Scribd
Upload
16 views2 pages

8-Digitalrecognitionusingcnn - Jupyter Notebook

Uploaded by

064- sarvani
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
16 views2 pages

8-Digitalrecognitionusingcnn - Jupyter Notebook

Uploaded by

064- sarvani
Copyright
© © All Rights Reserved
We take content rights seriously. If you suspect this is your content, claim it here.
Available Formats
Download as PDF, TXT or read online on Scribd
You are on page 1/ 2

13/06/2024, 08:12 8-digitalrecognitionusingcnn - Jupyter Notebook

In [2]: from keras.datasets import mnist


from keras.models import Sequential
from keras.layers import Dense, Conv2D, MaxPooling2D, Flatten
from keras.optimizers import Adam
from keras.losses import SparseCategoricalCrossentropy
import numpy
import matplotlib.pyplot as plt

--------------------------------------------------------------------------
-
ModuleNotFoundError Traceback (most recent call las
t)
Input In [2], in <cell line: 1>()
----> 1 from keras.datasets import mnist
2 from keras.models import Sequential
3 from keras.layers import Dense, Conv2D, MaxPooling2D, Flatten

ModuleNotFoundError: No module named 'keras'

In [3]: (train_images, train_labels), (test_images, test_labels) = mnist.load_data()

--------------------------------------------------------------------------
-
NameError Traceback (most recent call las
t)
Input In [3], in <cell line: 1>()
----> 1 (train_images, train_labels), (test_images, test_labels) = mnist.l
oad_data()

NameError: name 'mnist' is not defined

In [ ]: train_images = train_images/255.0
test_images = test_images/255.0

In [ ]: train_images = train_images.reshape((len(train_images), 28, 28, 1))


test_images = test_images.reshape((len(test_images), 28, 28, 1))

In [ ]: model = Sequential([

Conv2D(filters=32, kernel_size=(3, 3), activation='relu'),


MaxPooling2D(),
Conv2D(filters=64, kernel_size=(3, 3), activation='relu'),
MaxPooling2D(),
Conv2D(filters=128, kernel_size=(3, 3), activation='relu'),
MaxPooling2D(),

Flatten(),
Dense(units=28, activation='relu'),
Dense(units=len(set(train_labels)))
])

localhost:8888/notebooks/Desktop/ml lab/8/8-digitalrecognitionusingcnn.ipynb 1/2


13/06/2024, 08:12 8-digitalrecognitionusingcnn - Jupyter Notebook

In [ ]: model.compile(optimizer='adam', loss=SparseCategoricalCrossentropy(from_logi
model.fit(x=train_images, y=train_labels, batch_size=32, epochs=10)

In [ ]: pred = model.predict(test_images)

In [ ]: ran = numpy.random.randint(low=0, high=100)


plt.imshow(test_images[ran])

In [ ]: numpy.argmax(pred[ran])

In [ ]: ​

localhost:8888/notebooks/Desktop/ml lab/8/8-digitalrecognitionusingcnn.ipynb 2/2

You might also like