yunlongdong’s gists

yunlongdong / GenPDF2d.py

Last active April 6, 2019 05:53

generate PDF from a gray image

	import numpy as np
	from skimage.data import camera
	import matplotlib.pyplot as plt

	img = camera().astype('float32')
	f = (img/img.sum()).ravel()
	p = np.cumsum(f)
	ys = np.random.rand(500)
	xs = np.searchsorted(p, ys)
	buf = np.zeros(img.shape)

yunlongdong / trans_utils.py

Created March 24, 2019 05:15

Transfromation between quternion and euler angle

	from math import *

	def euler2q(roll, pitch, yaw):
	"""
	https://en.wikipedia.org/wiki/Conversion_between_quaternions_and_Euler_angles
	"""
	cy = cos(yaw * 0.5)
	sy = sin(yaw * 0.5)
	cp = cos(pitch * 0.5)
	sp = sin(pitch * 0.5)

yunlongdong / dataloader.py

Created December 24, 2018 10:28

Pytorch Generic Dataloader

	import torch
	import torch.nn as nn
	from torch.utils.data import Dataset, DataLoader
	from torchvision import transforms
	from PIL import Image as Image
	import os
	import pdb

	transform = transforms.Compose([transforms.ToTensor(), transforms.Normalize(mean=[0.485, 0.456, 0.406], std=[0.229, 0.224, 0.225])])

yunlongdong / classifier_from_little_data_script_3.py

Created November 1, 2018 14:05 — forked from fchollet/classifier_from_little_data_script_3.py

Fine-tuning a Keras model. Updated to the Keras 2.0 API.

	'''This script goes along the blog post
	"Building powerful image classification models using very little data"
	from blog.keras.io.
	It uses data that can be downloaded at:
	https://www.kaggle.com/c/dogs-vs-cats/data
	In our setup, we:
	- created a data/ folder
	- created train/ and validation/ subfolders inside data/
	- created cats/ and dogs/ subfolders inside train/ and validation/
	- put the cat pictures index 0-999 in data/train/cats

yunlongdong / get_batch.py

Created November 1, 2018 12:28

get batch items from a list obj

yunlongdong / DrawPolyLIne.py

Created August 18, 2018 11:30

Draw polygen around the line

	import numpy as np
	import matplotlib.pyplot as plt
	from matplotlib.patches import Polygon

	x = np.arange(10)
	y = np.random.rand(10)
	ymax = y + np.random.rand(10)/5
	ymin = y - np.random.rand(10)/5
	xy = list(zip(x, ymin)) + list(zip(x, ymax))[::-1]

Y. Dong yunlongdong