lukas

import numpy as np
import os
import wandb
from wandb.keras import WandbCallback
import tensorflow as tf

run = wandb.init()
config = run.config
config.dropout = 0.25
config.dense_layer_nodes = 100

lukas

import tensorflow as tf
import wandb

# logging code
run = wandb.init()
config = run.config

# load data
(X_train, y_train), (X_test, y_test) = tf.keras.datasets.mnist.load_data()
img_width = X_train.shape[1]

lukas

import tensorflow as tf
import wandb

# logging code
run = wandb.init()
config = run.config

# load data
(X_train, y_train), (X_test, y_test) = tf.keras.datasets.mnist.load_data()
img_width = X_train.shape[1]

lukas

from argparse import ArgumentParser
import wandb
import torch
from torch import nn
from torch.optim import SGD
from torch.utils.data import DataLoader
import torch.nn.functional as F
from torchvision.transforms import Compose, ToTensor, Normalize
from torchvision.datasets import MNIST

lukas

import wandb
import matplotlib.pyplot as plt
from sklearn import datasets


wandb.init()
iris = datasets.load_iris()
X = iris.data[:, :2]  # we only take the first two features.
y = iris.target

lukas

word_to_id = imdb.get_word_index()
word_to_id = {k: (v+3) for k, v in word_to_id.items()}
id_to_word = {value: key for key, value in word_to_id.items()}
id_to_word[0] = ""  # Padding
id_to_word[1] = ""  # Start token
id_to_word[2] = "�"  # Unknown
id_to_word[3] = ""  # End token


def decode(word):

lukas

import wandb
import numpy as np
import xgboost as xgb
from keras.datasets import mnist 

def wandb_callback():
    def callback(env):
        for k, v in env.evaluation_result_list:
            wandb.log({k: v}, commit=False)

lukas

declare -a voices=(
"Agnes"
"Albert"
"Alex"
"Alice"
"Alva"
"Amelie"
"Anna"
"Bad"
"Bahh"

lukas

Slides at http://bit.ly/lukas-qcom-course

Step 1)
Wandb is a logging program that will help you visualize neural network performance in the afternoon online.
Go to "https://app.wandb.ai/login?invited" and create an account.  No need to follow further instructions.

Step 2)
On your server run:
cd ml-class/
git pull origin master

lukas

ar arDrone = require('ar-drone');
var client  = arDrone.createClient();

client.takeoff();

client.after(5000, function() {
  this.clockwise(0.5);
}).after(3000, function() {
  this.stop();
  this.land();