N.Watanabe nwatab

We couldn’t find that file to show.

Fine-tuning with DAGM2007 dataset. 109 Epochs was enough. It took 8 hours with a Tesla K80 (12GB Memory, 61GB RAM, 100GB SSD)

	/**
	* This is a code for Google App Script to see if there is a line for QBHouse at Kojimachi.
	* main(): Access to qb house kojimachi homepage and check the number of people in line.
	* Replace an email with yours.
	* doGet(): This function is for publishing a web service as API (only one endpoint).
	*/

	function main() {
	var url = 'http://www.qbhouse.co.jp/search/detail.php?id=475'; // QB HOUSE Kojimachi
	var text = UrlFetchApp.fetch(url).getContentText('utf-8');

	var CHANNEL_ACCESS_TOKEN = 'xxx=';
	var line_endpoint = 'https://api.line.me/v2/bot/message/reply';

	function doGet(e) {
	return ContentService.createTextOutput(UrlFetchApp.fetch("http://ip-api.com/json"));
	}

	function doPost(e) {
	var contents = JSON.parse(e.postData.contents);

	import matplotlib.pyplot as plt
	import numpy as np
	from keras.datasets import mnist
	from keras.models import Sequential
	from keras.layers import Dense, Dropout, Flatten, BatchNormalization
	from keras.layers.advanced_activations import LeakyReLU
	from keras.layers import Conv2D, MaxPooling2D, Reshape, UpSampling2D, InputLayer
	from keras.optimizers import Adam
	import os