rfalaize

1 follower · 0 following

View GitHub Profile

Recently created

Least recently created

Recently updated

Least recently updated

rfalaize / cvx_simple_gradient_descent.py

Last active July 30, 2020 13:48

	#%% gradient descent
	# ***********************************************************

	def run_gradient_descent(func, initial_point, gradients, verbose=False):
	"""
	Simple implementation of gradient descent for a convex function of 2 arguments.

	Arguments:
	func: the function of 2 variables to minimize
	initial_point: a 2D tuple representing the initial point

rfalaize / mnistapp_ui.js

Last active July 31, 2021 14:01

	import React, { Component } from "react";
	import Chart from "chart.js";
	import "./App.css";

	/*
	Mnist application
	Draw hand-written digits on a canvas and send it to backend server for classification.
	*/
	class App extends Component {
	constructor(props) {

rfalaize / mnistapp_flaskapi.py

Created December 21, 2019 04:25

	import flask
	from flask_cors import CORS
	from flask_restplus import Api, Resource, fields
	import tensorflow as tf
	from skimage.transform import resize
	import numpy as np

	# disable GPU usage for inference
	import os
	os.environ["CUDA_VISIBLE_DEVICES"] = "-1"

rfalaize / mnistapp_train.py

Created December 21, 2019 03:27

	# choose a loss function and an optimizer
	model.compile(loss=tf.keras.losses.categorical_crossentropy,
	optimizer=tf.keras.optimizers.Adam(),
	metrics=['accuracy'])

	# (optional) configure tensorboard to collect training stats
	log_dir = "C:\\temp\\tensorboard\\{}".format(datetime.now().strftime("%Y%m%d-%H%M%S"))
	os.mkdir(log_dir)
	tensorboardCallback = tf.keras.callbacks.TensorBoard(log_dir=log_dir)

rfalaize / mnistapp_createmodel.py

Last active December 21, 2019 03:26

	import os
	from tensorflow.keras.models import Sequential
	from tensorflow.keras.layers import Dense, Dropout, Flatten, Conv2D, MaxPooling2D
	from datetime import datetime

	# convert class vectors to binary class matrices
	num_classes = 10
	y_train = tf.keras.utils.to_categorical(y_train, num_classes)
	y_test = tf.keras.utils.to_categorical(y_test, num_classes)

rfalaize / mnistapp_loaddata.py

Last active December 21, 2019 02:39

	import numpy as np
	import tensorflow as tf

	print("Loading mnist dataset...")
	(X_train, y_train), (X_test, y_test) = tf.keras.datasets.mnist.load_data()
	X_train, X_test = X_train / 255.0, X_test / 255.
	# add a channels dimension
	X_train = X_train[..., tf.newaxis]
	X_test = X_test[..., tf.newaxis]
	print('Data loaded. X_train shape:', X_train.shape)

rfalaize / mnistapp_plotdigits.py

Last active December 15, 2019 03:35

	w = 10
	h = 10
	fig=plt.figure(figsize=(8, 8))
	columns = 4
	rows = 4
	for i in range(0, columns*rows):
	img = X_train[i]
	ax = fig.add_subplot(rows, columns, i+1)
	ax.title.set_text('label:' + str(y_train[i]))
	plt.imshow(img)

rfalaize / symbolicdiff.py

Last active October 12, 2019 02:25

symbolic differentiation

	import sympy
	x1 = sympy.symbols('x1')
	x2 = sympy.symbols('x2')
	x3 = sympy.symbols('x3')

	def f(x1, x2, x3):
	return 3(x12 + x2x3)

	u = f(x1, x2, x3)
	print('f(x1, x2, x3) = ',u)