name
Aspen.invoke(‘InitFromArchive2’,[mess.Name ” Simulation_Name ‘.bkp’]);
Aspen.Visible = 1; % 1 —> Aspen is Visible; 0 —> Aspen is open but not visible
Aspen.SuppressDialogs = 1; % Suppress windows dialogs.
Aspen.Engine.Run2(1); % Run the simulation
while Aspen.Engine.IsRunning == 1 % 1 –> If Aspen is running; 0 —> If Aspen stop.
pause(0.5);
end

%% Example of Application
Reflux_Ratio = [1, 3, 5, 7];
for i = 1:length(Reflux_Ratio)
Aspen.Tree.FindNode("DataBlocksRC-101InputBASIS_RR").Value = Reflux_Ratio(i); % Column Reflux
Aspen.Reinit; % Reinit simulation
Aspen.Engine.Run2(1); %Run the simulation. (1) —> Matlab isnt busy; (0) Matlab is Busy;
time = 1;
while Aspen.Engine.IsRunning == 1 % 1 –> If Aspen is running; 0 —> If Aspen stop.
pause(0.5);
time = time+1;
if time==15 % Control of simulation time.
Aspen.Engine.Stop;
end
end
Simulation_Convergency = Aspen.Tree.FindNode("DataResults SummaryRun-StatusOutputPCESSTAT").Value; % 1 Doesn’t Convergence; 0 Converge
if Simulation_Convergency == 0 && time < 10
Duty(i) = Aspen.Tree.FindNode("DataBlocksRC-101OutputREB_UTL_DUTY").Value; %Duty value of reactive column
else
Duty(i) = inf; % Its Penalized if simulation doesn’t converge;

end
end
%% Plotting
figure()
plot(Reflux_Ratio, Duty, ‘ok’);
Aspen.Close;
Aspen.Quit;Please help me I am new to Matlab and Aspen Plus but have basic knowledge so please guide in detail. Please tell me what steps do I follow to link Aspen file and Matlab.
The Matlab cod file is:
%% Created by Ing. Andrés Felipe Abril. Universidad Nacional de Colombia. Departamento de Ingeniería Química.
%% Linking
Aspen = actxserver(‘Apwn.Document.36.0’); %34.0 —> V8.8; 35.0 —> V9.0; and 36.0 —> V10.0
[stat,mess]=fileattrib; % get attributes of folder (Necessary to establish the location of the simulation)
Simulation_Name = ‘Reactive_Distillation’;% Aspeen Plus Simulation Name
Aspen.invoke(‘InitFromArchive2’,[mess.Name ” Simulation_Name ‘.bkp’]);
Aspen.Visible = 1; % 1 —> Aspen is Visible; 0 —> Aspen is open but not visible
Aspen.SuppressDialogs = 1; % Suppress windows dialogs.
Aspen.Engine.Run2(1); % Run the simulation
while Aspen.Engine.IsRunning == 1 % 1 –> If Aspen is running; 0 —> If Aspen stop.
pause(0.5);
end

%% Example of Application
Reflux_Ratio = [1, 3, 5, 7];
for i = 1:length(Reflux_Ratio)
Aspen.Tree.FindNode("DataBlocksRC-101InputBASIS_RR").Value = Reflux_Ratio(i); % Column Reflux
Aspen.Reinit; % Reinit simulation
Aspen.Engine.Run2(1); %Run the simulation. (1) —> Matlab isnt busy; (0) Matlab is Busy;
time = 1;
while Aspen.Engine.IsRunning == 1 % 1 –> If Aspen is running; 0 —> If Aspen stop.
pause(0.5);
time = time+1;
if time==15 % Control of simulation time.
Aspen.Engine.Stop;
end
end
Simulation_Convergency = Aspen.Tree.FindNode("DataResults SummaryRun-StatusOutputPCESSTAT").Value; % 1 Doesn’t Convergence; 0 Converge
if Simulation_Convergency == 0 && time < 10
Duty(i) = Aspen.Tree.FindNode("DataBlocksRC-101OutputREB_UTL_DUTY").Value; %Duty value of reactive column
else
Duty(i) = inf; % Its Penalized if simulation doesn’t converge;

