Hfrxdjt

How to count in linear time worst-case?

Co-worker works way more than he should

Visa-free travel to the US using refugee travel document from Spain?

Could Neutrino technically as side-effect, incentivize centralization of the bitcoin network?

Justification for leaving new position after a short time

Is accepting an invalid credit card number a security issue?

Protagonist's race is hidden - should I reveal it?

How would I use different systems of magic when they are capable of the same effects?

How to translate "red flag" into Spanish?

Is Diceware more secure than a long passphrase?

Can I criticise the more senior developers around me for not writing clean code?

How would this chord from "Rocket Man" be analyzed?

All ASCII characters with a given bit count

I preordered a game on my Xbox while on the home screen of my friend's account. Which of us owns the game?

"My boss was furious with me and I have been fired" vs. "My boss was furious with me and I was fired"

Why didn't the Space Shuttle bounce back into space as many times as possible so as to lose a lot of kinetic energy up there?

Are these square matrices always diagonalisable?

Expansion//Explosion and Siren Stormtamer

Putting Ant-Man on house arrest

What do you call the part of a novel that is not dialog?

What is the ongoing value of the Kanban board to the developers as opposed to management

Why does the Cisco show run command not show the full version, while the show version command does?

Password Generator in batch

Book with legacy programming code on a space ship that the main character hacks to escape

Input/output shapes of GANs for sequential data

0

$begingroup$

I am trying to do time series prediction using GANs. I am using MXNet/Gluon. Thus, I have a sequential data of size (N, 1). Now I have a hard time understanding the input out shapes of the network. Here is, the code for Generator and Discriminator networks.

netG = nn.Sequential()
with netG.name_scope():
 netG.add(nn.Dense(20))
 netG.add(nn.BatchNorm(momentum = 0.8))
 netG.add(nn.Dropout(0.5))
 netG.add(nn.Dense(15))
 netG.add(nn.BatchNorm(momentum = 0.8))
 netG.add(nn.Dropout(0.5))
 netG.add(nn.Dense(20))
 netG.add(nn.BatchNorm(momentum = 0.8))
 netG.add(nn.Dropout(0.5))
 netG.add(nn.Dense(step_size, activation = "tanh"))


#300, 50, 2
#input shape is inferred
netD = nn.Sequential()
with netD.name_scope():
 netD.add(nn.Dense(20))
 netG.add(nn.BatchNorm(momentum = 0.8))
 netD.add(nn.Dense(15, activation='tanh'))
 netG.add(nn.BatchNorm(momentum = 0.8))
 netD.add(nn.Dense(20, activation='tanh'))
 netD.add(nn.Dense(step_size))

Thanks in advance

time-series prediction gan

share|improve this question

asked 1 hour ago

DickDick

1

New contributor

Dick is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

$endgroup$

• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  are you looking for changes to the code or for an explanation of it?
  $endgroup$
  – oW_♦
  34 mins ago
  

  
  
  
  

add a comment | 

0

$begingroup$

I am trying to do time series prediction using GANs. I am using MXNet/Gluon. Thus, I have a sequential data of size (N, 1). Now I have a hard time understanding the input out shapes of the network. Here is, the code for Generator and Discriminator networks.

netG = nn.Sequential()
with netG.name_scope():
 netG.add(nn.Dense(20))
 netG.add(nn.BatchNorm(momentum = 0.8))
 netG.add(nn.Dropout(0.5))
 netG.add(nn.Dense(15))
 netG.add(nn.BatchNorm(momentum = 0.8))
 netG.add(nn.Dropout(0.5))
 netG.add(nn.Dense(20))
 netG.add(nn.BatchNorm(momentum = 0.8))
 netG.add(nn.Dropout(0.5))
 netG.add(nn.Dense(step_size, activation = "tanh"))


#300, 50, 2
#input shape is inferred
netD = nn.Sequential()
with netD.name_scope():
 netD.add(nn.Dense(20))
 netG.add(nn.BatchNorm(momentum = 0.8))
 netD.add(nn.Dense(15, activation='tanh'))
 netG.add(nn.BatchNorm(momentum = 0.8))
 netD.add(nn.Dense(20, activation='tanh'))
 netD.add(nn.Dense(step_size))

Thanks in advance

time-series prediction gan

share|improve this question

asked 1 hour ago

DickDick

1

New contributor

Dick is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

$endgroup$

• 
  
  
  

  
  

  
  
  
  
  
  

  
  $begingroup$
  are you looking for changes to the code or for an explanation of it?
  $endgroup$
  – oW_♦
  34 mins ago
  

  
  
  
  

add a comment | 

$begingroup$

I am trying to do time series prediction using GANs. I am using MXNet/Gluon. Thus, I have a sequential data of size (N, 1). Now I have a hard time understanding the input out shapes of the network. Here is, the code for Generator and Discriminator networks.

netG = nn.Sequential()
with netG.name_scope():
 netG.add(nn.Dense(20))
 netG.add(nn.BatchNorm(momentum = 0.8))
 netG.add(nn.Dropout(0.5))
 netG.add(nn.Dense(15))
 netG.add(nn.BatchNorm(momentum = 0.8))
 netG.add(nn.Dropout(0.5))
 netG.add(nn.Dense(20))
 netG.add(nn.BatchNorm(momentum = 0.8))
 netG.add(nn.Dropout(0.5))
 netG.add(nn.Dense(step_size, activation = "tanh"))


#300, 50, 2
#input shape is inferred
netD = nn.Sequential()
with netD.name_scope():
 netD.add(nn.Dense(20))
 netG.add(nn.BatchNorm(momentum = 0.8))
 netD.add(nn.Dense(15, activation='tanh'))
 netG.add(nn.BatchNorm(momentum = 0.8))
 netD.add(nn.Dense(20, activation='tanh'))
 netD.add(nn.Dense(step_size))

Thanks in advance

time-series prediction gan

share|improve this question

asked 1 hour ago

DickDick

1

New contributor

Dick is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

$endgroup$

netG = nn.Sequential()
with netG.name_scope():
 netG.add(nn.Dense(20))
 netG.add(nn.BatchNorm(momentum = 0.8))
 netG.add(nn.Dropout(0.5))
 netG.add(nn.Dense(15))
 netG.add(nn.BatchNorm(momentum = 0.8))
 netG.add(nn.Dropout(0.5))
 netG.add(nn.Dense(20))
 netG.add(nn.BatchNorm(momentum = 0.8))
 netG.add(nn.Dropout(0.5))
 netG.add(nn.Dense(step_size, activation = "tanh"))


#300, 50, 2
#input shape is inferred
netD = nn.Sequential()
with netD.name_scope():
 netD.add(nn.Dense(20))
 netG.add(nn.BatchNorm(momentum = 0.8))
 netD.add(nn.Dense(15, activation='tanh'))
 netG.add(nn.BatchNorm(momentum = 0.8))
 netD.add(nn.Dense(20, activation='tanh'))
 netD.add(nn.Dense(step_size))

share|improve this question

asked 1 hour ago

DickDick

1

New contributor

Dick is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

share|improve this question

asked 1 hour ago

DickDick

1

New contributor

Dick is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

asked 1 hour ago

DickDick

1

New contributor

Dick is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

asked 1 hour ago

DickDick

1