Skip to content

Instantly share code, notes, and snippets.

View Ac2zoom's full-sized avatar

Akshay Chalana Ac2zoom

149 followers · 650 following
View GitHub Profile
@vik-y
vik-y / Readme.txt
Created March 18, 2016 20:44
Eclipse ProR installation
How to Install ProR plugin into Eclipse
Open Eclipse
Go to Help->Install New Software
Click on Add new site
Add name as : ProR
link:
http://download.eclipse.org/rmf/updates/releases
@joschu
joschu / 1-cem-v0-writeup.md
Last active August 1, 2020 19:09

I used the cross-entropy method (an evolutionary algorithm / derivative free optimization method) to optimize small two-layer neural networks.

Code used to obtain these results can be found at the url https://github.com/joschu/modular_rl, commit 3324639f82a81288e9d21ddcb6c2a37957cdd361. The command line expression used for all the environments can be found in the text file below. Note that the same exact parameters were used for all tasks. The important parameters are:

  • hid_sizes=10,5: hidden layer sizes of MLP
  • extra_std=0.01: noise added to variance, see [1]
@emeeks
emeeks / graph.json
Created April 30, 2016 03:41
D3v4 Constraint-Based Layout
{"nodes": [{"id":"1","module":0,"i":0},{"id":"3","module":0,"i":1},{"id":"8","module":2,"i":2},{"id":"9","module":4,"i":3},{"id":"12","module":2,"i":4},{"id":"15","module":2,"i":5},{"id":"23","module":3,"i":6},{"id":"26","module":3,"i":7},{"id":"37","module":10,"i":8},{"id":"46","module":2,"i":9},{"id":"2","module":1,"i":10},{"id":"4","module":2,"i":11},{"id":"5","module":3,"i":12},{"id":"6","module":3,"i":13},{"id":"7","module":1,"i":14},{"id":"10","module":4,"i":15},{"id":"11","module":1,"i":16},{"id":"13","module":1,"i":17},{"id":"14","module":1,"i":18},{"id":"16","module":5,"i":19},{"id":"18","module":1,"i":20},{"id":"19","module":3,"i":21},{"id":"20","module":1,"i":22},{"id":"21","module":6,"i":23},{"id":"22","module":2,"i":24},{"id":"25","module":3,"i":25},{"id":"27","module":1,"i":26},{"id":"28","module":3,"i":27},{"id":"29","module":1,"i":28},{"id":"31","module":2,"i":29},{"id":"33","module":2,"i":30},{"id":"34","module":9,"i":31},{"id":"35","module":1,"i":32},{"id":"38","module":2,"i":33},{"id":"41",
@tony-gutierrez
tony-gutierrez / AWS_Single_LetsEncrypt.yaml
Last active March 7, 2024 11:29
AWS Elastic Beanstalk .ebextensions config for single instance free SSL using letsencrypt certbot and nginx. http://bluefletch.com/blog/domain-agnostic-letsencrypt-ssl-config-for-elastic-beanstalk-single-instances/
# Dont forget to set the env variable "certdomain", and either fill in your email below or use an env variable for that too.
# Also note that this config is using the LetsEncrypt staging server, remove the flag when ready!
Resources:
sslSecurityGroupIngress:
Type: AWS::EC2::SecurityGroupIngress
Properties:
GroupId: {"Fn::GetAtt" : ["AWSEBSecurityGroup", "GroupId"]}
IpProtocol: tcp
ToPort: 443
@jaron
jaron / urban-sound-cnn-1.py
Created October 4, 2016 15:10
A stacked convolutional neural network (CNN) to classify the Urban Sound 8K dataset. Uses Tensorflow, with Keras to provide some higher-level abstractions. Inspired by a blog post by Aaqib Saeed (http://aqibsaeed.github.io/2016-09-24-urban-sound-classification-part-2/)
import numpy as np
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Convolution2D, MaxPooling2D
from keras.optimizers import Adam
from keras.utils import np_utils
from sklearn import metrics
# to run this code, you'll need to load the following data:
# train_x, train_y
@jaron
jaron / urban-sound-cnn-salamon.py
Last active July 12, 2019 15:07
A Keras/Tensorflow implementation of the 5-layer CNN described in Salamon and Bello's paper (https://arxiv.org/pdf/1608.04363.pdf). See http://aqibsaeed.github.io/2016-09-24-urban-sound-classification-part-2/ for a description on how to create the data this uses.
import numpy as np
from keras.models import Sequential
from keras.layers import Dense, Dropout, Activation, Flatten
from keras.layers import Convolution2D, MaxPooling2D
from keras.optimizers import SGD
from keras.regularizers import l2, activity_l2
from keras.utils import np_utils
from sklearn import metrics
# to run this code, you'll need to load the following data:
@tomrunia
tomrunia / tf_queue.py
Created November 2, 2016 14:48
TensorFlow queue example
# Initialize placeholders for feeding in to the queue
pl_queue_screens = tf.placeholder(tf.float32, shape=[config.seq_length, config.image_size, config.image_size, config.input_channels], name="queue_inputs")
pl_queue_targets = tf.placeholder(tf.uint8, shape=[config.seq_length], name="queue_targets_cnt")
# ...
capacity = config.min_after_dequeue + 10 * (config.num_gpus*config.batch_size)
q = tf.RandomShuffleQueue(
@ASvyatkovskiy
ASvyatkovskiy / TF_replica_test.py
Created April 17, 2017 04:40
Test distributed data parallel synchronous LSTM with Tensorflow
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import math
import sys
import tempfile
import time
import os
@khacanh
khacanh / mdn.py
Last active February 11, 2019 23:20
Mixture density network with Tensorflow
# From http://blog.otoro.net/2015/11/24/mixture-density-networks-with-tensorflow/
import matplotlib.pyplot as plt
import numpy as np
import tensorflow as tf
import math
NHIDDEN = 24
STDEV = 0.5
KMIX = 24 # number of mixtures
@omoindrot
omoindrot / tensorflow_finetune.py
Last active October 7, 2024 18:58
Example TensorFlow script for fine-tuning a VGG model (uses tf.contrib.data)
"""
Example TensorFlow script for finetuning a VGG model on your own data.
Uses tf.contrib.data module which is in release v1.2
Based on PyTorch example from Justin Johnson
(https://gist.github.com/jcjohnson/6e41e8512c17eae5da50aebef3378a4c)
Required packages: tensorflow (v1.2)
Download the weights trained on ImageNet for VGG:
```
wget http://download.tensorflow.org/models/vgg_16_2016_08_28.tar.gz