Projects

latest | popular

Filter by
U^2-Net
The code for our newly accepted paper in Pattern Recognition 2020: "U^2-Net: Going Deeper with Nested U-Structure for Salient Object Detection."
object-detection salient-object-detection unet computer-vision
Big GANs Are Watching You
We demonstrate that object saliency masks for GAN-produced images can be obtained automatically with BigBiGAN.
generative-adversarial-networks unet object-saliency big-gan
Segmentation Models
Segmentation models with pretrained backbones. Keras and TensorFlow Keras.
model-store models unet computer-vision
Unet Model for Image Segmentation With EfficientNet Encoder
Implemented using tensorflow 2.2.0 with custom train and test step.
unet efficientnet computer-vision segmentation
A U-Net Based Discriminator for Generative Adversarial Networks
U-Net based architecture allows to provide detailed per-pixel feedback to the generator while maintaining the global coherence of synthesized images.
generative-adversarial-networks unet discriminator cvpr-2020
Overriding train/test steps for custom training in TF2.2
Custom training loops in tf.keras can't make use of things like callbacks,etc. by default and you have to write one for yourself. How to overcome it?
tensorflow custom-training-loops unet bone-drr
Introduction to Image Inpainting With Deep Learning
In this article, we are going to learn how to do “image inpainting”, i.e. fill in missing parts of images precisely using deep learning.
inpainting computer-vision deep-learning wandb
DeepWay: Autonomous navigation for blind.
I have tried to make something which can be used by blind people to navigate around the streets. Have a look at the video and GitHub repo for details.
computer-vision arduino jetson-nano unet
U-Net Deep Learning Colorization of Greyscale Images
This article describes experiments training a neural network to generate 3 channel colour images from single channel greyscale images using deep learning.
colorization unet computer-vision tutorial
projects 1 - 9 of 9
Topic experts
Share a project
Share something you or the community has made with ML.