neale

import sys
import numpy as np
import cv2
from perlin_noise import PerlinNoise
import glob

def vector_field(x, y, noise, scale=0.01, w=100):
  noise_x = w * noise([scale*x, scale*y])
  noise_y = w * noise([100+scale*x, scale*y])
  return noise_x, noise_y

neale

 FROM ros:indigo
 
 RUN apt-get update
 RUN apt-get install -y
 RUN apt-get install -y wget nano build-essential vim curl
 RUN apt-get install -y ros-indigo-geodesy ros-indigo-pcl-ros ros-indigo-nmea-msgs
 
 RUN apt-get install build-essential
 RUN wget http://www.cmake.org/files/v3.2/cmake-3.2.2.tar.gz
 RUN tar xf cmake-3.2.2.tar.gz

neale

import numpy as np
import matplotlib.pyplot as plt 
import mpl_toolkits.mplot3d.axes3d as p3
import matplotlib.animation as animation
import pandas as pd
from sys import exit
def update_lines(num, data, line):
    # NOTE: there is no .set_data() for 3 dim data...
    line.set_data(data[0:2, :num])    
    line.set_3d_properties(data[2, :num])    

neale

import re
import csv


def get_n(string):
    return re.findall(r"[-+]?\d*\.\d+|\d+", string)


lines = []
with open('coordsOut.txt', 'r') as f:

neale

import numpy as np
import cv2, os, sys, getopt
from glob import glob
import natsort


# Global Variables
helpMessage = 'Usage:\n\tcrop.py <command> [argument]\n\nCommands:\n\t-h --help\t\tDisplay this help message\n\t-i --image [path]\tInput image\n\t-f --folder [path]\tImage Folder\n\t-r --regex [regex]\tNaming of output files [WIP]\n\t-s --save [path]\tPath to Save'

# Arguments

neale

   import foolbox
   import keras
   import numpy
   from keras.applications.resnet50 import ResNet50
   import matplotlib.pyplot as plt
   import scipy.misc
   
   # instantiate model
   keras.backend.set_learning_phase(0)
   kmodel = ResNet50(weights='imagenet')

neale

name: "CNN"
input: "data"
input_shape {
  dim: 1
  dim: 3
  dim: 224
  dim: 224
}

layer {

neale

class A4C(torch.nn.Module):

    def __init__(self, input, n_actions):
        """ Standard recurrent A3C """
        self.conv1 = nn.Conv2d(input, 32, 3, stride=2, padding=1)
        self.conv2 = nn.Conv2d(32, 32, 3, stride=2, padding=1)
        self.conv3 = nn.Conv2d(32, 32, 3, stride=2, padding=1)
        self.conv4 = nn.Conv2d(32, 32, 3, stride=2, padding=1)
        self.lstm = StackedLSTM(2, 256, 256, dropout=.5)

neale

name: "ResNet-152"
input: "data"
input_shape {
    dim: 1
    dim: 3
    dim: 224
    dim: 224
}
layer {
	bottom: "data"

neale

net: "models/darkvgg/train_test.prototxt"
test_iter: 1000
test_interval: 5000
base_lr: 0.0005
lr_policy: "inv"
gamma: 0.0001
power: 0.75
display: 200
max_iter: 450000
momentum: 0.0