[go: up one dir, main page]
Scribd
Upload
2 views2 pages

Exp 7-1

The document provides a Python script that utilizes the VGG16 model from TensorFlow to classify an image of a cat. It includes functions to load and preprocess the image, make predictions, and display the results. The predictions indicate the likelihood of the image being an Egyptian cat, tabby, or tiger cat, with associated probabilities.

Uploaded by

nagallahema2004
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
2 views2 pages

Exp 7-1

The document provides a Python script that utilizes the VGG16 model from TensorFlow to classify an image of a cat. It includes functions to load and preprocess the image, make predictions, and display the results. The predictions indicate the likelihood of the image being an Egyptian cat, tabby, or tiger cat, with associated probabilities.

Uploaded by

nagallahema2004
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

import tensorflow as tf

from tensorflow.keras.applications import VGG16


from tensorflow.keras.preprocessing.image import load_img,
img_to_array
from tensorflow.keras.applications.vgg16 import preprocess_input,
decode_predictions
import numpy as np
import matplotlib.pyplot as plt

model = VGG16(weights='imagenet')

Downloading data from https://storage.googleapis.com/tensorflow/keras-


applications/vgg16/vgg16_weights_tf_dim_ordering_tf_kernels.h5
553467096/553467096 ━━━━━━━━━━━━━━━━━━━━ 842s 2us/step

# Function to load and preprocess an image


def load_and_preprocess_image(image_path, target_size=(224, 224)):
img = load_img(image_path, target_size=target_size) # Load the image
img_array = img_to_array(img) # Convert to array
img_array = np.expand_dims(img_array, axis=0) # Expand dimensions to
match
img_array = preprocess_input(img_array) # Preprocess the image
return img_array, img

def predict_image(model, img_array):


predictions = model.predict(img_array) # Get predictions
decoded_predictions = decode_predictions(predictions, top=3)[0] #
Decode t
return decoded_predictions

image_path = r'C:\Users\nagal\OneDrive\Desktop\cat.jpg' # Corrected


file path
img_array, img = load_and_preprocess_image(image_path)
predictions = predict_image(model, img_array)
# Display the input image
plt.imshow(img)
plt.title("Input Image")
plt.axis('off')
plt.show()

1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 260ms/step


Downloading data from
https://storage.googleapis.com/download.tensorflow.org/data/imagenet_c
lass_index.json
35363/35363 ━━━━━━━━━━━━━━━━━━━━ 1s 14us/step
for pred in predictions:
print(f"Predicted: {pred[1]} with a probability of {pred[2]*100:.2f}
%")

Predicted: Egyptian_cat with a probability of 49.79%


Predicted: tabby with a probability of 38.66%
Predicted: tiger_cat with a probability of 8.95%

You might also like