Scribd Logo
Upload

Welcome to Scribd!

  • 9 views

    Import As Import As Import Import As Import As From Import From Import From Import From Import From Import From Import

    Uploaded by

    indhaygude07

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd

    Import As Import As Import Import As Import As From Import From Import From Import From Import From Import From Import

    Uploaded by

    indhaygude07
    9 views4 pages

    Original Title

    DL3

    Copyright

    © © All Rights Reserved

    Available Formats

    PDF, TXT or read online from Scribd

    Did you find this document useful?

    Is this content inappropriate?

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    9 views4 pages

    Import As Import As Import Import As Import As From Import From Import From Import From Import From Import From Import

    Uploaded by

    indhaygude07

    Copyright:

    © All Rights Reserved
    Download as PDF, TXT or read online from Scribd
    Download as pdf or txt
    of 4

    import numpy as np

    import pandas as pd
    import random
    import tensorflow as tf
    import matplotlib.pyplot as plt
    from sklearn.metrics import accuracy_score

    from tensorflow.keras.models import Sequential


    from tensorflow.keras.layers import Flatten, Conv2D, Dense, MaxPooling2D
    from tensorflow.keras.optimizers import SGD
    from tensorflow.keras.utils import to_categorical
    from tensorflow.keras.datasets import mnist

    WARNING:tensorflow:From C:\Users\rutik\anaconda3\Lib\site-packages\keras\src\losses.py:2976: The name tf.losses.


    sparse_softmax_cross_entropy is deprecated. Please use tf.compat.v1.losses.sparse_softmax_cross_entropy instead.

    (X_train, y_train), (X_test, y_test) = mnist.load_data()

    print(X_train.shape)

    (60000, 28, 28)

    X_train[0].min(), X_train[0].max()

    (0, 255)

    X_train = (X_train - 0.0) / (255.0 - 0.0)


    X_test = (X_test - 0.0) / (255.0 - 0.0)
    X_train[0].min(), X_train[0].max()

    (0.0, 1.0)

    def plot_digit(image, digit, plt, i):


    plt.subplot(4, 5, i + 1)
    plt.imshow(image, cmap=plt.get_cmap('gray'))
    plt.title(f"Digit: {digit}")
    plt.xticks([])
    plt.yticks([])
    plt.figure(figsize=(16, 10))
    for i in range(20):
    plot_digit(X_train[i], y_train[i], plt, i)
    plt.show()

    X_train = X_train.reshape((X_train.shape + (1,)))


    X_test = X_test.reshape((X_test.shape + (1,)))
    y_train[0:20]

    array([5, 0, 4, 1, 9, 2, 1, 3, 1, 4, 3, 5, 3, 6, 1, 7, 2, 8, 6, 9],
    dtype=uint8)

    model = Sequential([
    Conv2D(32, (3, 3), activation="relu", input_shape=(28, 28, 1)),
    MaxPooling2D((2, 2)),
    Flatten(),
    Dense(100, activation="relu"),
    Dense(10, activation="softmax")
    ])

    WARNING:tensorflow:From C:\Users\rutik\anaconda3\Lib\site-packages\keras\src\backend.py:873: The name tf.get_def


    ault_graph is deprecated. Please use tf.compat.v1.get_default_graph instead.

    WARNING:tensorflow:From C:\Users\rutik\anaconda3\Lib\site-packages\keras\src\layers\pooling\max_pooling2d.py:161
    : The name tf.nn.max_pool is deprecated. Please use tf.nn.max_pool2d instead.

    optimizer = SGD(learning_rate=0.01, momentum=0.9)


    model.compile(
    optimizer=optimizer,
    loss="sparse_categorical_crossentropy",
    metrics=["accuracy"]
    )
    model.summary()

    Model: "sequential"
    _________________________________________________________________
    Layer (type) Output Shape Param #
    =================================================================
    conv2d (Conv2D) (None, 26, 26, 32) 320

    max_pooling2d (MaxPooling2 (None, 13, 13, 32) 0


    D)

    flatten (Flatten) (None, 5408) 0

    dense (Dense) (None, 100) 540900

    dense_1 (Dense) (None, 10) 1010

    =================================================================
    Total params: 542230 (2.07 MB)
    Trainable params: 542230 (2.07 MB)
    Non-trainable params: 0 (0.00 Byte)
    _________________________________________________________________

    model.fit(X_train, y_train, epochs=10, batch_size=32)

    Epoch 1/10
    WARNING:tensorflow:From C:\Users\rutik\anaconda3\Lib\site-packages\keras\src\utils\tf_utils.py:492: The name tf.
    ragged.RaggedTensorValue is deprecated. Please use tf.compat.v1.ragged.RaggedTensorValue instead.

