I have trained custom DenseNet like lightweight model the increases the size of image by the factor of 2. I trained my model on an anime episode and used it on faces dataset. Here is comparison between bilinear interpolation and my super-resolution.

5 12

Our article on and , AI artists using their own paintings and drawings as datasets, is finally up on 🤖🎨

Written together with Alex Estorick

Read it here: https://t.co/1P6bUJfMIm

16 41

Two new datasets now avail from OpenTopography: Palmerston North, Manawatu-Whanganui, NZ 2018; Christchurch & Ashley River, Canterbury, NZ 2018 - 1100 sq km of data: https://t.co/Gjfy0DIZiT 📷 1: wind turbines in motion; 📷 2: lidar intensity, Waimakariri River

12 37

IntrA: 3D Intracranial Aneurysm Dataset for Deep Learning. https://t.co/Eyb6z2mArd

2 4

DiverseDepth predicts depth in a broader range of scenes, with more detail, than most depth models do in their best dataset. So they made a harder dataset.

DiverseDepth: Affine-invariant Depth Prediction Using Diverse Data

abs: https://t.co/wvy4FOzNsR

15 55

白面鸮头像生成器。 🦉
StyleGAN2の フィリオプシス画像生成
StyleGan2 finetune test。

It's hard to find a 4 GPU machine to run the algorithm:3。
Thx 2 for u dataset ,and anime portraits by

10 42

Some of the diversity in MUNIT samples (because of the dataset I use, some end up slightly blurry—not shown here)

0 1

Day 9 - Yellow (I know it's 24th...)
I visualized the CERA dataset from that lists Spaniards that are living abroad :) I consider it a personal dataset because I'm part of it

4 17

SciartNow day 22: Kidney. Geometry adapted from 's NLM3D dataset. Another bonus colour version! rendered in

6 20

Six new datasets now available from OpenTopography. CA sites: Sacramento–San Joaquin River Delta; Horseshoe Lake & Hilton Crk Fault near Mammoth Lakes; Antelope Valley Ranch. Idaho Batholith. Goat Rock Volcano, WA. Campeche, Mexico. https://t.co/zX5InOcfY8

14 33

Want to train deep networks to model 3D human pose and motion? AMASS is a new dataset with 45 hours of mocap - and growing – all in SMPL format. Tutorial code shows how to use AMASS for deep learning. To appear: data: https://t.co/FnHeQhM3C9

50 161

Finalizing my plots of paleo-topography, this one at the LGM (20000 years before present). Very soon, I hope that my paleo-topography datasets will be available for everyone!

30 157

Following
Rob Woodside's talk featuring Castle & Spit at yesterday re-found some DC datasets showing rollback of spit since 1946. Also Vegetation index mapping of saltmarsh behind spit demonstrating Carbon sequestration potential

1 4

Recognition of Ischaemia and Infection in Diabetic Foot Ulcers: Dataset and Techniques. https://t.co/Y8YRJEdu5T

6 2

For my new collaboration with & we are building a machine learning system which compares views of Charley's new 'green' painting to a custom image dataset on the political status of the colour green. Here's industrial farms, trash, and brand logos.

6 18

I finally finished a fancy word cloud using R/WordCloud2 using my Bibliometrix dataset of online journals 🧐 Quite enjoying NEANDERTHAL being splayed across the center! 😎

3 17

Structured3D: A Large Photo-realistic Dataset for Structured 3D Modeling. https://t.co/I19MWHPHuv

10 32

The Herbarium Challenge 2019 Dataset. https://t.co/eauczipRuT

1 7

New hand painting added to the still life dataset this morning.

0 8