end
end
%% Plotting
figure()
plot(Reflux_Ratio, Duty, ‘ok’);
Aspen.Close;
Aspen.Quit; Please help me I am new to Matlab and Aspen Plus but have basic knowledge so please guide in detail. Please tell me what steps do I follow to link Aspen file and Matlab.
The Matlab cod file is:
%% Created by Ing. Andrés Felipe Abril. Universidad Nacional de Colombia. Departamento de Ingeniería Química.
%% Linking
Aspen = actxserver(‘Apwn.Document.36.0’); %34.0 —> V8.8; 35.0 —> V9.0; and 36.0 —> V10.0
[stat,mess]=fileattrib; % get attributes of folder (Necessary to establish the location of the simulation)
Simulation_Name = ‘Reactive_Distillation’;% Aspeen Plus Simulation Name
Aspen.invoke(‘InitFromArchive2’,[mess.Name ” Simulation_Name ‘.bkp’]);
Aspen.Visible = 1; % 1 —> Aspen is Visible; 0 —> Aspen is open but not visible
Aspen.SuppressDialogs = 1; % Suppress windows dialogs.
Aspen.Engine.Run2(1); % Run the simulation
while Aspen.Engine.IsRunning == 1 % 1 –> If Aspen is running; 0 —> If Aspen stop.
pause(0.5);
end

%% Example of Application
Reflux_Ratio = [1, 3, 5, 7];
for i = 1:length(Reflux_Ratio)
Aspen.Tree.FindNode("DataBlocksRC-101InputBASIS_RR").Value = Reflux_Ratio(i); % Column Reflux
Aspen.Reinit; % Reinit simulation
Aspen.Engine.Run2(1); %Run the simulation. (1) —> Matlab isnt busy; (0) Matlab is Busy;
time = 1;
while Aspen.Engine.IsRunning == 1 % 1 –> If Aspen is running; 0 —> If Aspen stop.
pause(0.5);
time = time+1;
if time==15 % Control of simulation time.
Aspen.Engine.Stop;
end
end
Simulation_Convergency = Aspen.Tree.FindNode("DataResults SummaryRun-StatusOutputPCESSTAT").Value; % 1 Doesn’t Convergence; 0 Converge
if Simulation_Convergency == 0 && time < 10
Duty(i) = Aspen.Tree.FindNode("DataBlocksRC-101OutputREB_UTL_DUTY").Value; %Duty value of reactive column
else
Duty(i) = inf; % Its Penalized if simulation doesn’t converge;

end
end
%% Plotting
figure()
plot(Reflux_Ratio, Duty, ‘ok’);
Aspen.Close;
Aspen.Quit; aspen plus MATLAB Answers — New Questions

​

Hello everybody. I’m using Newton’s method to solve a liner equation whose solution should be in [0 1]. Unfortunately, the coe I’m using gives NaN as a result for a specific combination of parameters and I would like to understand if I can improve the code I wrote for my Newton’s method. In the specific case I’m considering, I reach the maximum iterations even if the tolerance is very low.
function [x,n,ier] = newton(f,fd,x0,nmax,tol)
% Newton’s method for non-linear equations
ier = 0;
for n = 1:nmax
x = x0-f(x0)/fd(x0);
if abs(x-x0) <= tol
ier = 1;
break
end
x0 = x;
end

% % % % Script for solving NaN
mNAN= 16.1;
lNAN= 10^-4;
f= @(x) mNAN*x+lNAN*exp(mNAN*x)-lNAN*exp(mNAN);
Fd= @(x) mNAN*(1+lNAN*exp(mNAN*x));
tolNaN=10^-1;
nmax=10^8;
AB0 = 0.5;
[amNAN,nNAN,ierNAN]=newton(f,Fd,AB0,nmax,tolNaN);
amNAN
Llimit=f(0)
Ulimit=f(1)
fplot(@(x) mNAN*x+lNAN*exp(mNAN*x)-lNAN*exp(mNAN),[0 1.1])Hello everybody. I’m using Newton’s method to solve a liner equation whose solution should be in [0 1]. Unfortunately, the coe I’m using gives NaN as a result for a specific combination of parameters and I would like to understand if I can improve the code I wrote for my Newton’s method. In the specific case I’m considering, I reach the maximum iterations even if the tolerance is very low.
function [x,n,ier] = newton(f,fd,x0,nmax,tol)
% Newton’s method for non-linear equations
ier = 0;
for n = 1:nmax
x = x0-f(x0)/fd(x0);
if abs(x-x0) <= tol
ier = 1;
break
end
x0 = x;
end

