import os
os.environ['KAGGLE_CONFIG_DIR'] = "/content/gdrive/My Drive/Kaggle"
from google.colab import drive
drive.mount('/content/gdrive')

import os
import torch
import pandas as pd
import numpy as np
from torch.utils.data import Dataset, random_split, DataLoader
from PIL import Image
import torchvision.models as models
import matplotlib.pyplot as plt
import torchvision.transforms as transforms
from sklearn.metrics import f1_score
import torch.nn.functional as F
import torchvision.transforms as T
import torch.nn as nn
from torchvision.utils import make_grid
from torchvision.datasets import ImageFolder
%matplotlib inline

# checking the number of images for each class.
data_directory = '/content/gdrive/My Drive/Kaggle/stanford_dogs_dataset/train2/'
#data_directory = '/content/gdrive/My Drive/Kaggle/stanford_dogs_dataset/train/'

num_images = []
for root, dirs, files in os.walk(data_directory):
  if files == []:
    continue
  else:
    num_images.append(len(files))
print(num_images)
# to test the size of the images
image_size_test = ImageFolder(data_directory, T.ToTensor())
len(image_size_test)
#checking the size of the first 10 images in the dataset

im_count = 0
for image,_ in image_size_test:
  im_count += 1
  print(image.shape)
  if im_count == 10:
    break
height = []
width = []
for image,_ in image_size_test:
  height.append(image.shape[1])
  width.append(image.shape[2])
print("minimum height: {}, maximum height: {}, minimum width: {}, maximum width: {}".format(min(height), max(height), min(width), max(width)))

%cd /content/gdrive/My Drive/Kaggle