An implementation of Efficientnet in PyTorch
Pytorch
B0:
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| call plug#begin("~/.vim/plugged") | |
| " Theme | |
| Plug 'arcticicestudio/nord-vim' | |
| " Language Client | |
| Plug 'neoclide/coc.nvim', {'branch': 'release'} | |
| let g:coc_global_extensions = ['coc-emmet', 'coc-css', 'coc-html', 'coc-json', 'coc-prettier', 'coc-tsserver', 'coc-python'] | |
| " TypeScript Highlighting | |
| Plug 'vim-airline/vim-airline' | |
| Plug 'vim-airline/vim-airline-themes' |
SharanSMenon
/ opencl_matrix_multiply.ipynb
Created
April 19, 2022 00:47
Matrix Multiplication with OpenCL. Performance comparison test.
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
SharanSMenon
/ MetalAdder.h
Created
April 8, 2022 23:39
Adding in metal. Borrowed from the apple developer documentation.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| // | |
| // MetalAdder.h | |
| // MetalLearn1 | |
| // | |
| // Created by Sharan Sajiv Menon on 4/3/22. | |
| // | |
| #import <Foundation/Foundation.h> | |
| #import <Metal/Metal.h> | |
| #ifndef MetalAdder_h |
SharanSMenon
/ vulkano_vector_scalar_product.rs
Created
March 23, 2022 01:12
Vulkano 0.29 Vector-Scalar Product program. Multiplies a vector of 65K numbers by 12 using the GPU device. Vulkano and Vulkano shaders required for this.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| extern crate vulkano; | |
| extern crate vulkano_shaders; | |
| use vulkano::{ | |
| sync, | |
| buffer::{BufferUsage, CpuAccessibleBuffer}, | |
| command_buffer::{AutoCommandBufferBuilder, CommandBufferUsage}, | |
| device::{ | |
| physical::{PhysicalDevice}, | |
| QueueCreateInfo, |
SharanSMenon
/ Accelerate_sgemm.cpp
Created
February 26, 2022 00:01
SGEMM with Accelerate Frame in C++ (macOS)
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
| #include<stdio.h> | |
| #include<iostream> | |
| #include<Accelerate/Accelerate.h> | |
| #include <random> | |
| #include <stdlib.h> | |
| #include <vector> | |
| #include <chrono> | |
| void fill(float *a, int n) { | |
| for (int i = 0; i < n; i++) { |
SharanSMenon
/ efficientnet-pytorch.md
Last active
November 10, 2023 04:00
EfficientNet Implementation PyTorch
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
SharanSMenon
/ README.MD
Last active
December 5, 2021 22:40
A simple implementation of evolution strategies to train a classification network. Based on https://openai.com/blog/evolution-strategies/
Based on this paper: https://arxiv.org/pdf/1703.03864.pdf
More info can be found in this blog post: https://openai.com/blog/evolution-strategies/
Based on DCGAN from this paper: https://arxiv.org/pdf/1511.06434.pdf
Implementation of SRGAN in PyTorch. Superresolves to 4x
Based on this paper: https://arxiv.org/pdf/1609.04802.pdf
Model is to be trained for 150 epochs.
NewerOlder