aa1607’s gists

aa1607 / Deep Learning with Python 3 on ubuntu 16.04.sh

Created September 23, 2017 15:08 — forked from cbaziotis/Deep Learning with Python 3 on ubuntu 16.04.sh

	# This is inspired by the fantastic guide https://github.com/saiprashanths/dl-setup
	# I have just updated the python-related commands so that everything works in Python 3.
	# Tested on Xubuntu 16.04.

	# First of all let's update the repos:
	sudo apt-get update

	# Only if you have a CUDA-compatible Nvidia card, install CUDA.
	# Check on the Nvidia website what is the latest driver version which supports your card.
	# At the time of this writing it was 367.

aa1607 / layers_tied.py

Created September 15, 2017 22:23 — forked from dswah/layers_tied.py

Tied Convolutional Weights with Keras for CNN Auto-encoders

	from keras import backend as K
	from keras import activations, initializations, regularizers, constraints
	from keras.engine import Layer, InputSpec
	from keras.utils.np_utils import conv_output_length
	from keras.layers import Convolution1D, Convolution2D
	import tensorflow as tf

	class Convolution1D_tied(Layer):
	'''Convolution operator for filtering neighborhoods of one-dimensional inputs.
	When using this layer as the first layer in a model,

aa1607 / install-gpu-gce.sh

Created July 27, 2017 03:40 — forked from rahimnathwani/install-gpu-gce.sh

Set up a Google Cloud GPU instance for doing the exercises in course.fast.ai

	#!/bin/bash
	if ! dpkg-query -W cuda; then
	curl -O http://developer.download.nvidia.com/compute/cuda/repos/ubuntu1604/x86_64/cuda-repo-ubuntu1604_8.0.61-1_amd64.deb
	dpkg -i ./cuda-repo-ubuntu1604_8.0.61-1_amd64.deb
	fi
	apt-get update
	apt-get -y upgrade
	apt-get -y install tmux build-essential gcc g++ make binutils software-properties-common cuda unzip
	modprobe nvidia
	nvidia-smi

aa1607 / figure_grid.py

Created July 21, 2017 17:37 — forked from asross/figure_grid.py

A helper to plot grids of graphs in matplotlib.pyplot

aa1607 / keras_attention_wrapper.py

Created July 20, 2017 13:30 — forked from wassname/keras_attention_wrapper.py

A keras attention layer that wraps RNN layers.

	"""
	A keras attention layer that wraps RNN layers.

	Based on tensorflows [attention_decoder](https://github.com/tensorflow/tensorflow/blob/c8a45a8e236776bed1d14fd71f3b6755bd63cc58/tensorflow/python/ops/seq2seq.py#L506)
	and [Grammar as a Foreign Language](https://arxiv.org/abs/1412.7449).

	date: 20161101
	author: wassname
	url: https://gist.github.com/wassname/5292f95000e409e239b9dc973295327a
	"""