% % % % Script for solving NaN
mNAN= 16.1;
lNAN= 10^-4;
f= @(x) mNAN*x+lNAN*exp(mNAN*x)-lNAN*exp(mNAN);
Fd= @(x) mNAN*(1+lNAN*exp(mNAN*x));
tolNaN=10^-1;
nmax=10^8;
AB0 = 0.5;
[amNAN,nNAN,ierNAN]=newton(f,Fd,AB0,nmax,tolNaN);
amNAN
Llimit=f(0)
Ulimit=f(1)
fplot(@(x) mNAN*x+lNAN*exp(mNAN*x)-lNAN*exp(mNAN),[0 1.1]) Hello everybody. I’m using Newton’s method to solve a liner equation whose solution should be in [0 1]. Unfortunately, the coe I’m using gives NaN as a result for a specific combination of parameters and I would like to understand if I can improve the code I wrote for my Newton’s method. In the specific case I’m considering, I reach the maximum iterations even if the tolerance is very low.
function [x,n,ier] = newton(f,fd,x0,nmax,tol)
% Newton’s method for non-linear equations
ier = 0;
for n = 1:nmax
x = x0-f(x0)/fd(x0);
if abs(x-x0) <= tol
ier = 1;
break
end
x0 = x;
end

% % % % Script for solving NaN
mNAN= 16.1;
lNAN= 10^-4;
f= @(x) mNAN*x+lNAN*exp(mNAN*x)-lNAN*exp(mNAN);
Fd= @(x) mNAN*(1+lNAN*exp(mNAN*x));
tolNaN=10^-1;
nmax=10^8;
AB0 = 0.5;
[amNAN,nNAN,ierNAN]=newton(f,Fd,AB0,nmax,tolNaN);
amNAN
Llimit=f(0)
Ulimit=f(1)
fplot(@(x) mNAN*x+lNAN*exp(mNAN*x)-lNAN*exp(mNAN),[0 1.1]) transferred MATLAB Answers — New Questions

​

Is there a way to evaluate classification/regression performance accounting of noisy annotations.
Let’s say I have a cat/dog detector and 1000 cat/dog test images. The 1000 images are human annotated, so it’s likely there are annotation errors, e.g. some bounding box may be incorrect and some class label may be wrong. Simply draw a confusion matrix or derive an IoU just compare the detector performance with the noisy data, and I don’t think such way is appropriate.
So my questions are
What’s the appropriate way to estimate the bbox and class error margin in the data set, given it’s not possible to go through each of them?
How to incorporate the above annotation error when reporting the performance of the cat/dog detector?
Thanks.Is there a way to evaluate classification/regression performance accounting of noisy annotations.
Let’s say I have a cat/dog detector and 1000 cat/dog test images. The 1000 images are human annotated, so it’s likely there are annotation errors, e.g. some bounding box may be incorrect and some class label may be wrong. Simply draw a confusion matrix or derive an IoU just compare the detector performance with the noisy data, and I don’t think such way is appropriate.
So my questions are
What’s the appropriate way to estimate the bbox and class error margin in the data set, given it’s not possible to go through each of them?
How to incorporate the above annotation error when reporting the performance of the cat/dog detector?
Thanks. Is there a way to evaluate classification/regression performance accounting of noisy annotations.
Let’s say I have a cat/dog detector and 1000 cat/dog test images. The 1000 images are human annotated, so it’s likely there are annotation errors, e.g. some bounding box may be incorrect and some class label may be wrong. Simply draw a confusion matrix or derive an IoU just compare the detector performance with the noisy data, and I don’t think such way is appropriate.
So my questions are
What’s the appropriate way to estimate the bbox and class error margin in the data set, given it’s not possible to go through each of them?
How to incorporate the above annotation error when reporting the performance of the cat/dog detector?
Thanks. annotation, classification, regression, noise, evaluation MATLAB Answers — New Questions

​

I am trying to run the "semanticseg" function on an image with size (8557×11377) and my own custom network, and I receive the error:

ERROR: Error using nnet.internal.cnngpu.convolveForward2D
Maximum variable size allowed on the device is exceeded.
I expect MATLAB to tile the image, run the semantic segmentation, and reassemble the tile, but I am receiving this error on a windows laptop with a GTX 1070 card.

