jkjung-avt

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

jkjung-avt

jkjung-avt

# Feature extractor
def extract_features(image_path, vector_size=32):
    image = imread(image_path, mode="RGB")
    try:
        # Using KAZE, cause SIFT, ORB and other was moved to additional module
        # which is adding addtional pain during install
        alg = cv2.KAZE_create()
        # Dinding image keypoints
        kps = alg.detect(image)
        # Getting first 32 of them. 

jkjung-avt

"""disjoint_set.py
"""


import random


class DisjointSet(object):
    """DisjointSet

jkjung-avt

" JK Jung's .vmirc
"
" Reference:
"
" 1. Sample .vimrc by Martin Brochhaus, presented at PyCon APAC 2012
"    https://github.com/mbrochh/vim-as-a-python-ide
" 2. https://realpython.com/vim-and-python-a-match-made-in-heaven/
" 3. https://github.com/fisadev/fisa-vim-config
" 4. https://github.com/thesheff17/youtube/blob/master/vim/vimrc
" 5. https://github.com/amix/vimrc

jkjung-avt

# --------------------------------------------------------
# Camera Recorder for Tegra X2/X1
#
# This program captures video from IP CAM, USB webcam,
# or the Tegra onboard camera, adds some watermark on
# the video frames and then records it into a TS file.
# The code demonstrates how to use cv2.VideoWriter()
# while taking advantage of TX2/TX1's H.264 H/W encoder
# capabilities.
#

jkjung-avt

# Reference: https://michhar.github.io/how-i-built-pytorch-gpu/
# I have a GTX-1080 and a GTX-2080 Ti, thus CUDA_ARCH "6.1" and "7.5".

# Patch cmake if necessary: https://github.com/arrayfire/arrayfire/issues/2330

git clone https://github.com/pytorch/pytorch.git pytorch-v1.3.1
cd pytorch-v1.3.1
git checkout v1.3.1
git submodule update --init --recursive 

jkjung-avt

from pathlib import Path
import struct

lines = Path('calib_yolov4-int8-608.bin').read_text().splitlines()
for line in lines:
    pair = line.split(':')
    if len(pair) != 2:
        continue
    assert len(pair[1]) == 9
    bstr = bytes.fromhex(pair[1][1:])    # convert to byte string

jkjung-avt

import numpy as np
import keras

class DataGenerator(keras.utils.Sequence):
    'Generates data for Keras'
    def __init__(self, list_IDs, labels, batch_size=32, dim=(32,32,32), n_channels=1,
                 n_classes=10, shuffle=True):
        'Initialization'
        self.dim = dim
        self.batch_size = batch_size

jkjung-avt

"""dcgan_mnist.py

This script was orginally written by Rowel Atienza (see below), and
was modified by JK Jung <jkjung13@gmail.com>.

------

DCGAN on MNIST using Keras
Author: Rowel Atienza
Project: https://github.com/roatienza/Deep-Learning-Experiments