jasonsalas

import android.app.Activity;
import android.content.Context;
import android.content.Intent;
import android.os.Bundle;
import android.support.wearable.view.WearableListView;
import android.util.Log;
import android.view.LayoutInflater;
import android.view.ViewGroup;
import android.widget.TextView;

jasonsalas

application: YOUR_APP_NAME_HERE
version: 1
runtime: python27
api_version: 1
threadsafe: true

handlers:
- url: /.*
  script: oauth.application
  

jasonsalas

''' SHALLOW MODEL '''
img_shape = (32, 32, 3)
z_dim = 100
init = initializers.RandomNormal(mean=0.0, stddev=0.02)
opt = Adam(lr=0.0002, beta_1=0.5)

def build_discriminator(in_shape=img_shape):
    model = Sequential()
    
    model.add(Conv2D(64, (5,5), input_shape=in_shape, kernel_initializer=init))

jasonsalas

''' client to produce generator images from latent space '''
import numpy as np
from keras.models import load_model

MODEL = './generator_model_2800.h5'

z_noise = np.random.randn(100*25)
z_noise = z_noise.reshape(25, 100)

model = load_model(MODEL)

jasonsalas

from keras.applications.vgg16 import VGG16

model = VGG16(weights='imagenet')
model.save('model_vgg16_imagenet.h5')
print('Pre-trained VGG16 model with ImageNet weights saved!')

jasonsalas

import os
import numpy as np
import tensorflow as tf
from keras.applications.vgg16 import preprocess_input, decode_predictions
from keras.models import load_model
from keras.preprocessing.image import img_to_array, load_img
from flask import Flask, redirect, url_for, request, render_template

# define a Flask app
app = Flask(__name__)

jasonsalas

# Make predictions on unseen data
#
# follows my full demo/repo at
# https://github.com/jasonsalas/nlp_predict_movie_rating_via_description/

import pickle
from keras.preprocessing.text import Tokenizer
from keras.models import load_model

''' Cabin in the Woods (R) '''

jasonsalas

import numpy as np
import sys
from keras.models import Sequential
from keras.layers import Dense, Dropout, LSTM
from keras.callbacks import ModelCheckpoint
from keras.utils import to_categorical

filename = 'dm_lyrics.txt'
raw_text = open(filename, 'r', encoding='utf-8').read()
raw_text = raw_text.lower()

jasonsalas

import numpy as np
import sys
from keras.models import Sequential

filename = 'trained_depechemode_lyrics_model.h5'

model = Sequential()
model.load_weights(filename)
model.compile(loss='categorical_crossentropy', optimizer='adam')

jasonsalas

/* using worker pools & buffered channels in Go */
// h/t: Naveen Ramanathan @ golangbot.com
// https://golangbot.com/buffered-channels-worker-pools/

package main

import (
	"fmt"
	"math/rand"
	"sync"