Akash James's repositories
Hermes-Deepstream
Hermes is a Wildfire detection system that utilizes Computer Vision and is accelerated using NVIDIA Deepstream
Activity-Recognition-TensorRT
3D ResNet Video Classification accelerated by TensorRT
YOLOv4-OpenCV-CUDA-DNN
Run YOLOv4 directly with OpenCV using the CUDA enabled DNN module.
YOLOv4-Deepstream
YOLOv4 accelerated wtih TensorRT and multi-stream input using Deepstream
yolov8-deepstream-6-1
YOLOv8 by Ultralytics in DeepStream 6.1
Centerface-Deepstream
Centerface ONNX accelerated with Deepstream 5.1
ShredFPSOpponents
Pipeline Game Input to YOLOv3 Object Detection to detect opponents.
vector-advanced-ai
Vector with Advanced AI compatibilities
gemma-nanoowl-whisper
Repository that combines Zero-Shot object detection, LLMs and ASR for a whack demo
Photo-Realistic-Image-Stylization
Whitening and Colorization Transform from the paper "A Closed-form Solution to Photorealistic Image Stylization"
FasterRCNN-TLT-Triton
End-to-end FasterRCNN training and deployment with TLT 3.0, Deepstream and Triton Inference Server
yolov5-autoannotator
Annotate datasets with a semi-trained or fully trained YOLOv5 model
aegir-core
NASA Space Apps 2021 Submission for AI/ML plastic marine debris problem statement
Lightweight-face-detection-CenterNet
Lightweight-face-detection-CenterNet
keras-onnx
Convert tf.keras/Keras models to ONNX
NSAC-NULLPointers
Entry for NASA Space Apps Challenge 2020 | Spot that Fire V3.0
nvidia-tlt-get-started
Repository with resources to get started with NVIDIA's Transfer Learning Toolkit 3.0
Quantum-Programming-Exps
My experiments with Quantum Programming
retinaface-onnx
RetinaFace ONNX Export and Inference
yolov7-deepstream-6-1
YOLOv7 with NVIDIA DeepStream 6.1
FastSpeech2
An implementation of Microsoft's "FastSpeech 2: Fast and High-Quality End-to-End Text to Speech"
nanoowl
A project that optimizes OWL-ViT for real-time inference with NVIDIA TensorRT.
RT-DETR-DeepStream
DeepStream 6.2 Repository with Detection Transformer
streamlink
Streamlink is a CLI utility which pipes video streams from various services into a video player
Transformer-TTS
A Pytorch Implementation of "Neural Speech Synthesis with Transformer Network"
TransformerTTS
🤖💬 Transformer TTS: Implementation of a non-autoregressive Transformer based neural network for text to speech.
vector-python-sdk
Anki Vector Python SDK