bsridatta/Speech-and-Speaker-Recognition-DT2119-VT19-1

Stars
3
Rank 3,963,521 (Top 79 %)
Language
Jupyter Notebook
Created over 5 years ago
Updated over 3 years ago

bsridatta/Speech-and-Speaker-Recognition-DT2119-VT19-1

bsridatta

There are no reviews yet. Be the first to send feedback to the community and the maintainers!

Speech-and-Speaker-Recognition-DT2119-VT19-1 Project Oriented Course at KTH

Rotated-Object-Detection

Tiny ResNet inspired FPN network (<2M params) for Rotated Object Detection using 5-parameter Modulated Rotation Loss

Cone-Detection

Cone Detection using dark flow YOLOv2 for formula student. Custom Dataset from google images

Jupyter Notebook

Panoptic-Segmentaion-AIWB

Panoptic Segmentation - Internship @ AI without Borders 2019

HPE3D

Master Thesis in Unsupervised 3D Human Pose Estimation

Jupyter Notebook

Timely

Full-Fledged Portal officially made for the faculty of Amrita

wav2letter-Swedish

Wav2letter++ on Swedish corpus

Awesome-3D-Human-Pose-Estimation

A collection of 3D Human Pose Estimation papers

Rethinking-Binarized-Neural-Network-Optimization

Reproduction of "Latent Weights Do Not Exist: Rethinking Binarized Neural Network Optimization" for the Reproducibility challenge@NeurIPS19

Jupyter Notebook

awesome_human_pose_estimation

Interesting papers and datasets for the task of Human Pose Estimation (3D)

Data-Intensive-Computing

ID2221 Data Intensive Computing Platforms @ KTH

Jupyter Notebook

ReinforcementLearning

KTH EL2805 Reinforcement Learning

Deep-Image-Colorization

Colorizing B&W images using autoencoder by fusing encoder embedding with features extracted from pre-trained InceptionNet