    WARNING:tensorflow:From C:\Users\rutik\anaconda3\Lib\site-packages\keras\src\engine\base_layer_utils.py:384: The


    name tf.executing_eagerly_outside_functions is deprecated. Please use tf.compat.v1.executing_eagerly_outside_fun
    ctions instead.

    1875/1875 [==============================] - 29s 14ms/step - loss: 0.2402 - accuracy: 0.9278


    Epoch 2/10
    1875/1875 [==============================] - 28s 15ms/step - loss: 0.0799 - accuracy: 0.9765
    Epoch 3/10
    1875/1875 [==============================] - 26s 14ms/step - loss: 0.0525 - accuracy: 0.9844
    Epoch 4/10
    1875/1875 [==============================] - 28s 15ms/step - loss: 0.0379 - accuracy: 0.9881
    Epoch 5/10
    1875/1875 [==============================] - 29s 16ms/step - loss: 0.0294 - accuracy: 0.9909
    Epoch 6/10
    1875/1875 [==============================] - 27s 14ms/step - loss: 0.0219 - accuracy: 0.9933
    Epoch 7/10
    1875/1875 [==============================] - 27s 14ms/step - loss: 0.0160 - accuracy: 0.9951
    Epoch 8/10
    1875/1875 [==============================] - 26s 14ms/step - loss: 0.0121 - accuracy: 0.9963
    Epoch 9/10
    1875/1875 [==============================] - 27s 15ms/step - loss: 0.0094 - accuracy: 0.9974
    Epoch 10/10
    1875/1875 [==============================] - 27s 15ms/step - loss: 0.0063 - accuracy: 0.9984
    <keras.src.callbacks.History at 0x13f38a25010>

    plt.figure(figsize=(16, 10))
    for i in range(20):
    image = random.choice(X_test).squeeze()
    digit = np.argmax(model.predict(image.reshape((1, 28, 28, 1)))[0], axis=-1)
    plot_digit(image, digit, plt, i)
    plt.show()

    1/1 [==============================] - 0s 270ms/step


    1/1 [==============================] - 0s 77ms/step
    1/1 [==============================] - 0s 48ms/step
    1/1 [==============================] - 0s 67ms/step
    1/1 [==============================] - 0s 71ms/step
    1/1 [==============================] - 0s 49ms/step
    1/1 [==============================] - 0s 51ms/step
    1/1 [==============================] - 0s 56ms/step
    1/1 [==============================] - 0s 51ms/step
    1/1 [==============================] - 0s 51ms/step
    1/1 [==============================] - 0s 51ms/step
    1/1 [==============================] - 0s 52ms/step
    1/1 [==============================] - 0s 55ms/step
    1/1 [==============================] - 0s 49ms/step
    1/1 [==============================] - 0s 53ms/step
    1/1 [==============================] - 0s 56ms/step
    1/1 [==============================] - 0s 49ms/step
    1/1 [==============================] - 0s 52ms/step
    1/1 [==============================] - 0s 50ms/step
    1/1 [==============================] - 0s 56ms/step

    predictions = np.argmax(model.predict(X_test), axis=-1)


    accuracy_score(y_test, predictions)*100

    313/313 [==============================] - 2s 6ms/step


    98.69

    n=random.randint(0,9999)
    plt.imshow(X_test[n])
    plt.show()
    predicted_value=model.predict(X_test)
    print("Handwritten number in the image is= %d" %np.argmax(predicted_value[n]))

    313/313 [==============================] - 2s 6ms/step


    Handwritten number in the image is= 8

    score = model.evaluate(X_test, y_test, verbose=0)


    print('Test loss:', score[0]) #Test loss: 0.0296396646054
    print('Test accuracy:', score[1])

    Test loss: 0.04847879707813263


    Test accuracy: 0.9868999719619751

    #The implemented CNN model is giving Loss=0.04624301567673683 and


    #accuracy: 0.9872000217437744 for test mnist dataset
    Loading [MathJax]/jax/output/CommonHTML/fonts/TeX/fontdata.js

    You might also like

    pFad - Phonifier reborn

    Pfad - The Proxy pFad of © 2024 Garber Painting. All rights reserved.

    Note: This service is not intended for secure transactions such as banking, social media, email, or purchasing. Use at your own risk. We assume no liability whatsoever for broken pages.


    Alternative Proxies:

    Alternative Proxy

    pFad Proxy

    pFad v3 Proxy

    pFad v4 Proxy