Hfrxdjt

Does tea made with boiling water cool faster than tea made with boiled (but still hot) water?

Rivers without rain

How to denote matrix elements succinctly?

How come there are so many candidates for the 2020 Democratic party presidential nomination?

Re-entry to Germany after vacation using blue card

Implications of cigar-shaped bodies having rings?

How do I deal with a coworker that keeps asking to make small superficial changes to a report, and it is seriously triggering my anxiety?

Which big number is bigger?

What is causing the white spot to appear in some of my pictures

Classification of surfaces

Is there really no use for MD5 anymore?

Minor Revision with suggestion of an alternative proof by reviewer

Check if a string is entirely made of the same substring

Why does nature favour the Laplacian?

A ​Note ​on ​N!

As an international instructor, should I openly talk about my accent?

What's the polite way to say "I need to urinate"?

Could the terminal length of components like resistors be reduced?

What happens to Mjolnir (Thor's hammer) at the end of Endgame?

What term is being referred to with "reflected-sound-of-underground-spirits"?

Extension of 2-adic valuation to the real numbers

Apply MapThread to all but one variable

Why was the Spitfire's elliptical wing almost uncopied by other aircraft of World War 2?

What's the name of these pliers?

Label embedding in Auxiliary Classifier GANs

EEG data layout for RNNClassification with millions of records, thousands of categories - keep memory use efficient?What does discriminator of a GAN should do?Adversarial Learning for Semantic SegmentationHow to use deep learning to add local (e.g. repairing) transformations to images?Connection between cross entropy and likelihood for multi-class soft label classificationHow to train the generator in a recurrent GAN (Keras)Architecture for linear regression with variable input where each input is n-sized one-hot encodedWhen should embeddings not be used for categorical data? What are their limitations?Why my CNN model is not learning?

0

$begingroup$

In Auxiliary Classifier GAN the generator takes two inputs, 1. one hot encoding of the labels, and 2. noise vector. But in the implementation of the GAN (e.g.:) some embedding is used, I think it is to convert the sparse one-hot-encoded vectors into a dense form. But what I dont understand is, then this embedded labels are then multiplied with the noise vector and rest of the layers are based on this multiplied input. My questions are:

1. Why these two vectors are multiplied instead of concatenation?


2. Lets assume that I have to give another input, y (another one-hot representation), in addition to the labels, and noise. In that case can I still multiply the embedded labels, embedded y and noise all together and give as the input to the rest of the layers?

machine-learning convnet pytorch gan

share|improve this question

asked 12 mins ago

user570593user570593

1011

New contributor

user570593 is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

$endgroup$

add a comment | 

0

$begingroup$

In Auxiliary Classifier GAN the generator takes two inputs, 1. one hot encoding of the labels, and 2. noise vector. But in the implementation of the GAN (e.g.:) some embedding is used, I think it is to convert the sparse one-hot-encoded vectors into a dense form. But what I dont understand is, then this embedded labels are then multiplied with the noise vector and rest of the layers are based on this multiplied input. My questions are:

1. Why these two vectors are multiplied instead of concatenation?


2. Lets assume that I have to give another input, y (another one-hot representation), in addition to the labels, and noise. In that case can I still multiply the embedded labels, embedded y and noise all together and give as the input to the rest of the layers?

machine-learning convnet pytorch gan

share|improve this question

asked 12 mins ago

user570593user570593

1011

New contributor

user570593 is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

$endgroup$

add a comment | 

$begingroup$

In Auxiliary Classifier GAN the generator takes two inputs, 1. one hot encoding of the labels, and 2. noise vector. But in the implementation of the GAN (e.g.:) some embedding is used, I think it is to convert the sparse one-hot-encoded vectors into a dense form. But what I dont understand is, then this embedded labels are then multiplied with the noise vector and rest of the layers are based on this multiplied input. My questions are:

1. Why these two vectors are multiplied instead of concatenation?


2. Lets assume that I have to give another input, y (another one-hot representation), in addition to the labels, and noise. In that case can I still multiply the embedded labels, embedded y and noise all together and give as the input to the rest of the layers?

machine-learning convnet pytorch gan

share|improve this question

asked 12 mins ago

user570593user570593

1011

New contributor

user570593 is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

$endgroup$

share|improve this question

asked 12 mins ago

user570593user570593

1011

New contributor

user570593 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 12 mins ago

user570593user570593

1011

New contributor

user570593 is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

asked 12 mins ago

user570593user570593

1011

New contributor

user570593 is a new contributor to this site. Take care in asking for clarification, commenting, and answering.
Check out our Code of Conduct.

asked 12 mins ago

user570593user570593

1011