vkkhare’s gists

vkkhare / train.kt

Created April 1, 2020 07:55

pytorch testing module

	val script = Module.load("torchscript.pt")
	val batchSize = IValue.from(
	Tensor.fromBlob(longArrayOf(1), longArrayOf(1, 1))
	)
	val lr = IValue.from(
	Tensor.fromBlob(floatArrayOf(0.01f), longArrayOf(1, 1))
	)
	val w1 = IValue.from(
	Tensor.fromBlob(
	FloatArray(392 * 784) { Random.nextFloat() / sqrt(784F) },

vkkhare / MainActivity.kt

Last active March 4, 2020 10:42

testing pytorch mobile for training on android

	package org.openmined.KotlinSyft

	import android.os.Bundle
	import com.google.android.material.snackbar.Snackbar
	import androidx.appcompat.app.AppCompatActivity
	import android.view.Menu
	import android.view.MenuItem

	import kotlinx.android.synthetic.main.activity_main.*

vkkhare / pytorch.py

Last active November 24, 2018 15:28

	from __future__ import print_function, division

	import torch
	import torch.nn as nn
	import torch.optim as optim
	from torch.optim import lr_scheduler
	import numpy as np
	import torchvision
	from torchvision import datasets, models, transforms
	import matplotlib.pyplot as plt

vkkhare / train.py

Created October 11, 2018 14:41

	def train(model, resnet,device, train_loader, optimizer_res, optimizer_att, epoch,losslist,loss,lmb):
	for param in model.parameters():
	param.requires_grad = False
	for param in resnet.parameters():
	param.requires_grad = True
	model.eval()
	resnet.train()
	loss_l = torch.zeros(1,dtype=torch.float32).to(device)
	b_idx = 0
	for x in train_loader:

vkkhare / INSTALL.md

Created June 26, 2018 07:43 — forked from arya-oss/INSTALL.md

Ubuntu 16.04 Developer Tools installation

Ubuntu 16.04 Developer Tools Installation

First things first !

sudo apt update
sudo apt upgrade

sudo apt-get install build-essential git

vkkhare / mips.s

Last active February 13, 2018 14:46

vkkhare / python3.5

Last active January 17, 2018 15:14

	import numpy as np
	import random
	import sklearn
	from sklearn.datasets.samples_generator import make_regression
	import pylab
	from scipy import stats

	def gradient_descent(alpha, x, y, ep, max_iter):
	converged = False
	iter = 0