danyashorokh

# Plot training & validation accuracy values
plt.plot(results.history['iou_coef'])
plt.plot(results.history['val_iou_coef'])
plt.title('Model accuracy')
plt.ylabel('IOU')
plt.xlabel('Epoch')
plt.legend(['Train', 'Test'], loc='upper left')
plt.show()

# Plot training & validation loss values

danyashorokh

from skimage.exposure import cumulative_distribution
import numpy as np


def cdf(im):
    '''
    computes the CDF of an image im as 2D numpy ndarray
    '''
    c, b = cumulative_distribution(im)
    # pad the beginning and ending pixels and their CDF values

danyashorokh

from skimage.exposure import cumulative_distribution
import numpy as np


def cdf(im):
    '''
    computes the CDF of an image im as 2D numpy ndarray
    '''
    c, b = cumulative_distribution(im)
    # pad the beginning and ending pixels and their CDF values

danyashorokh

import numpy as np

def hist_match(source, template):
    """
    Adjust the pixel values of a grayscale image such that its histogram
    matches that of a target image

    Arguments:
    -----------
        source: np.ndarray

danyashorokh

import tensorflow as tf
from keras.models import Sequential
from tensorflow.keras.layers import (
    Conv2D, MaxPooling2D, Flatten,
    Dense, Dropout, Input
)

image_input = Input(shape=(100, 100, 3), name='input_layer')
conv_1 = Conv2D(8,
                kernel_size=(3, 3),

danyashorokh

import cv2 as cv
import numpy as np


def nothing(x):
    pass


# Color trackbars

danyashorokh

df1 = df.copy()  
var_types = pd.DataFrame(df1.dtypes.index, columns = ['Variable'])

lst = []
for col in df1.columns:
    try:
        df1[col] = df1[col].astype(float)
        lst.append(False)
    except:
        try:

danyashorokh

import pandas as pd

variables = []

rlst = []
for i in range(0, len(variables)):
    clst = []
    for j in range(0, len(variables)):
        if i != j:
            clst.append( round(df[variables[i]].corr(df[variables[j]]), 3))

danyashorokh

from scipy.optimize import curve_fit

# interpolate

df_int[field] = df[field].interpolate(method='piecewise_polynomial')

'''
'linear’, ‘time’, ‘index’, ‘values’, ‘nearest’, ‘zero’,
‘slinear’, ‘quadratic’, ‘cubic’, ‘barycentric’, ‘krogh’, ‘polynomial’, ‘spline’ ‘piecewise_polynomial’, ‘pchip’}
'''

danyashorokh

# %matplotlib inline
from matplotlib import pyplot as plt
plt.rcParams['figure.figsize'] = (10, 8)

fig = plt.figure(figsize=(25, 15))
cols = 5
rows = np.ceil(float(data_train.shape[1]) / cols)

for i, column in enumerate(data_train.columns):
    ax = fig.add_subplot(rows, cols, i + 1)