Skip to content

Instantly share code, notes, and snippets.

@twmht
twmht / extract_ILSVRC.sh
Created December 28, 2020 06:27 — forked from BIGBALLON/extract_ILSVRC.sh
script for ImageNet data extract.
#!/bin/bash
#
# script to extract ImageNet dataset
# ILSVRC2012_img_train.tar (about 138 GB)
# ILSVRC2012_img_val.tar (about 6.3 GB)
# make sure ILSVRC2012_img_train.tar & ILSVRC2012_img_val.tar in your current directory
#
# https://github.com/facebook/fb.resnet.torch/blob/master/INSTALL.md
#
# train/
@twmht
twmht / pr.md
Created June 25, 2017 06:34 — forked from piscisaureus/pr.md
Checkout github pull requests locally

Locate the section for your github remote in the .git/config file. It looks like this:

[remote "origin"]
	fetch = +refs/heads/*:refs/remotes/origin/*
	url = [email protected]:joyent/node.git

Now add the line fetch = +refs/pull/*/head:refs/remotes/origin/pr/* to this section. Obviously, change the github url to match your project's URL. It ends up looking like this:

@twmht
twmht / DeepLearningFaces.md
Created June 8, 2017 09:19 — forked from jdsgomes/DeepLearningFaces.md
Deep Learning for Face Recognition

Deep Learning for Face Recognition (May 2016)

Popular architectures

  • FaceNet (Google)
    • They use a triplet loss with the goal of keeping the L2 intra-class distances low and inter-class distances high
  • DeepID (Hong Kong University)
    • They use verification and identification signals to train the network. Afer each convolutional layer there is an identity layer connected to the supervisory signals in order to train each layer closely (on top of normal backprop)
  • DeepFace (Facebook)
    • Convs followed by locally connected, followed by fully connected
#!/usr/bin/env python2
# coding: utf-8
import os,socket,threading,time
#import traceback
allow_delete = False
local_ip = socket.gethostbyname(socket.gethostname())
local_port = 8888
currdir=os.path.abspath('.')