The two questions I have are:

1) Why do I receive this error message?
2) I would like to know what the maximum allowed image size I can have with my own custom network when running the "semanticseg" function.I am trying to run the "semanticseg" function on an image with size (8557×11377) and my own custom network, and I receive the error:

ERROR: Error using nnet.internal.cnngpu.convolveForward2D
Maximum variable size allowed on the device is exceeded.
I expect MATLAB to tile the image, run the semantic segmentation, and reassemble the tile, but I am receiving this error on a windows laptop with a GTX 1070 card.

The two questions I have are:

1) Why do I receive this error message?
2) I would like to know what the maximum allowed image size I can have with my own custom network when running the "semanticseg" function. I am trying to run the "semanticseg" function on an image with size (8557×11377) and my own custom network, and I receive the error:

ERROR: Error using nnet.internal.cnngpu.convolveForward2D
Maximum variable size allowed on the device is exceeded.
I expect MATLAB to tile the image, run the semantic segmentation, and reassemble the tile, but I am receiving this error on a windows laptop with a GTX 1070 card.

The two questions I have are:

1) Why do I receive this error message?
2) I would like to know what the maximum allowed image size I can have with my own custom network when running the "semanticseg" function. convolveforward2d, semanticseg MATLAB Answers — New Questions

​

I want to create a matrix that the main diagonal of K are alternatively 2 and -2’s, the sub- and sup-diagonal of K alternatively
1 and -1’s, and everywhere else 0. The size of K is 2n by 2n.

Here is what I got so far.

x=ones(1,5);
y=ones(1,4);
x2=2*x;
y2=y*-1;
z=diag(x2,0)
[rows, columns] = size(z)

z(1:2*rows+2:end) = -z(1:2*rows+2:end)

b=diag(y2,+1)

d=diag(y2,-1)
g=z+b+dI want to create a matrix that the main diagonal of K are alternatively 2 and -2’s, the sub- and sup-diagonal of K alternatively
1 and -1’s, and everywhere else 0. The size of K is 2n by 2n.

Here is what I got so far.

x=ones(1,5);
y=ones(1,4);
x2=2*x;
y2=y*-1;
z=diag(x2,0)
[rows, columns] = size(z)

z(1:2*rows+2:end) = -z(1:2*rows+2:end)

b=diag(y2,+1)

d=diag(y2,-1)
g=z+b+d I want to create a matrix that the main diagonal of K are alternatively 2 and -2’s, the sub- and sup-diagonal of K alternatively
1 and -1’s, and everywhere else 0. The size of K is 2n by 2n.

Here is what I got so far.

x=ones(1,5);
y=ones(1,4);
x2=2*x;
y2=y*-1;
z=diag(x2,0)
[rows, columns] = size(z)

z(1:2*rows+2:end) = -z(1:2*rows+2:end)

b=diag(y2,+1)

