Piotr Skalski SkalskiP

👨‍💻

I open-source stuff

Open Source Lead @roboflow | Founder @ makesense.ai

SkalskiP / saving_model.py

Last active May 15, 2018 22:29

saving trained Python model in from readable by TensorFlow.js

	import tensorflowjs as tfjs
	# creating and training of model using Keras
	# ...
	tfjs.converters.save_keras_model(model, './ModelJS')

SkalskiP / saving_model.sh

Last active May 16, 2018 16:09

saving trained Python model in from readable by TensorFlow.js

$ tensorflowjs_converter --input_format keras ./ModelPY/model.h5 ./../ModelJS

SkalskiP / loading_model.js

Created May 15, 2018 23:30

Loading the model to the application

	import * as tf from '@tensorflow/tfjs';
	// Definition of the component supporting the model
	// ...
	protected async loadModel() {
	this.model = await tf.loadModel(AppSettings.mnistModelUrl);
	}

SkalskiP / make_prediction.js

Created May 16, 2018 16:15

making predictions based on image data

	protected async predict(imageData: ImageData) {

	const pred = await tf.tidy(() => {

	let img:any = tf.fromPixels(imageData, 1);
	img = img.reshape([1, 28, 28, 1]);
	img = tf.cast(img, 'float32');

	const output = this.model.predict(img) as any;

SkalskiP / adding_tensorflow.html

Created May 16, 2018 16:33

adding tensorflow/tfjs to your project

SkalskiP / first_model_layer.py

Created May 16, 2018 17:30

parameters of the first layer in Keras Mnist model

SkalskiP / simple_nn.py

Created August 13, 2018 16:32

Simple KERAS neural network for binary classification

	from keras.models import Sequential
	from keras.layers import Dense

	model = Sequential()
	model.add(Dense(4, input_dim=2,activation='relu'))
	model.add(Dense(6, activation='relu'))
	model.add(Dense(6, activation='relu'))
	model.add(Dense(4, activation='relu'))
	model.add(Dense(1, activation='sigmoid'))

SkalskiP / create_frames.py

Created September 9, 2018 22:16

Function to create animation frames

	def create_frames(dt, steps, padding, output_dir):
	fig, ax = create_blank_chart_with_styling((6, 6))
	# creation of data describing the trajectory
	xs, ys, zs = build_lorenz_trajectory(dt, steps)
	# setting the fixed range of axes
	ax.set_xlim3d(xs.min() - padding, xs.max() + padding)
	ax.set_ylim3d(ys.min() - padding, ys.max() + padding)
	ax.set_zlim3d(zs.min() - padding, zs.max() + padding)

	for i in range(steps-1):

SkalskiP / lorenz_animation_imports.py

Last active September 13, 2018 18:36

Libraries that have to be imported to create 3D animation using matplotlib.

	import numpy as np
	import matplotlib.pyplot as plt
	from mpl_toolkits.mplot3d import Axes3D
	import numpy as np
	from matplotlib.animation import FuncAnimation

SkalskiP / lorenz_animation_init.py

Created September 13, 2018 18:12

Animation initiation process

	# Calculation of the points belonging to the three trajectories,
	# based on the given starting conditions
	plots_data = [build_lorenz_trajectory(DELTA_T, STEPS,
	initial_values=initial_conditions[i]) for i in range(3)]

	# Creation of an empty chart
	fig, ax = create_blank_chart_with_styling(plots_data, PADDING, (8, 8))

	# Setting up (for the time being empty) data sequences for each trajectory
	plots = [ax.plot([],[],[], color=colors[i], label=str(initial_conditions[i]),