Unai uelordi01

How to install CUDA / cuDNN / TensorRT on Ubuntu

Install NVIDIA drivers

Update & upgrade

sudo apt update && sudo apt upgrade

Remove previous NVIDIA installation

DISCLAIMER

This gist is unofficial. It was created for personal use but have kept it public in case it would be of use to others. This document is not updated regularly and may not reflect the current status of the CUDA backend.

Install dlib and face_recognition on a Raspberry Pi

Instructions tested with a Raspberry Pi 2 with an 8GB memory card. Probably also works fine on a Raspberry Pi 3.

Steps

Download the latest Raspbian Jessie Light image. Earlier versions of Raspbian won't work.

Write it to a memory card using Etcher, put the memory card in the RPi and boot it up.

How to install virtualenv:

Install pip first

sudo apt-get install python3-pip

Then install virtualenv using pip3

sudo pip3 install virtualenv

	#!/bin/bash
	TENSORFLOW_DIR=/home/VICOMTECH/uelordi/repos/tensorflow
	MODEL_NAME=quantized_face_graph.pb
	arch=armeabi-v7a
	ANDROID_PROJ=/home/VICOMTECH/uelordi/projects/SwitchTrackingEngine/kanvas_tracker/kt/tools/Deep-learning-tools/android/TFFaceDetection
	NATIVE_LIB_DIR=${ANDROID_PROJ}/app/src/main/jniLibs/$arch
	JAVA_LIBRARY_DIR=${ANDROID_PROJ}/app/libs

	#APPLY SELECTIVE REGISTRATION:
	OLD_PWD=$(pwd)

	toco \
	--input_file=frozen_output.pb \
	--output_file=optimized_graph_seg.lite \
	--input_format=TENSORFLOW_GRAPHDEF \
	--output_format=TFLITE \
	--input_shape=1024,2048,3 \
	--input_array=Placeholder \
	--output_array=Reshape_1 \
	--inference_type=FLOAT \
	--input_type=FLOAT

	// This file was autogenerated by print_selective_registration_header.py
	#ifndef OPS_TO_REGISTER
	#define OPS_TO_REGISTER

	namespace {
	constexpr const char* skip(const char* x) {
	return (x) ? (x == ' ' ? skip(x + 1) : x) : x;
	}

	constexpr bool isequal(const char* x, const char* y) {

	// callback4.cpp - C++11 Lambda Callback

	// To build:
	// g++ -std=c++11 callback4.cpp

	// Situation: A "Caller" class allows another class "Callee"
	// to connect to it via callback. How to implement this?

	// A C++11 lambda function can be used.

	bazel build -c opt //tensorflow/contrib/android:libtensorflow_inference.so \
	--crosstool_top=//external:android/crosstool \
	--host_crosstool_top=@bazel_tools//tools/cpp:toolchain --cpu=armeabi-v7a