pravn
Machine learner and parallel computing enthusiast. I work in Bird's Eye View Modelling in the context of autonomous vehicles.
Montreal, Canada
Pinned Repositories
cvae
HighwayLayerTest
Scratch notebook to use Highway layers
PatchGAN
Simple notebook to test patch gan kernel
pyramidal_rnns
Experiments to hack together a pyramidal bilstm from the listen, attend and spell paper
SuperResGANUnet
Attempt at creating larger images with the StackGAN concept
vae_draw
vae_ebgan_mnist
VAE EBGAN
vae_frey
Vanilla VAE Frey face generator
vaegan
GAN+VAE hybrid experiments
wasserstein_autoencoders
Implementation of Wasserstein Autoencoders
pravn's Repositories
pravn/vaegan
GAN+VAE hybrid experiments
pravn/pyramidal_rnns
Experiments to hack together a pyramidal bilstm from the listen, attend and spell paper
pravn/cvae
pravn/HighwayLayerTest
Scratch notebook to use Highway layers
pravn/PatchGAN
Simple notebook to test patch gan kernel
pravn/SuperResGANUnet
Attempt at creating larger images with the StackGAN concept
pravn/vae_ebgan_mnist
VAE EBGAN
pravn/wasserstein_autoencoders
Implementation of Wasserstein Autoencoders
pravn/BEGAN_MNIST
BEGAN experiments
pravn/bidirectional-rnn
Design a simple bi-RNN by hand
pravn/blog
pravn/deep-voice-conversion
Deep neural networks for voice conversion (voice style transfer) in Tensorflow
pravn/ebgan_mnist
EBGAN/VAE experiments with mnist
pravn/librispeech-alignments
Word alignments generated by the Montreal Forced Aligner for the Librispeech dataset
pravn/merlin
This is now the official location of the Merlin project.
pravn/MNIST_svhn_dataloader
General utils for dataloader and vis
pravn/numpy-100
100 numpy exercises (with solutions)
pravn/poker
Evaluate poker hands
pravn/Postnet
pravn/pravn.github.io
pravn/PyTorch_Speaker_Verification
PyTorch implementation of "Generalized End-to-End Loss for Speaker Verification" by Wan, Li et al.
pravn/Real-Time-Voice-Cloning
Clone a voice in 5 seconds to generate arbitrary speech in real-time
pravn/TensorRT
NVIDIA® TensorRT™, an SDK for high-performance deep learning inference, includes a deep learning inference optimizer and runtime that delivers low latency and high throughput for inference applications.
pravn/test_hugo
pravn/UltraLiDAR_nusc_waymo
pravn/vaegan_lsun
VAEGAN experiments with patchgan strategy
pravn/VideoPose3D
Efficient 3D human pose estimation in video using 2D keypoint trajectories
pravn/VisionMamba
Implementation of Vision Mamba from the paper: "Vision Mamba: Efficient Visual Representation Learning with Bidirectional State Space Model" It's 2.8x faster than DeiT and saves 86.8% GPU memory when performing batch inference to extract features on high-res images
pravn/voice_conversion
Some code from my voice conversion paper
pravn/wgan_mnist
WGAN wiith conv layers