lanpa

%2013/1/1
%Tzu-Wei Huang
%demo of 'derivative of Gaussian', Difference of Gaussians and
%'Laplacian of Gaussian' in matlab.

close all;

[x,y] = meshgrid(-5:0.1:5,-5:0.1:5);
%gaussian with sigma = 1
z = (1/sqrt(2*pi))./exp((x.^2+y.^2)/2);

lanpa

prices = {
    "banana": 10,
    "apple": 20,
    "orange": 15,
    "mango": 30
}
shopping_list1 = ["banana", "orange", "apple", "apple", "apple"]
shopping_list2 = ["banana", "orange", "apple", "banana", "apple"]

def sumThemAll(shoplist):

lanpa

f = open('drinkquiz.txt', 'w')
char_remove = ['。\n。\n', '.\n.\n', '…\n…\n', '．\n．\n', '°\n°\n', '·\n·\n', '•\n•\n', '+\n+\n']
for i in range(2500):
    for feed in feeds['data']:
        if 'message' in feed:
            msg = feed['message']
            #print (msg)
            for rm in char_remove:
                msg = msg.replace(rm,'')
            #print(msg)

lanpa

#!/usr/bin/env bash
set -e

######################################################################
# This script installs required dependencies for Torch7
######################################################################
{

install_openblas() {
    # Get and build OpenBlas (Torch is much better with a decent Blas)

lanpa

class AlexNet(nn.Module):

    def __init__(self, num_classes=1000):
        super(AlexNet, self).__init__()
        self.features = nn.Sequential(
            nn.Conv2d(3, 64, kernel_size=11, stride=4, padding=2),
            nn.ReLU(inplace=True),
            nn.MaxPool2d(kernel_size=3, stride=2),
            nn.Conv2d(64, 192, kernel_size=5, padding=2),
            nn.ReLU(inplace=True),

lanpa

graph(%0 : Float(1, 3, 224, 224)
      %1 : Float(64, 3, 11, 11)
      %2 : Float(64)
      %3 : Float(192, 64, 5, 5)
      %4 : Float(192)
      %5 : Float(384, 192, 3, 3)
      %6 : Float(384)
      %7 : Float(256, 384, 3, 3)
      %8 : Float(256)
      %9 : Float(256, 256, 3, 3)

lanpa

graph(%0 : Float(1, 3, 224, 224)
      %1 : Float(64, 3, 11, 11)
      %2 : Float(64)
      %3 : Float(192, 64, 5, 5)
      %4 : Float(192)
      %5 : Float(384, 192, 3, 3)
      %6 : Float(384)
      %7 : Float(256, 384, 3, 3)
      %8 : Float(256)
      %9 : Float(256, 256, 3, 3)

lanpa

with open ('data.csv') as f:
    lines = f.readlines()

valid = []
for line in lines:
    a, b = line.strip('\n').split(',')
    if a=='1' or a=='2' or a=='3':
        print(a, b)
        valid.append((int(a), int(b)))

lanpa

from __future__ import print_function
import argparse
import torch
import torch.nn as nn
import torch.nn.functional as F
import torch.optim as optim
from torchvision import datasets, transforms
from torch.autograd import Variable
from tensorboardX import SummaryWriter
# Training settings

lanpa

class Net1(nn.Module):
    def __init__(self):
        super(Net1, self).__init__()
        self.conv1 = nn.Conv2d(1, 10, kernel_size=5)
        self.conv2 = nn.Conv2d(10, 20, kernel_size=5)
        self.conv2_drop = nn.Dropout2d()
        self.fc1 = nn.Linear(320, 50)
        self.fc2 = nn.Linear(50, 10)
        self.bn = nn.BatchNorm2d(20)