Skip to content

Instantly share code, notes, and snippets.

View bodokaiser's full-sized avatar
😀
Happy to be here!

Bodo Kaiser bodokaiser

😀
Happy to be here!
103 followers · 60 following
View GitHub Profile
@bodokaiser
bodokaiser / runtime.ipynb
Last active June 29, 2018 12:56
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@bodokaiser
bodokaiser / pi.ipynb
Created June 27, 2018 12:09
Loading
Sorry, something went wrong. Reload?
Sorry, we cannot display this file.
Sorry, this file is invalid so it cannot be displayed.
@bodokaiser
bodokaiser / win-tfrecord.py
Created October 20, 2017 09:50
import numpy as np
import tensorflow as tf
SIZE = int(64e6)
def _bytes_feature(value):
return tf.train.Feature(bytes_list=tf.train.BytesList(value=value))
@bodokaiser
bodokaiser / zshenv
Created October 13, 2017 14:24
export PYTHON_CONFIGURE_OPTS=--enable-framework
export EDITOR=vim
export CLICOLOR=1
export LANG=en_US.UTF-8
@bodokaiser
bodokaiser / grid.py
Last active September 24, 2017 09:29
How to construct a 3d grid in tensorflow (equivalent functions exist in numpy).
import tensorflow as tf
# volume shape: H x W x D
# cartesian notation (x,y):
# (0,0) (1,0) (2,0) ... (W-1,0)
# (0,1) (1,1) (2,1) ... (W-1,1)
# index notation (i,j):
# (0,0) (0,1) (0,2) ... (0,W-1)
@bodokaiser
bodokaiser / project-3d.py
Created September 21, 2017 07:46
project 3d volumes along each axes.
import math
import numpy as np
from matplotlib import pyplot as plt
from matplotlib.widgets import Slider
def show_volumes_projection(volumes):
n = len(volumes)
@bodokaiser
bodokaiser / bibtex.html
Created May 21, 2017 13:35
<html>
<head></head>
<body>
<ul></ul>
<script>
const PARSER = 'https://raw.githubusercontent.com/ORCID/bibtexParseJs/master/bibtexParse.js'
fetch(PARSER)
.then(res => res.text())
.then(eval)
@bodokaiser
bodokaiser / segnet.prototxt
Created April 21, 2017 12:51
https://github.com/alexgkendall/SegNet-Tutorial/blob/master/Models/segnet_train.prototxt
name: "VGG_ILSVRC_16_layer"
layer {
name: "data"
type: "DenseImageData"
top: "data"
top: "label"
dense_image_data_param {
source: "/SegNet/CamVid/train.txt" # Change this to the absolute path to your data file
batch_size: 4 # Change this number to a batch size that will fit on your GPU
shuffle: true
@bodokaiser
bodokaiser / resnet101.prototxt
Last active April 20, 2017 09:17
https://github.com/KaimingHe/deep-residual-networks/blob/master/prototxt/ResNet-101-deploy.prototxt
name: "ResNet-101"
input: "data"
input_dim: 1
input_dim: 3
input_dim: 224
input_dim: 224
layer {
bottom: "data"
top: "conv1"
@bodokaiser
bodokaiser / deeplabv2-resnet.prototxt
Last active April 20, 2017 09:17
http://liangchiehchen.com/projects/DeepLabv2_resnet.html
name: "${NET_ID}"
layer {
name: "data"
type: "ImageSegData"
top: "data"
top: "label"
#top: "data_dim"
include {
phase: TRAIN