manashmandal

import os
from tqdm import tqdm
import cv2
import numpy as np
from pprint import pprint
from os.path import join
import glob
from sklearn.utils import shuffle
from keras.utils import to_categorical

manashmandal

manashmandal

>>> R[0]
array([26801.16945753, 38668.6046967 , 34937.9753498 , 45478.98967837])
>>> R[1]
array([39823.04549356, 45055.11438545, 44048.634533  , 50008.11226016])
>>> zip(R[0], R[1])
[(26801.16945753, 39823.04549356), (38668.6046967, 45055.11438545), (34937.9753498, 44048.634533), (45478.98967837, 50008.11226016)]

manashmandal

#include "LineFollower.h"

//Setting inverted logic false
bool pdlf::Robot::inverted_logic = false;

//Setting the default threshold value

size_t pdlf::Robot::THRESHOLD = 200;

//Setting global speed

manashmandal

Download videos from egghead

Go to the egghead website, i.e. Building a React.js App

run

$.each($('h4 a'), function(index, video){
  console.log(video.href);
});

manashmandal

def infer(input_data, model=model):
    inference = []
    
    classes = np.array(['desert', 'mountain', 'sea', 'sunset', 'trees'])
    
    y_pred = model.predict(input_data)
    
    # Performing masking
    y_pred = (y_pred > 0.5) * 1.0
    

manashmandal

from keras.models import Sequential
from keras.layers import Dense, Dropout, Flatten
from keras.layers import Conv2D, MaxPooling2D, Activation

batch_size = 100
num_classes = 5
epochs = 50

# input image dimensions
img_rows, img_cols = 100, 100

manashmandal

import keras.backend as K

def multitask_loss(y_true, y_pred):
    # Avoid divide by 0
    y_pred = K.clip(y_pred, K.epsilon(), 1 - K.epsilon())
    # Multi-task loss
    return K.mean(K.sum(- y_true * K.log(y_pred) - (1 - y_true) * K.log(1 - y_pred), axis=1))

manashmandal

import matplotlib.pyplot as plt
import h5py
from sklearn.model_selection import train_test_split

def load():
    f = h5py.File("./data/dataset.h5")
    x = f['x'].value
    y = f['y'].value
    f.close()
    

manashmandal

def build_deep_conv_autoencoder(img_shape=(44, 44, 3), code_size):
    H,W,C = img_shape
    
    # encoder
    encoder = keras.models.Sequential()
    encoder.add(L.InputLayer(img_shape))
    encoder.add(L.Conv2D(32, kernel_size=(3, 3),strides=1, padding='same', activation='elu'))
    encoder.add(L.MaxPool2D(pool_size=(2, 2)))
    encoder.add(L.Conv2D(64, kernel_size=(3, 3),strides=1, padding='same', activation='elu'))
    encoder.add(L.MaxPool2D(pool_size=(2, 2)))