Modify transforms.py from torchvision, in order to do the same fixed or random transformation on multiple images simultaneously for data augmentation
-
Updated
Aug 9, 2018 - Python
Modify transforms.py from torchvision, in order to do the same fixed or random transformation on multiple images simultaneously for data augmentation
Pytorch implementation of UNet for converting aerial satellite images into google maps kinda images.
My solutions to the projects assigned for the Udacity Computer Vision Nanodegree
Vanilla GAN implementation on MNIST dataset using PyTorch
Recreate a style transfer-uses 19 layer VGG Network- method to mix photo of 'high' Elon Musk and Picasso 's painting, The Dream.
VGG | Resnet | Alexnet | Squeezenet | Densenet | Inception
PyTorch | Flask | Google Colab | Kaggle
Implementation of paper :Lightweight Deep Convolutional Network for Tiny Object Recognition
Personal projects for the Udacity Computer Vision Nanodegree
Introduction to Deep Learning and Transfer Learning using MNIST and Fashion MNIST dataset
A Swift Wrapper for PyTorch and Torchvision.
This is a repository which looks at Deep learning tutorial with Pytorch, with various important functions and documentation.
Attempts to solve CAPTCHA images using Computer Vision
Extension of torchvision-tramsforms to handle simultaneous transform of input and ground-truth when the latter is an image
Anime head detection using faster-rcnn-fpn
Build a Python application that can train an image classifier on a dataset, then predict new images using the trained model.
PyTorch 3D video classification models pre-trained on 65 million Instagram videos
Add a description, image, and links to the torchvision topic page so that developers can more easily learn about it.
To associate your repository with the torchvision topic, visit your repo's landing page and select "manage topics."