Scribd
Upload
28 views5 pages

DL 2

The document outlines an assignment to build a multiclass classifier using a CNN model with the MNIST dataset. It includes steps for data preprocessing, model definition, training, and evaluation using a confusion matrix. The final model achieved a test accuracy of 99.10% and provides a classification report and confusion matrix visualization.

Uploaded by

gayatri.jagadale.aids.2021
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
28 views5 pages

DL 2

The document outlines an assignment to build a multiclass classifier using a CNN model with the MNIST dataset. It includes steps for data preprocessing, model definition, training, and evaluation using a confusion matrix. The final model achieved a test accuracy of 99.10% and provides a classification report and confusion matrix visualization.

Uploaded by

gayatri.jagadale.aids.2021
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/ 5

Assingmnet No.

: 2
Name: Gayatri Rajendra Jagadale
Roll No.:2447062
Batch: D
Problem Statement –
Build a Multiclass classifier using the CNN model. Use MNIST or any other suitable dataset. a.
Perform Data Pre-processing b. Define Model and perform training c. Evaluate Results using
confusion matrix.

import numpy as np
import matplotlib.pyplot as plt
import seaborn as sns
from tensorflow.keras.datasets import mnist from
tensorflow.keras.utils import to_categorical from
tensorflow.keras.models import Sequential
from tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten,
Dense, Dropout
from sklearn.metrics import confusion_matrix, classification_report

# Load MNIST dataset


(x_train, y_train), (x_test, y_test) = mnist.load_data()

# Display first 9 images from the training set


plt.figure(figsize=(6,6)) for i in range(9):
plt.subplot(3,3,i+1)
plt.imshow(x_train[i].reshape(28,28), cmap='gray')
plt.title(f"Label: {y_train[i]}") plt.axis('off')
plt.tight_layout()
plt.show()
# Reshape data to add channel dimension
x_train = x_train.reshape(-1, 28, 28, 1).astype('float32') / 255.0
x_test = x_test.reshape(-1, 28, 28, 1).astype('float32') / 255.0

# One-hot encode the labels


y_train_cat = to_categorical(y_train, 10)
y_test_cat = to_categorical(y_test, 10)

model = Sequential([
Conv2D(32, kernel_size=(3,3), activation='relu',
input_shape=(28,28,1)),
MaxPooling2D(pool_size=(2,2)),

Conv2D(64, kernel_size=(3,3), activation='relu'),


MaxPooling2D(pool_size=(2,2)),

Flatten(),
Dense(128, activation='relu'),
Dropout(0.5),
Dense(10, activation='softmax') # 10 classes for MNIST
])

D:\Users\shrey\anaconda3\lib\site-packages\keras\src\layers\
convolutional\base_conv.py:107: UserWarning: Do not pass an
`input_shape`/`input_dim` argument to a layer. When using Sequential
models, prefer using an `Input(shape)` object as the first layer in
the model instead.
super().__init__(activity_regularizer=activity_regularizer,
**kwargs)

model.compile(optimizer='adam', loss='categorical_crossentropy',
metrics=['accuracy'])

history = model.fit(x_train, y_train_cat, epochs=5, batch_size=128,


validation_split=0.1)

Epoch 1/5 422/422 ━━━━━━━━━━━━━━━━━━━━ 9s 20ms/step -


accuracy: 0.7977 - loss:
0.6469 - val_accuracy: 0.9817 - val_loss: 0.0636 Epoch 2/5 422/422
━━━━━━━━━━━━━━━━━━━━ 9s 21ms/step - accuracy: 0.9668 -
loss:
0.1096 - val_accuracy: 0.9858 - val_loss: 0.0497 Epoch 3/5 422/422
━━━━━━━━━━━━━━━━━━━━ 8s 20ms/step - accuracy: 0.9775 -
loss:
0.0743 - val_accuracy: 0.9883 - val_loss: 0.0423 Epoch 4/5 422/422
━━━━━━━━━━━━━━━━━━━━ 8s 20ms/step - accuracy: 0.9805 -
loss:
0.0638 - val_accuracy: 0.9903 - val_loss: 0.0355 Epoch 5/5 422/422
━━━━━━━━━━━━━━━━━━━━ 9s 22ms/step - accuracy: 0.9852 -
loss:
0.0495 - val_accuracy: 0.9905 - val_loss: 0.0347

y_pred = model.predict(x_test)
y_pred_classes = np.argmax(y_pred, axis=1)

313/313 ━━━━━━━━━━━━━━━━━━━━ 1s 3ms/step

# Evaluate the model on test data


test_loss, test_accuracy = model.evaluate(x_test, y_test_cat,
verbose=0)
print(f"Test Accuracy: {test_accuracy * 100:.2f}%")

Test Accuracy: 99.10%

# Print classification report


print(classification_report(y_test, y_pred_classes))

precision recall f1-score support


0 0.99 1.00 0.99 980
1 1.00 0.99 0.99 1135
2 0.99 0.99 0.99 1032
3 0.99 0.99 0.99 1010
4 0.99 0.99 0.99 982
5 0.98 0.99 0.99 892
6 1.00 0.99 0.99 958
7 0.99 0.99 0.99 1028
8 0.98 0.99 0.99 974
9 0.99 0.99 0.99 1009
accuracy 0.99 10000
macro avg 0.99 0.99 0.99 10000
weighted avg 0.99 0.99 0.99 10000
cm = confusion_matrix(y_test, y_pred_classes)

plt.figure(figsize=(10,8))
sns.heatmap(cm, annot=True, fmt='d', cmap='Blues',
xticklabels=range(10), yticklabels=range(10))
plt.title('Confusion Matrix')
plt.xlabel('Predicted Label') plt.ylabel('True
Label') plt.show()

You might also like