Goals: Add links that are reasonable and good explanations of how stuff works. No hype and no vendor content if possible. Practical first-hand accounts of models in prod eagerly sought.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
docker run -d \ | |
--name=crashplan-pro \ | |
-h $HOSTNAME \ | |
-e USER_ID=0 \ | |
-e GROUP_ID=0 \ | |
-e TZ=“America/Los_Angeles” \ | |
-p 5800:5800 \ | |
-p 5900:5900 \ | |
-v /share/CACHEDEV1_DATA/Container/config/crashplanpro:/config:rw \ | |
-v /share/CACHEDEV1_DATA:/storage:rw \ |
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# git clone from https://github.com/tkarras/progressive_growing_of_gans | |
# download the snapshot from their Google drive | |
# use the following code in the same directory to generate random faces | |
import os | |
import sys | |
import time | |
import glob | |
import shutil | |
import operator | |
import theano |
https://gist.github.com/victor-shepardson/5b3d3087dc2b4817b9bffdb8e87a57c4
I'm using Ubuntu 16.04 with a GTX 1060
Notes from arXiv:1611.07004v1 [cs.CV] 21 Nov 2016
- Euclidean distance between predicted and ground truth pixels is not a good method of judging similarity because it yields blurry images.
- GANs learn a loss function rather than using an existing one.
- GANs learn a loss that tries to classify if the output image is real or fake, while simultaneously training a generative model to minimize this loss.
- Conditional GANs (cGANs) learn a mapping from observed image
x
and random noise vectorz
toy
:y = f(x, z)
- The generator
G
is trained to produce outputs that cannot be distinguished from "real" images by an adversarially trained discrimintor,D
which is trained to do as well as possible at detecting the generator's "fakes". - The discriminator
D
, learns to classify between real and synthesized pairs. The generator learns to fool the discriminator. - Unlike an unconditional GAN, both th
Code for Keras plays catch blog post
python qlearn.py
- Generate figures
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
#!/usr/bin/env python | |
try: | |
# for python newer than 2.7 | |
from collections import OrderedDict | |
except ImportError: | |
# use backport from pypi | |
from ordereddict import OrderedDict | |
import yaml |
- Install the nbconvert package, though you probably already have it if you are using jupyter.
- Put the
nb2md
script below in your path and make executable - Add the following to your
.gitattributes
file, which can be in your home directory (usenb2md
for all projects) or in the root of your project:
*.ipynb diff=nb2md
- Run
##VGG16 model for Keras
This is the Keras model of the 16-layer network used by the VGG team in the ILSVRC-2014 competition.
It has been obtained by directly converting the Caffe model provived by the authors.
Details about the network architecture can be found in the following arXiv paper:
Very Deep Convolutional Networks for Large-Scale Image Recognition
K. Simonyan, A. Zisserman
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
""" | |
Minimal character-level Vanilla RNN model. Written by Andrej Karpathy (@karpathy) | |
BSD License | |
""" | |
import numpy as np | |
# data I/O | |
data = open('input.txt', 'r').read() # should be simple plain text file | |
chars = list(set(data)) | |
data_size, vocab_size = len(data), len(chars) |
NewerOlder