aaronmarkham / nano inference notes

Created June 13, 2019 19:33

https://cdn-images-1.medium.com/max/800/1*x5lnmcK-PvjDeXZAfMEsRQ.jpeg

aaronmarkham / inception_predict.py

Created February 14, 2019 17:51

prediction example (from wine_detector on raspberry pi tutorial)

	# inception_predict.py

	import mxnet as mx
	import numpy as np
	import cv2, os, urllib
	from collections import namedtuple
	Batch = namedtuple('Batch', ['data'])

	# Load the symbols for the networks
	with open('synset.txt', 'r') as f:

aaronmarkham / gist:b3d0c715abca92ccc4b79ed0f19d1916

Last active July 10, 2020 16:56

Raspberry Pi MXNet setup

	Requirements:
	Raspberry Pi 3B with Stretch.

	If you have an existing installation, it must be upgraded to Stretch.
	Follow these directions to upgrade: https://www.datenreise.de/en/raspberry-pi-raspbian-update-update-jessie-to-stretch/

	Format your SD card with SD Card Formatter.
	Download, unzip, then copy contents of the NOOBS (network install) zip file to SD card.
	Boot up the Pi and follow the prompts to install the headless Raspbian.
	Login to the pi with user `pi` and password `raspberry`.

aaronmarkham / install-template.md

Last active October 16, 2018 16:57

Installation Instructions for MXNet-$binding on $OS

The following guide will help you install MXNet-$binding on $OS.

Prerequisites

The following are required prerequisites:

aaronmarkham / Git setup

Last active August 12, 2021 18:03

	# To setup initial repo
	export USER=aaronmarkham
	export REPO=amazon-sagemaker-examples
	export REPO_URL=https://github.com/aws/amazon-sagemaker-examples
	git clone --recursive https://github.com/${USER}/${REPO}.git ${USER}-${REPO}
	cd ${USER}-${REPO}
	git remote add upstream ${REPO_URL}


	# Need to add user/email and auth settings steps

aaronmarkham / gluon-export-model

Created January 30, 2018 22:58

shows a problem with exporting then importing a model in gluon

	import mxnet as mx
	from mxnet.test_utils import download
	from mxnet.gluon.model_zoo import vision as models
	gpus = 0
	contexts = [mx.gpu(i) for i in range(gpus)] if gpus > 0 else [mx.cpu()]

	deep_dog_net = models.squeezenet1_1(prefix='deep_dog_', classes=2)
	deep_dog_net.collect_params().initialize(ctx=contexts)

	download('https://apache-mxnet.s3-accelerate.amazonaws.com/gluon/models/deep-dog-5a342a6f.params',

aaronmarkham / alexnet_codes

Created April 4, 2017 23:43

This list of codes is useful for looking up results from a neural network trained on AlexNet

	{
	0: 'tench, Tinca tinca',
	1: 'goldfish, Carassius auratus',
	2: 'great white shark, white shark, man-eater, man-eating shark, Carcharodon carcharias',
	3: 'tiger shark, Galeocerdo cuvieri',
	4: 'hammerhead, hammerhead shark',
	5: 'electric ray, crampfish, numbfish, torpedo',
	6: 'stingray',
	7: 'cock',
	8: 'hen',

aaronmarkham / gist:dcdb284065c9ea4569214bcb0ca3a858

Created March 1, 2017 02:34

Caffe2 relu op test output

	Trying example: test_relu(self=<__main__.TestRelu testMethod=test_relu>, X=array([[-0.7635088 ],
	[-0.24276257]], dtype=float32), gc=, dc=[])
	Trying example: test_relu(self=<__main__.TestRelu testMethod=test_relu>, X=array([[ 0. , 1. ],
	[ 0.20600842, -0.92744243]], dtype=float32), gc=, dc=[])
	Trying example: test_relu(self=<__main__.TestRelu testMethod=test_relu>, X=array([ 0.22169138, -0. , 0. , 0. ], dtype=float32), gc=, dc=[])
	Trying example: test_relu(self=<__main__.TestRelu testMethod=test_relu>, X=array([-0.], dtype=float32), gc=, dc=[])
	Trying example: test_relu(self=<__main__.TestRelu testMethod=test_relu>, X=array([ 0.], dtype=float32), gc=, dc=[])
	Trying example: test_relu(self=<__main__.TestRelu testMethod=test_relu>, X=array([[-0.28297934],
	[ 0.20971532],
	[ 0. ]], dtype=float32), gc=, dc=[])