implementation-of-research-paper topic
Rough-Sketch-Simplification-Using-FCNN
This is a PyTorch implementation of the the Paper by Simo-Sera et.al. on Cleaning Rough Sketches using Fully Convolutional Neural Networks.
Sketch2Color-anime-translation
Given a simple anime line-art sketch the model outputs a decent colored anime image using Conditional-Generative Adversarial Networks (C-GANs) concept.
pytorch-multi-class-focal-loss
An (unofficial) implementation of Focal Loss, as described in the RetinaNet paper, generalized to the multi-class case.
Papers-in-100-Lines-of-Code
Implementation of papers in 100 lines of code.
Custom_MaskRCNN
Custom Mask R-CNN for object detection and instance segmentation on Keras and TensorFlow
pytorch-fpn
PyTorch implementations of some FPN-based semantic segmentation architectures: vanilla FPN, Panoptic FPN, PANet FPN; with ResNet and EfficientNet backbones.
pytorch_paper_implementations
Deep Learning Paper Implementations in PyTorch
botanical-trees
Unofficial implementation of the paper "Learning to reconstruct botanical trees from single images"