Thimira’s gists

Thimira / DCGAN.py

Created May 20, 2020 10:58

Handwritten Digit Generation by Deep Convolutional Generative Adversarial Networks. Requires TensorFlow 2, OpenCV, Matplotlib, and imageio

	import tensorflow as tf

	import glob
	import imageio
	import matplotlib.pyplot as plt
	import numpy as np
	import os
	import PIL
	from tensorflow.keras import layers
	import time

Thimira / face_blur_circle.py

Created May 8, 2020 07:51

	# Using a circular mask as the blur area to automatically blur the face in a video, giving it a more cleaner look.
	# We're using OpenCV, and Dlib with Python.
	# See tutorial here: https://youtu.be/1p1lUyLGB2E

	import numpy as np
	import cv2
	import dlib

	video_capture = cv2.VideoCapture(1)
	detector = dlib.get_frontal_face_detector()

Thimira / face_blur.py

Created May 8, 2020 07:47

	# Blur Your Face Automatically with OpenCV and Dlib
	# See tutorial at https://www.youtube.com/watch?v=QKggnWdCTNY

	import numpy as np
	import cv2
	import dlib

	video_capture = cv2.VideoCapture(1)
	detector = dlib.get_frontal_face_detector()

Thimira / bird_watch_train.py

Last active December 1, 2019 15:09

The main model training code from the Bird Watch project: https://github.com/Thimira/bird_watch . The project is currently live at https://www.birdwatch.photo/

	import numpy as np
	from keras.preprocessing.image import ImageDataGenerator, img_to_array, load_img
	from keras.models import Sequential, Model
	from keras.layers import Dropout, Flatten, Dense, GlobalAveragePooling2D, Input
	from keras.applications.inception_v3 import InceptionV3
	from keras.utils.np_utils import to_categorical
	from keras import optimizers
	from keras.callbacks import EarlyStopping, ModelCheckpoint
	from datetime import datetime, timedelta
	import matplotlib.pyplot as plt

Thimira / snapchat_like_image_overlays.py

Last active September 6, 2021 17:49

Snapchat like Image Overlays with Dlib, OpenCV, and Python. Tutorial: https://www.codesofinterest.com/2017/07/snapchat-like-filters-with-dlib-opencv-python.html

	import numpy as np
	import cv2
	import dlib
	from scipy.spatial import distance as dist
	from scipy.spatial import ConvexHull

	PREDICTOR_PATH = "../data/dlib_models/shape_predictor_68_face_landmarks.dat"

	FULL_POINTS = list(range(0, 68))
	FACE_POINTS = list(range(17, 68))

Thimira / ObjectTracker.py

Last active November 11, 2021 06:07

Track any object in a video with Dlib Correlation Trackers. Tutorial: https://www.codesofinterest.com/2018/02/track-any-object-in-video-with-dlib.html

	'''
	Using Correlation Trackers in Dlib, you can track any object in a video stream without needing to train a custom object detector.
	Check out the tutorial at: http://www.codesofinterest.com/2018/02/track-any-object-in-video-with-dlib.html
	'''
	import numpy as np
	import cv2
	import dlib

	# this variable will hold the coordinates of the mouse click events.
	mousePoints = []

Thimira / resnet50_predict.py

Created September 3, 2017 08:35

How to use the ResNet50 model from Keras Applications trained on ImageNet to make a prediction on an image.

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

	model = ResNet50(weights='imagenet')

	img_path = 'Data/Jellyfish.jpg'
	img = image.load_img(img_path, target_size=(224, 224))
	x = image.img_to_array(img)

Thimira / vgg16_predict.py

Created September 3, 2017 08:34

How to use the VGG16 model from Keras Applications trained on ImageNet to make a prediction on an image.

	from keras.applications.vgg16 import VGG16
	from keras.preprocessing import image
	from keras.applications.vgg16 import preprocess_input, decode_predictions
	import numpy as np

	model = VGG16(weights='imagenet')

	img_path = 'Data/Jellyfish.jpg'
	img = image.load_img(img_path, target_size=(224, 224))
	img_data = image.img_to_array(img)

Thimira / vgg16_sequential.py

Created September 3, 2017 08:28

The VGG16 Deep Learning model created using the Sequential model of Keras v2

	from keras.models import Sequential
	from keras.layers.core import Flatten, Dense, Dropout
	from keras.layers.convolutional import Conv2D, MaxPooling2D, ZeroPadding2D
	from keras.optimizers import SGD
	import numpy as np

	def VGG_16(weights_path=None):
	input_shape=(224,224,3)

	model = Sequential()

Thimira / lenet_mnist_keras.py

Last active February 27, 2018 13:27

Deep Learning Beginner Tutorial. Using the LeNet model on the MNIST dataset for handwritten digit recognition. Works with Keras v2 and TensorFLow. This code is part of the book Build Deeper: Deep Learning Beginners' Guide (https://www.amazon.com/dp/B07564Y6CL)

	# How to use
	#
	# Train the model and save the model weights
	# python lenet_mnist_keras.py --train-model 1 --save-trained 1
	#
	# Train the model and save the model wights to a give directory
	# python lenet_mnist_keras.py --train-model 1 --save-trained 1 --weights data/lenet_weights.hdf5
	#
	# Evaluate the model from pre-trained model wights
	# python lenet_mnist_keras.py

Thimira Amaratunga Thimira