Tawn Kramer tawnkramer

keyboard masher, bit twiddler

tawnkramer / ps3 drivers

Last active April 2, 2019 22:46

	adapted from http://wiki.tekkotsu.org/index.php/Sony_PlayStation_Eye_driver_install_instructions

	sudo -s
	cd /usr/src
	apt-get update
	apt-get install -y build-essential kernel-package linux-source libssl-dev
	tar --bzip2 -xvf linux-source-*.tar.bz2
	ln -s `find . -maxdepth 1 -type d -name "linux-source-*"` linux

	#PS3 Eye Drivers

tawnkramer / intel path follow redme.txt

Last active April 25, 2019 03:29

Intel RealSense T265 Path follower on Donkey

	Setup on the pi:

	git clone https://github.com/tawnkramer/donkey donkey_tkramer
	cd donkey_tkramer
	git checkout dev
	pip3 uninstall donkeycar
	pip3 install .[pi]
	donkey createcar --path ~/follow --template path_follower
	cd ~/follow
	python3 manage.py drive

tawnkramer / keras_quant.py

Created May 3, 2019 22:55 — forked from rocking5566/keras_quant.py

Quantization aware training in keras

	import numpy as np
	import tensorflow as tf
	from tensorflow.keras.datasets import mnist
	from tensorflow.keras.utils import to_categorical
	from tensorflow.keras.models import Sequential
	from tensorflow.keras.layers import Dense, Activation, Conv2D, Flatten
	from tensorflow.keras.optimizers import RMSprop

	# download the mnist to the path '~/.keras/datasets/' if it is the first time to be called
	# X shape (60,000 28x28), y shape (10,000, )

tawnkramer / minimal_nano_cfg.py

Created June 17, 2019 04:01

tawnkramer / train_imagenet.py

Created January 1, 2020 19:13

	"""
	Usage:
	train_imagenet.py --model="mymodel.h5" --data="/data/ImageNetDir" --resume

	Note:

	The idea here is to pre-train a network on imagenet, or some large corpus, and then transfer weights.
	I used https://github.com/mf1024/ImageNet-Datasets-Downloader.git to create a large dataset:
	`cd ImageNet-Datasets-Downloader
	python downloader.py -data_root /data/ImageNetData -number_of_classes 1000 -images_per_class 1000`

tawnkramer / sdsim_racing.txt

Last active April 10, 2020 07:42

	* linux ubuntu only now

	Get donkeycar, if you don't have it. If you do, just checkout dev.
	* cd ~/projects
	* git clone https://github.com/autorope/donkeycar
	* cd donkeycar
	* git checkout master

	Install conda. Optional but recommended
	* wget https://repo.anaconda.com/miniconda/Miniconda3-latest-Linux-x86_64.sh

tawnkramer / racer.py

Last active September 24, 2021 10:43

	"""
	Script to drive a keras TF model with the Virtual Race Environment.

	Usage:
	racer.py (--model=<model>) (--host=<ip_address>) (--name=<car_name>)

	Options:
	-h --help Show this screen.
	"""

tawnkramer / simple_cv_racer.py

Last active May 23, 2021 09:49

	#!/usr/bin/env python3
	"""

	Usage:
	simple_cv_racer.py --name=your_name


	Options:
	-h --help Show this screen.
	"""