d=diag(y2,-1)
g=z+b+d matrix manipulation MATLAB Answers — New Questions

​

I’m using an API from an Audio Precision to detect the available channels from an ASIO device. The API outputs a .NET array of type IChannelInfo[] that I can’t seem to get information from. If I create the array as chanInfo and try to access the first object either with chanInfo(1) or chanInfo.GetValue(1) or any other number of Methods, it just returns a "MarshalByRefObject" with no properties that I can’t figure out how to actually use. I would expect it to either just return a string like "Analog 2 (1)" or to return another .NET object that includes the name, channel number, etc.I’m using an API from an Audio Precision to detect the available channels from an ASIO device. The API outputs a .NET array of type IChannelInfo[] that I can’t seem to get information from. If I create the array as chanInfo and try to access the first object either with chanInfo(1) or chanInfo.GetValue(1) or any other number of Methods, it just returns a "MarshalByRefObject" with no properties that I can’t figure out how to actually use. I would expect it to either just return a string like "Analog 2 (1)" or to return another .NET object that includes the name, channel number, etc. I’m using an API from an Audio Precision to detect the available channels from an ASIO device. The API outputs a .NET array of type IChannelInfo[] that I can’t seem to get information from. If I create the array as chanInfo and try to access the first object either with chanInfo(1) or chanInfo.GetValue(1) or any other number of Methods, it just returns a "MarshalByRefObject" with no properties that I can’t figure out how to actually use. I would expect it to either just return a string like "Analog 2 (1)" or to return another .NET object that includes the name, channel number, etc. .net, system MATLAB Answers — New Questions

​

I am using tiled layout(‘flow’) to plot a series of 20 plots on one figure. I want to have just one x and one y label for the entire figure, but when I try using the following code I get a figure that plots every subplot over each other.
figure()
t=tiledlayout(‘flow’);
autoCorr = zeros(ceil(length(dataSource)),N);
lag = zeros(ceil(length(dataSource)),N);
for ii=1:N
[autoCorr(:,ii),lag(:,ii)] = autocorrelation(dataSource(:,ii));
nexttile(t)
plot(lag(:,ii),autoCorr(:,ii))
end
title(t,’title’)
xlabel(t,’xlabel’)
ylabel(t,’ylabel’)

When I use this code the plot works fine but I’m not sure how to add the x and y axis labels.
autoCorr = zeros(ceil(length(dataSource)),N);
lag = zeros(ceil(length(dataSource)),N);
figure()
tiledlayout(‘flow’)
for ii=1:N
[autoCorr(:,ii),lag(:,ii)] = autocorrelation(dataSource(:,ii));
nexttile
plot(lag(:,ii),autoCorr(:,ii))
% xlim([100,fmax])
endI am using tiled layout(‘flow’) to plot a series of 20 plots on one figure. I want to have just one x and one y label for the entire figure, but when I try using the following code I get a figure that plots every subplot over each other.
figure()
t=tiledlayout(‘flow’);
autoCorr = zeros(ceil(length(dataSource)),N);
lag = zeros(ceil(length(dataSource)),N);
for ii=1:N
[autoCorr(:,ii),lag(:,ii)] = autocorrelation(dataSource(:,ii));
nexttile(t)
plot(lag(:,ii),autoCorr(:,ii))
end
title(t,’title’)
xlabel(t,’xlabel’)
ylabel(t,’ylabel’)

When I use this code the plot works fine but I’m not sure how to add the x and y axis labels.
autoCorr = zeros(ceil(length(dataSource)),N);
lag = zeros(ceil(length(dataSource)),N);
figure()
tiledlayout(‘flow’)
for ii=1:N
[autoCorr(:,ii),lag(:,ii)] = autocorrelation(dataSource(:,ii));
nexttile
plot(lag(:,ii),autoCorr(:,ii))
% xlim([100,fmax])
end I am using tiled layout(‘flow’) to plot a series of 20 plots on one figure. I want to have just one x and one y label for the entire figure, but when I try using the following code I get a figure that plots every subplot over each other.
figure()
t=tiledlayout(‘flow’);
autoCorr = zeros(ceil(length(dataSource)),N);
lag = zeros(ceil(length(dataSource)),N);
for ii=1:N
[autoCorr(:,ii),lag(:,ii)] = autocorrelation(dataSource(:,ii));
nexttile(t)
plot(lag(:,ii),autoCorr(:,ii))
end
title(t,’title’)
xlabel(t,’xlabel’)
ylabel(t,’ylabel’)

When I use this code the plot works fine but I’m not sure how to add the x and y axis labels.
autoCorr = zeros(ceil(length(dataSource)),N);
lag = zeros(ceil(length(dataSource)),N);
figure()
tiledlayout(‘flow’)
for ii=1:N
[autoCorr(:,ii),lag(:,ii)] = autocorrelation(dataSource(:,ii));
nexttile
plot(lag(:,ii),autoCorr(:,ii))
% xlim([100,fmax])
end tiled layout, tiledlayout, tiles, plot, subplot MATLAB Answers — New Questions

​

Hello dear Community,

i am currently trying to use a Feed-Forward Neural Network for a regression problem.
The input data i want to feed in are "rotational speed", "torque" and "time".
The target data is the temperature of an electrical drive.
And then i will have different operating points dependend on speed:
2000 rpm, 4000 rpm ….
The torque and time however stays the same for each point.
Right now, i am using a sequenceInputLayer and arranged the Data in 4 cells, where each cell contains 3 columns of data. One cell represents one OP.
The results are not good, and my gut tells me, that i might have a misunderstanding the way i treat the input data.

