What's wrong with the following code implementing knn? - python-2.7

Question

This is the modified code from what I found here.
import numpy as np
import cv2
from matplotlib import pyplot as plt
img = cv2.imread('digits.png')
gray = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
# Now we split the image to 5000 cells, each 20x20 size
cells = [np.hsplit(row,100) for row in np.vsplit(gray,50)]
# Make it into a Numpy array. It size will be (50,100,20,20)
x = np.array(cells)
# Now we prepare train_data.
train = x[:,:50].reshape(-1,400).astype(np.float32) # Size = (2500,400)
img = cv2.imread('1.png')
img1 = cv2.imread('2.png')
img = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
img1 = cv2.cvtColor(img1,cv2.COLOR_BGR2GRAY)
img = cv2.resize(img, (20,20)).astype(np.float32)
img1 = cv2.resize(img1, (20,20)).astype(np.float32)
img = img.flatten()
img1 = img1.flatten()
arr = [img,img1]
arr = np.asarray(arr)
# Create labels for train and test data
k = np.arange(10)
train_labels = np.repeat(k,250)[:,np.newaxis]
# Initiate kNN, train the data, then test it with test data for k=1
knn = cv2.ml.KNearest_create()
knn.train(train, 0,train_labels)
ret, result, neighbours, dist = knn.findNearest(arr, k=5)
for i in result:
print i
# save the data
np.savez('knn_data.npz',train=train, train_labels=train_labels)
# Now load the data
with np.load('knn_data.npz') as data:
print data.files
train = data['train']
train_labels = data['train_labels']
which works perfectly. But I can't figure out, how to use this knn_data.npz file.
This was my attempt:
import numpy as np
import cv2
from matplotlib import pyplot as plt
with np.load('knn_data.npz') as data:
print data.files
train = data['train']
train_labels = data['train_labels']
img = cv2.imread('1.png')
img1 = cv2.imread('2.png')
img = cv2.cvtColor(img,cv2.COLOR_BGR2GRAY)
img1 = cv2.cvtColor(img1,cv2.COLOR_BGR2GRAY)
img = cv2.resize(img, (20,20)).astype(np.float32)
img1 = cv2.resize(img1, (20,20)).astype(np.float32)
img = img.flatten()
img1 = img1.flatten()
arr = [img,img1]
arr = np.asarray(arr)
knn = cv2.ml.KNearest_create()
ret, result, neighbours, dist = knn.findNearest(arr, k=5)
for i in result:
print i
The error message I got, which I could not fix was:
OpenCV Error: Assertion failed (test_samples.type() == 5 && test_samples.cols == samples.cols) in findNearest, file /io/opencv/modules/ml/src/knearest.cpp, line 325
Traceback (most recent call last):
File "knn1.py", line 20, in
ret, result, neighbours, dist = knn.findNearest(img, k=5)
cv2.error: /io/opencv/modules/ml/src/knearest.cpp:325: error: (-215) test_samples.type() == 5 && test_samples.cols == samples.cols in function findNearest
I am using opencv 3.2.0 on python 2.7.15 in ubuntu 18.04. The files 1.png and 2.png are RGB-image files.

Answer 1

In your example, you create the variables train and train_labels but never use them.
Add the following anywhere before you call knn.findNearest(arr, k=5):
train = data['train']
train_labels = data['train_labels']
knn = cv2.ml.KNearest_create()
knn.train(train, 0,train_labels)