Okiriza Wibisono okiriza

okiriza / cctv-scraper.py

Last active December 11, 2016 04:18

Lambda function for scraping Transjakarta CCTV screenshot (https://tentangdata.wordpress.com/2016/12/10/managed-database-semurah-tahu-tempe-dengan-amazon-dynamodb/)

	from datetime import datetime, timedelta
	import urllib2
	from urllib2 import URLError

	import boto3


	START_BYTE = b'\xff\xd8'
	END_BYTE = b'\xff\xd9'
	ITER_LIMIT = 10000

okiriza / cctv-scrape-downloader.py

Last active December 30, 2016 23:19

Script for downloading screenshots of Transjakarta CCTV (https://tentangdata.wordpress.com/2016/12/10/managed-database-semurah-tahu-tempe-dengan-amazon-dynamodb/)

	from __future__ import print_function

	import os
	import time

	import boto3
	from boto3 import dynamodb
	import cv2
	import numpy as np
	import scipy.misc

okiriza / keras-resnet-extract-bottleneck-features.py

Last active May 1, 2017 19:48

Python function for extracting image features using bottleneck layer of Keras' ResNet50

	from keras.applications.resnet50 import ResNet50, preprocess_input
	from keras.preprocessing import image
	import numpy as np


	resnet = ResNet50(include_top=False)

	def extract_features(img_paths, batch_size=64):
	""" This function extracts image features for each image in img_paths using ResNet50 bottleneck layer.
	Returned features is a numpy array with shape (len(img_paths), 2048).

okiriza / example_autoencoder.py

Last active December 1, 2020 06:58

Example convolutional autoencoder implementation using PyTorch

	import random

	import torch
	from torch.autograd import Variable
	import torch.nn as nn
	import torch.nn.functional as F
	import torch.optim as optim
	import torchvision
	from torchvision import datasets, transforms

okiriza / autoencoder_visualization.py

Last active February 24, 2022 11:50

Script for visualizing autoencoder and PCA encoding on MNIST data

	import colorlover as cl
	from plotly import graph_objs as go
	from plotly import offline
	from sklearn.decomposition import PCA
	import torch
	from torch.autograd import Variable
	import torch.nn as nn
	import torch.nn.functional as F
	from torchvision import datasets, transforms