Not mild. Not medium. Shpicy.

Top Menu

We do design. Shpicy focuses on providing top notch creative design for businesses looking to improve their image. Since 2009, Shpicy has delivered fresh design deliverables that take businesses to the next level of professionalism.

Your new logo is just around the corner. Metaphorically speaking.

Logo design starting at $999

Shoot us your name and email and we'll get right back to you for a free consultation. Piece of cake. Mmmm...cake.

Name

Email

Favorite breakfast food (hopefully not Spam)

We’re just a hop, click, and a jump from starting your website.

Web design starting at $999

Shoot us your name and email and we’ll get right back to you for a free consultation. Easy as pie. Mmmm…pie.

Name

Email

Favorite breakfast food (hopefully not Spam)

Let’s get started on that print project of yours.

Print design starting at $199

Shoot us your name and email and we’ll get right back to you for a free consultation. Easy peasy. Lemon Squeezy.

Name

Email

Favorite breakfast food (hopefully not Spam)

Lights! Camera! Email Us!

Video services starting at $999

Shoot us your name and email and we’ll get right back to you for a free consultation. Easy as pie. Mmmm…pie.

Name

Email

Favorite breakfast food (hopefully not Spam)

Photorealistic Faces

By Shpicy

Posted in ,

Graphics card and electronics manufacturer Nvidia describe a new training methodology for generative adversarial networks. The key idea is to grow both the generator and discriminator progressively, starting from low-resolution images, and add new layers that deal with higher resolution details as the training progresses. This greatly stabilizes the training and allows us to produce images of unprecedented quality, e.g., CelebA images at 1024² resolution. We also propose a simple way to increase the variation in generated images, and achieve a record inception score of 8.80 in unsupervised CIFAR10. Additionally, we describe several small implementation details that are important for discouraging unhealthy competition between the generator and discriminator. Finally, we suggest a new metric for evaluating GAN results, both in terms of image quality and variation.

via nvidia

Share this story

No comments yet.

Leave a Reply

btt