华德禹 deyuhua

ResNet-152 in Keras

This is an Keras implementation of ResNet-152 with ImageNet pre-trained weights. I converted the weights from Caffe provided by the authors of the paper. The implementation supports both Theano and TensorFlow backends. Just in case you are curious about how the conversion is done, you can visit my blog post for more details.

ResNet Paper:

Deep Residual Learning for Image Recognition.
Kaiming He, Xiangyu Zhang, Shaoqing Ren, Jian Sun
arXiv:1512.03385

Competitive Machine Learning

feature engineering (most important by far)!!!!!
simple models
overfitting leaderboard
ensembling

predict the right thing!
build pipeline and put something on the leaderboard
allocate time to play with data, explore
make heavy use of forums
understand subtleties of algos, know what tool to use when

Default

Powerlevel10k

tmux shortcuts & cheatsheet

start new:

tmux

start new with session name:

tmux new -s myname

	General Nanodegree Information
	Nanodegrees Programs: https://www.udacity.com/nanodegree
	Nanodegree Plus (job guarantee): https://www.udacity.com/nanodegree/plus
	UConnect (weekly in-person study sessions): https://www.udacity.com/uconnect

	Courses on Udacity
	Machine Learning Engineer Nanodegree by Google (Currently Available): https://www.udacity.com/course/machine-learning-engineer-nanodegree-by-google--nd009
	Artificial Intelligence for Robots (Free Course) https://www.udacity.com/course/artificial-intelligence-for-robotics--cs373
	Intro to Statistics (Free Course) https://www.udacity.com/course/intro-to-statistics--st101
	Deep Learning (Free Course) https://www.udacity.com/course/deep-learning--ud730

	import dlib
	import cv2

	detector = dlib.simple_object_detector("detector.svm")

	cap = cv2.VideoCapture(0)

	while(True):
	# Capture frame-by-frame
	ret, frame = cap.read()

	#! /usr/bin/env bash

	# Get xv6 working with OSX Yosemite
	# Most things were here: https://doesnotscale.com/compiling-xv6-on-os-x-10-9/
	# You need homebrew installed to make this thing work
	brew tap homebrew/versions && brew install gcc48
	brew deps qemu \| xargs brew install
	export PATH=/usr/local/bin:$PATH
	export CC=/usr/local/bin/gcc-4.8
	brew install wget

	import scala.collection.mutable._

	class WorkerBee2 (val iterations : Int, var bins : ArrayBuffer[Int]) extends Runnable {

	def run() : Unit = {
	for(i <- 0 until iterations) {
	for (j <- 0 until bins.length) {
	// This compiles but misses some iterations:
	bins.update(j, bins(j) + 1)
	}