-
Notifications
You must be signed in to change notification settings - Fork 0
/
datagen.py
63 lines (51 loc) · 1.88 KB
/
datagen.py
1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
#!/usr/bin/env python3
# -*- coding: utf-8 -*-
"""
Created on Fri Jul 31 00:25:57 2020
@author: berk
"""
import numpy as np
import os
from tensorflow.python.keras.utils.data_utils import Sequence
import cv2
class DataGenerator(Sequence):
'Generates data for Keras'
def __init__(self, list_IDs, labels, batch_size=32, dim=(66,200,3), shuffle=True):
'Initialization'
self.dim = dim
self.batch_size = batch_size
self.labels = labels
self.list_IDs = list_IDs
self.shuffle = shuffle
self.on_epoch_end()
def __len__(self):
'Denotes the number of batches per epoch'
return int(np.floor(len(self.list_IDs) / self.batch_size))
def __getitem__(self, index):
'Generate one batch of data'
# Generate indexes of the batch
indexes = self.indexes[index*self.batch_size:(index+1)*self.batch_size]
# Find list of IDs
list_IDs_temp = [self.list_IDs[k] for k in indexes]
# Generate data
X, y = self.__data_generation(list_IDs_temp)
return X, y
def on_epoch_end(self):
'Updates indexes after each epoch'
self.indexes = np.arange(len(self.list_IDs))
if self.shuffle == True:
np.random.shuffle(self.indexes)
def __data_generation(self, list_IDs_temp):
'Generates data containing batch_size samples' # X : (n_samples, *dim, n_channels)
# Initialization
X = np.empty((self.batch_size, *self.dim))
y = np.empty(self.batch_size)
# Generate data
for i, ID in enumerate(list_IDs_temp):
# Store sample
image = cv2.imread(os.getcwd()+"/data/"+str(ID)+".jpg") #read images from disk
image=cv2.resize(image[-150:], (200,66))/255
X[i,] = image
# Store class
y[i] = float(self.labels[ID])
return X, y