RahulBhalley

🏠

Working from home

I like to build artificial intelligence softwares

RahulBhalley / aarch64_amx.py

Created December 31, 2021 09:54 — forked from dougallj/aarch64_amx.py

	# IDA (disassembler) and Hex-Rays (decompiler) plugin for Apple AMX
	#
	# WIP research. (This was edited to add more info after someone posted it to
	# Hacker News. Click "Revisions" to see full changes.)
	#
	# Copyright (c) 2020 dougallj


	# Based on Python port of VMX intrinsics plugin:
	# Copyright (c) 2019 w4kfu - Synacktiv

RahulBhalley / model.swift

Created January 30, 2020 07:40 — forked from kongzii/model.swift

Example of saving trained weights of model in the Swift For Tensorflow

	import Foundation
	import Python
	import TensorFlow

	public struct MyModel : Layer {
	public var conv1d: Conv1D<Float>
	public var dense1: Dense<Float>
	public var dropout: Dropout<Float>
	public var denseOut: Dense<Float>

RahulBhalley / min-char-rnn.py

Created June 2, 2018 16:03 — forked from karpathy/min-char-rnn.py

Minimal character-level language model with a Vanilla Recurrent Neural Network, in Python/numpy

	"""
	Minimal character-level Vanilla RNN model. Written by Andrej Karpathy (@karpathy)
	BSD License
	"""
	import numpy as np

	# data I/O
	data = open('input.txt', 'r').read() # should be simple plain text file
	chars = list(set(data))
	data_size, vocab_size = len(data), len(chars)

RahulBhalley / hyperparameters_2-snippet.py

Last active March 11, 2017 16:41

XOR gate solution to my post @ https://rahulbhalley.github.io/posts/2017-02/neural-networks-explained.html

	# 2nd layer hyperparameters of our network
	w = tf.Variable([[1], [-2]]) # weights between hidden layer and output layer.
	b = tf.Variable([[0], [0], [0], [0]]) # biases for output units.

RahulBhalley / hyperparameters_1-snippet.py

Last active March 11, 2017 16:41

XOR gate solution to my post @ https://rahulbhalley.github.io/posts/2017-02/neural-networks-explained.html

	import tensorflow as tf

	# 1st layer hyperparameters of our network
	X = tf.Variable([[0, 0], [0, 1], [1, 0], [1, 1]]) # inputs where the rows correspond to a single input.
	W = tf.Variable([[1, 1], [1, 1]]) # weights between hidden layer and input layer.
	c = tf.Variable([[0], [-1]]) # biases for hidden units.

RahulBhalley / feedforward_2-snippet.py

Last active March 11, 2017 16:42

XOR gate solution to my post @ https://rahulbhalley.github.io/posts/2017-02/neural-networks-explained.html

	# 2nd feedforward propagation
	a_XW_c_w = tf.matmul(a_XW_c, w)
	a_XW_c_w_b = tf.add(a_XW_c_w, b)

	init = tf.global_variables_initializer()

	# Launch the TensorFlow graph session
	with tf.Session() as sess:
	# initialize all the variables
	sess.run(init)

RahulBhalley / feedforward_1-snippet.py

Last active March 11, 2017 13:28

XOR gate solution to my post @ https://rahulbhalley.github.io/posts/2017-02/neural-networks-explained.html