Use a GAN to generate images based on a set of paintings

$250-750 AUD

Ολοκληρώθηκε

Αναρτήθηκε

πάνω από 5 χρόνια πριν

$250-750 AUD

Πληρωμή κατά την παράδοση

I am an artist. I want to use generative adversarial network or similar process to generate images based on my existing paintings. There would be a data set of approximately 250 representational paintings. I'd like to have the network generate images which it thinks look like those paintings.

Machine Learning (ML)

Ταυτότητα εργασίας: 17945161

Σχετικά με την εργασία

15 προτάσεις

Απομακρυσμένη Εργασία

Ενεργός/ή 6 χρόνια πριν

Ψάχνεις τρόπο για να κερδίσεις μερικά χρήματα;

Διεύθυνση Email

Πλεονεκτήματα πλειοδοσίας στο Freelancer

Καθόρισε τον προϋπολογισμό σου και το χρονοδιάγραμμα

Πληρώσου για τη δουλειά σου

Περίγραψε την πρόταση σου

Η εγγραφή και η πλειοδοσία σε εργασίες είναι δωρεάν

Βραβεύτηκε στον/στην:

@DoctorMatthew

I’ll build the network using Python and Keras - open source libraries, which you will be able to run yourself with little setup. UK based, native English speaker. Relevant Skills and Experience PhD in Physics. 3 years experience as a Data Science building Deep learning models for a FTSE100 company. Love art and open to future collaborations.

$611 AUD σε 7 ημέρες

5,0

(2 αξιολογήσεις)

3,6

15 freelancers δίνουν μια μέση προσφορά $474 AUD για αυτή τη δουλειά

@nkoutroumpinis

Hey there! I am working as a professional data scientist with lots of experience on deep learning and machine learning in general. You can check out my profile reviews to get a first impression of the work i am kindly delivering. Other than that we can discuss anything about your project in chat. Regards, Nick.

$555 AUD σε 10 ημέρες

5,0

(16 αξιολογήσεις)

5,4

@frankoziga

Hi, in GAN algorithms you have multiple algorithms you can choose on your desires. If you want to transfer your painting style to a some other picture, ... I have completed deep learning specialisation about one year ago and worked with those algorithms for quite a bit. please check my profile for more info about me and feel free to contact me. Regards, Žiga

$500 AUD σε 6 ημέρες

5,0

(7 αξιολογήσεις)

4,7

@sinhprous

I have experience in CNN and have good skill at Tensorflow. I have experience in CNN and have good skill at Tensorflow. I have experience in CNN and have good skill at Tensorflow.

$277 AUD σε 10 ημέρες

4,7

(9 αξιολογήσεις)

3,7

@arsalan012

Hello, We are a small team working in the field of Machine learning, Ai and deep neural network. We really happy to know that you are required a task which is looking really interesting to us. We will offer you a very reasonable price and we will work till satisfied results. Please contact me back to start this interesting job for you. Thanks!

$277 AUD σε 10 ημέρες

5,0

(3 αξιολογήσεις)

2,5

@inspiredwhiz

I am an engineer, I have successfully executed many engineering task than you can ever imagine both on freelancer and off freelancer. It will be a pleasure working with you on this one Sir. Thanks

$250 AUD σε 2 ημέρες

2,8

(2 αξιολογήσεις)

2,6

@Arghya1998

The first thing that I'd like to poiny out to is that the time required to make the following system can be much lower. But I like to maintain an uppercap to allow room for client corrections. A little about me: I'm Arghya, a reseach student at IIIT Hyderabad. My majors is in Computer Science and I am a Computational Linguist. I've worked with GANs before for similar tasks and the same is something I'm comfortable with. I'm also a mentor for Google CodeIn. I cam forward my resume is required. A little Idea of my Ideas for the project: Although GAN has shown great success in the realistic image generation, the training is not easy, The process is known to be slow and unstable. Things I plan to do to achieve better and faster convergence: (1) Feature Matching Feature matching suggests to optimize the discriminator to inspect whether the generator’s output matches expected statistics of the real samples (2) Minibatch Discrimination With minibatch discrimination, the discriminator is able to digest the relationship between training data points in one batch, instead of processing each point independently. (3) Historical Averaging (4) One-sided Label Smoothing When feeding the discriminator, instead of providing 1 and 0 labels, use soften values such as 0.9 and 0.1. It is shown to reduce the networks’ vulnerability. (5) Virtual Batch Normalization (VBN) Hope to work with you soon!

$388 AUD σε 20 ημέρες