HDF5 attempt

import numpy as np
import matplotlib.pyplot as plt
import os
import cv2
from tqdm import tqdm

DATADIR = "E:\Kash project files\Manveer\DataCollection\Scattered\Testing"

CATEGORIES = ["0", "1", "2", "3", "4", "5", "6", "7", "8", "9"]

IMG_SIZE = 100

training_data = []

def create_training_data():
    for category in CATEGORIES:

        path = os.path.join(DATADIR,category)
        class_num = CATEGORIES.index(category)

        for img in tqdm(os.listdir(path)):
            try:
                img_array = cv2.imread(os.path.join(path,img) ,cv2.IMREAD_GRAYSCALE)  # convert to array
                new_array = cv2.resize(img_array, (IMG_SIZE, IMG_SIZE))  # resize to normalize data size
                training_data.append([new_array, class_num])  # add this to our training_data
            except Exception as e:  # in the interest in keeping the output clean...
                pass
            #except OSError as e:
            #    print("OSErrroBad img most likely", e, os.path.join(path,img))
            #except Exception as e:
            #    print("general exception", e, os.path.join(path,img))

create_training_data()

print(len(training_data))

import random

random.shuffle(training_data)

for sample in training_data[:10]:
    print(sample[1])

X = []
y = []

for features,label in training_data:
    X.append(features)
    y.append(label)

print(X[0].reshape(-1, IMG_SIZE, IMG_SIZE, 1))

X = np.array(X).reshape(-1, IMG_SIZE, IMG_SIZE, 1)


import h5py

# import pickle

# pickle_out = open("x_test_plastic40.pickle","wb")
# pickle.dump(X, pickle_out)
# pickle_out.close()

# pickle_out = open("y_test_plastic40.pickle","wb")
# pickle.dump(y, pickle_out)
# pickle_out.close()