bkocis

bkocis

Deep Q-Network (DQN)

example of LunarLander-v2 environment deom OpenAi Gym.

import gym
!pip3 install box2d
import random
import torch
import numpy as np
from collections import deque

bkocis

Spark context and spark session

import pyspark
sc = pyspark.SparkContext(appName="maps_and_lazy_evaluation_example")

log_of_songs = [
        "Despacito",
        "Nice for what",
 "No tears left to cry",

bkocis

Code snippets from Udacity Spark Course

MapReduce

The biggest difference between Hadoop and Spark is that Spark tries to do as many calculations as possible in memory, which avoids moving data back and forth across a cluster. Hadoop writes intermediate calculations out to disk, which can be less efficient. Hadoop is an older technology than Spark and one of the cornerstone big data technologies.

MapReduce versus Hadoop MapReduce

bkocis

example 1 / from the CVND Image captioning project

class DecoderRNN(nn.Module):
    def __init__(self, embed_size, hidden_size, vocab_size, num_layers=1, dropout=0):
        super().__init__()
        self.embed_size = embed_size
        self.hidden_size = hidden_size
        self.vocab_size = vocab_size

bkocis

model class of CNN in PyToch

#  with batch normalization, dropout layer and 3 convolutional layers

import torch.nn as nn
import torch.nn.functional as F

# define the CNN architecture

bkocis

Finding Contours Fit Ellipse Crop selected contour based on angle of ellips

import numpy as np
import matplotlib.pyplot as plt
import cv2

bkocis

Harris corner detection

Detect corners

import matplotlib.pyplot as plt
import numpy as np
import cv2

bkocis

Canny Edge Detection

Hough Line Detection

import numpy as np
import matplotlib.pyplot as plt
import cv2

bkocis

Load image apply high-pass filter apply fourier tr

import numpy as np
import matplotlib.pyplot as plt
import cv2

# Read in an image