Learn practical skills, build real-world projects, and advance your career

Pokemon Classification Model ResNet9

Pokemon.jpg

Image source: usgamer.net

In this project, we are going to train a model for the classification of Pokemons. One of the main reason to choose this project is the large number of classes in which to classify Pokemons.

The number of images used in this project is near about 6,500 and they are classified into 150 different classes.

The dataset is obtained from kaggle.com. The link to the dataset is given below:

Link: https://www.kaggle.com/lantian773030/pokemonclassification

So, let's see how far can we reach in the end of this project.

Importing the required libraries and modules

import os
import torch
import torchvision
# import tarfile
import torch.nn as nn
import numpy as np
import torch.nn.functional as F
# from torchvision.datasets.utils import download_url
from torchvision.datasets import ImageFolder
from torch.utils.data import DataLoader
import torchvision.transforms as tt
from torch.utils.data import random_split
from torchvision.utils import make_grid
import matplotlib
import matplotlib.pyplot as plt
%matplotlib inline

# matplotlib.rcParams['figure.facecolor'] = '#ffffff'

Project Name