karolzak

def get_patches(img_arr, size=256, stride=256):
    '''
    Takes single image or array of images and returns
    crops using sliding window method.
    If stride < size it will do overlapping.
    '''
    # check size and stride
    if size % stride != 0: 
        raise ValueError('size % stride must be equal 0')
        

karolzak

import numpy as np
import matplotlib.pyplot as plt


def mask_to_red(mask, img_size=1024):
    '''
    Converts binary segmentation mask from white to red color.
    Also adds alpha channel to make black background transparent.
    '''
    c1 = mask.reshape(img_size,img_size)

karolzak

###################### unet ############################
from keras.models import Model
from keras.layers import *


def upsample_conv(filters, kernel_size, strides, padding):
    return Conv2DTranspose(filters, kernel_size, strides=strides, padding=padding)


def upsample_simple(filters, kernel_size, strides, padding):

karolzak

################### metrics ############################
from keras import backend as K

SMOOTH = 1e-12 

def iou(true, pred):    
    y_pred_pos = K.round(K.clip(pred, 0, 1))
    intersection = true * y_pred_pos   
    union = true + y_pred_pos
    return K.sum(intersection + SMOOTH) / K.sum(union - intersection + SMOOTH)

karolzak

#https://github.com/keras-team/keras-contrib/blob/master/keras_contrib/losses/jaccard.py
  
from keras import backend as K


def jaccard_distance(y_true, y_pred, smooth=100):
    """Jaccard distance for semantic segmentation.

    Also known as the intersection-over-union loss.

karolzak

import numpy as np
import matplotlib.pyplot as plt


def plot_segm_history(history):
    # summarize history for iou
    plt.figure(figsize=(12,6))
    plt.plot(history.history['iou'], linewidth=3)
    plt.plot(history.history['val_iou'], linewidth=3)
    plt.suptitle('iou metric', fontsize=20)

karolzak

from keras.preprocessing.image import ImageDataGenerator


# Runtime data augmentation
def get_augmented(
    X_train, 
    Y_train, 
    X_val,
    Y_val,
    batch_size=32, 

karolzak

# https://lars76.github.io/neural-networks/object-detection/losses-for-segmentation/

def weighted_cross_entropy(beta):
  def convert_to_logits(y_pred):
      # see https://github.com/tensorflow/tensorflow/blob/r1.10/tensorflow/python/keras/backend.py#L3525
      y_pred = tf.clip_by_value(y_pred, tf.keras.backend.epsilon(), 1 - tf.keras.backend.epsilon())

      return tf.log(y_pred / (1 - y_pred))

  def loss(y_true, y_pred):

karolzak

import sys
# These are the usual ipython objects, including this one you are creating
ipython_vars = ['In', 'Out', 'exit', 'quit', 'get_ipython', 'ipython_vars']
# Get a sorted list of the objects and their sizes
sorted([(x, sys.getsizeof(globals().get(x))) for x in dir() if not x.startswith('_') and x not in sys.modules and x not in ipython_vars], key=lambda x: x[1], reverse=True)

karolzak

from keras.backend.tensorflow_backend import set_session
from keras.backend.tensorflow_backend import clear_session
from keras.backend.tensorflow_backend import get_session
import tensorflow

# Reset Keras Session
def reset_keras():
    sess = get_session()
    clear_session()
    sess.close()