Ushma30

brain-segmentation-pytorch

U-Net implementation in PyTorch for FLAIR abnormality segmentation in brain MRI

Branch-Predictors

This repository consists of different types of branch predictors implemented throughout my course Computer Architecture which I undertook during my Master's in Fall 2018.

Cache-Simulator

This is a simulator to demonstrate the functionality of cache.

CNN-MobileNet-V1-implementation-on-AWS-FPGA-using-OpenCL

Increasing the accuracy of Convolutional Neural Networks (CNNs) has become a recent research focus in computer vision applications. Smaller CNN architectures like SqueezeNet and MobileNet can demonstrate accelerated performance on FPGAs and GPUs due to smaller model size and fewer network parameters. Implementation of CNNs on accelerators have two important benefits - GPUs provide thread-level parallelism to achieve higher throughput and FPGAs offer a customizable application-specific datapath. These two reasons make these platforms better suited for convolution like operations which involve huge data. This project aims to implement one such CNN architecture, MobileNet on an Image dataset in OpenCL, thereby comparing kernel execution time and memory bandwidth usage on FPGA and GPU

Dynamic-Branch-Predictor

Freeze-graph-from-Checkpoint

IAPC-Innovative-Assistance-for-Physically-Challenged

MobileNet-V1

MultiPE

This repository is a simple vector add based on hlslib

Vitis_Accel_Examples

Vitis_Accel_Examples

Ushma30/MobileNet-V1

Ushma30/brain-segmentation-pytorch

U-Net implementation in PyTorch for FLAIR abnormality segmentation in brain MRI

Ushma30/Branch-Predictors

This repository consists of different types of branch predictors implemented throughout my course Computer Architecture which I undertook during my Master's in Fall 2018.

Ushma30/Cache-Simulator

This is a simulator to demonstrate the functionality of cache.

Ushma30/CNN-MobileNet-V1-implementation-on-AWS-FPGA-using-OpenCL

Increasing the accuracy of Convolutional Neural Networks (CNNs) has become a recent research focus in computer vision applications. Smaller CNN architectures like SqueezeNet and MobileNet can demonstrate accelerated performance on FPGAs and GPUs due to smaller model size and fewer network parameters. Implementation of CNNs on accelerators have two important benefits - GPUs provide thread-level parallelism to achieve higher throughput and FPGAs offer a customizable application-specific datapath. These two reasons make these platforms better suited for convolution like operations which involve huge data. This project aims to implement one such CNN architecture, MobileNet on an Image dataset in OpenCL, thereby comparing kernel execution time and memory bandwidth usage on FPGA and GPU

Ushma30/Dynamic-Branch-Predictor

Ushma30/Freeze-graph-from-Checkpoint

Ushma30/IAPC-Innovative-Assistance-for-Physically-Challenged

Ushma30/MultiPE

This repository is a simple vector add based on hlslib

Ushma30/Vitis_Accel_Examples

Vitis_Accel_Examples