Quy Nguyen trungquy

trungquy / pg-pong.py

Created June 2, 2016 23:29 — forked from karpathy/pg-pong.py

Training a Neural Network ATARI Pong agent with Policy Gradients from raw pixels

	""" Trains an agent with (stochastic) Policy Gradients on Pong. Uses OpenAI Gym. """
	import numpy as np
	import cPickle as pickle
	import gym

	# hyperparameters
	H = 200 # number of hidden layer neurons
	batch_size = 10 # every how many episodes to do a param update?
	learning_rate = 1e-4
	gamma = 0.99 # discount factor for reward

trungquy / rsync_parallel.sh

Created July 8, 2016 04:20 — forked from rcoup/rsync_parallel.sh

Parallel-ise an rsync transfer when you want multiple concurrent transfers happening,

	#!/bin/bash
	set -e

	# Usage:
	# rsync_parallel.sh [--parallel=N] [rsync args...]
	#
	# Options:
	# --parallel=N Use N parallel processes for transfer. Defaults to 10.
	#
	# Notes:

trungquy / blaze_face_detect.py

Created January 13, 2020 23:56 — forked from ogl4jo3/blaze_face_detect.py

Demo BlazeFace model.

	import cv2
	import time
	import math
	import numpy as np
	import tensorflow as tf

	class SsdAnchorsCalculatorOptions:
	def __init__(self, input_size_width, input_size_height, min_scale, max_scale
	, num_layers, feature_map_width, feature_map_height
	, strides, aspect_ratios, anchor_offset_x=0.5, anchor_offset_y=0.5