Pokemon_Classification

#1

https://colab.research.google.com/drive/1kiOaX7EZE-wQfV8XS_7Heqwxr_6d9m8v

how to fix this error and why is this happening?

#2

Hey @rajukumarbhui, i am unable to view your file, make it shareable and than share the link

#3

https://drive.google.com/file/d/1kiOaX7EZE-wQfV8XS_7Heqwxr_6d9m8v/view?usp=sharing

#4

Hey @rajukumarbhui, you forgot two things, first of all all images are not of same size you need to resize them, secondly linear regression like models must have x_data of shape (NO.of examples, Features). and not like (no. of examples, height, width, 3).

you could do this by

X_data = []
files = glob.glob ("./Train/Images/*.jpg")
for myFile in files:
    image = cv2.imread (myFile)
    image = cv2.resize(image, (100,100))
    image = image.flatten()
    X_data.append (image)

Hope this resolved your doubt.
Plz mark it as resolved in my doubts section. :blush:

#5

https://drive.google.com/file/d/1kiOaX7EZE-wQfV8XS_7Heqwxr_6d9m8v/view?usp=sharing how i change my predicted array and imageid array to a 2d array as mentioned in the sample submission for output

#6

fixed the previous error ,please see this still getting error https://drive.google.com/file/d/1kiOaX7EZE-wQfV8XS_7Heqwxr_6d9m8v/view?usp=sharing

#7

done!! but the accuracy is only 38% using logistic regression

#8

Hey @rajukumarbhui, use svm classifier, and also check results after normalization(img/255.0). :blush:

#9

I hope I’ve cleared your doubt. I ask you to please rate your experience here
Your feedback is very important. It helps us improve our platform and hence provide you
the learning experience you deserve.

On the off chance, you still have some questions or not find the answers satisfactory, you may reopen
the doubt.

#10

even with MLP i am getting an accuracy of about 35% only https://drive.google.com/file/d/1v2MgjVfrBsx_4WvhDH4vi3Yvt1pZgzzc/view?usp=sharing

#11

Hey @rajukumarbhui, train until loss keeps on decreasing.