I am using MATLAB r24a and am training the network with the "trainnet"-function.
If you have any Suggestions to do this in a different way, go ahead.
Thank you very much in advance.Hello dear Community,

i am currently trying to use a Feed-Forward Neural Network for a regression problem.
The input data i want to feed in are "rotational speed", "torque" and "time".
The target data is the temperature of an electrical drive.
And then i will have different operating points dependend on speed:
2000 rpm, 4000 rpm ….
The torque and time however stays the same for each point.
Right now, i am using a sequenceInputLayer and arranged the Data in 4 cells, where each cell contains 3 columns of data. One cell represents one OP.
The results are not good, and my gut tells me, that i might have a misunderstanding the way i treat the input data.

I am using MATLAB r24a and am training the network with the "trainnet"-function.
If you have any Suggestions to do this in a different way, go ahead.
Thank you very much in advance. Hello dear Community,

i am currently trying to use a Feed-Forward Neural Network for a regression problem.
The input data i want to feed in are "rotational speed", "torque" and "time".
The target data is the temperature of an electrical drive.
And then i will have different operating points dependend on speed:
2000 rpm, 4000 rpm ….
The torque and time however stays the same for each point.
Right now, i am using a sequenceInputLayer and arranged the Data in 4 cells, where each cell contains 3 columns of data. One cell represents one OP.
The results are not good, and my gut tells me, that i might have a misunderstanding the way i treat the input data.

I am using MATLAB r24a and am training the network with the "trainnet"-function.
If you have any Suggestions to do this in a different way, go ahead.
Thank you very much in advance. deep learning, neural network, regression, data MATLAB Answers — New Questions

​

Please refer to the Matlab example (https://www.mathworks.com/help/images/learning-to-see-in-the-dark.html), This page itself acknowledges that "The colors of the network prediction are less saturated and vibrant than in the ground truth". I have compared it against the original TF model as provided by the original authors (https://github.com/cchen156/Learning-to-See-in-the-Dark) which DOES provide a very good reconstruction of the ground truth with vibrant colors. I have tried retraining the model in Matlab and got similarly poor results as the Matlab-provided pretrained model. Could someone please throw light on what could be causing this? I am afraid without a solution, Matlab example is not useful at all compared to the Tensorflow solution.Please refer to the Matlab example (https://www.mathworks.com/help/images/learning-to-see-in-the-dark.html), This page itself acknowledges that "The colors of the network prediction are less saturated and vibrant than in the ground truth". I have compared it against the original TF model as provided by the original authors (https://github.com/cchen156/Learning-to-See-in-the-Dark) which DOES provide a very good reconstruction of the ground truth with vibrant colors. I have tried retraining the model in Matlab and got similarly poor results as the Matlab-provided pretrained model. Could someone please throw light on what could be causing this? I am afraid without a solution, Matlab example is not useful at all compared to the Tensorflow solution. Please refer to the Matlab example (https://www.mathworks.com/help/images/learning-to-see-in-the-dark.html), This page itself acknowledges that "The colors of the network prediction are less saturated and vibrant than in the ground truth". I have compared it against the original TF model as provided by the original authors (https://github.com/cchen156/Learning-to-See-in-the-Dark) which DOES provide a very good reconstruction of the ground truth with vibrant colors. I have tried retraining the model in Matlab and got similarly poor results as the Matlab-provided pretrained model. Could someone please throw light on what could be causing this? I am afraid without a solution, Matlab example is not useful at all compared to the Tensorflow solution. see in the light dataset, image regression, low light enhancement MATLAB Answers — New Questions

​