Skip to main content

2-C .Understanding and Using ANN : Identifying age group of an actor

 AIM:  Design Artificial Neural Networks for Identifying and Classifying an actor using Kaggle Dataset.

Link to download Model file:

https://drive.google.com/file/d/12lsyOHe5QifEaiW_d9K8BLLy5PeCEWsf/view?usp=sharing


Link to Images to test:

https://drive.google.com/drive/folders/1xhQJSzL_OL72YXBgdQD10_JmYpHPngLu?usp=sharing


Program to predict Face Image's Age group:

from tensorflow.keras.models import load_model
from PIL import Image
import numpy as np


# Define the input image dimensions
image_height = 128
image_width = 128
num_channels = 3

# Load the trained model
model = load_model('/content/drive/MyDrive/trained_model_C_Dataset.h5') # Replace 'your_trained_model.h5' with the actual file name

# Read the new face image
new_face_path = '/content/drive/MyDrive/2_Predict/old.jpeg'  # Replace 'path_to_new_face.jpg' with the actual file path
new_face = Image.open(new_face_path)
display(new_face)
# Preprocess the image
new_face = new_face.resize((image_width, image_height))
#new_face.show()
print('path ',new_face_path )
new_face = np.array(new_face)
#new_face = new_face.astype('float32') / 255.0
new_face = np.expand_dims(new_face, axis=0)  # Add a batch dimension

# Perform prediction
predictions = model.predict(new_face)
predicted_age_group = np.argmax(predictions)
print("predictions are ",predictions)
print("Predicted Age Group:", predicted_age_group)

# Map the predicted age group index to the actual label
age_mapping = {0: 'YOUNG', 1: 'MIDDLE', 2: 'OLD'}  # Update with your age group labels mapping
predicted_age_group_label = age_mapping[predicted_age_group]

print("Predicted Age Group:", predicted_age_group_label)

O/p:

WARNING:absl:Compiled the loaded model, but the compiled metrics have yet to be built. `model.compile_metrics` will be empty until you train or evaluate the model.

path  /content/drive/MyDrive/2_Predict/a.jpg
1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 152ms/step
predictions are  [[0.43104544 0.16487518 0.40407938]]
Predicted Age Group: 0
Predicted Age Group: YOUNG


Program to build Model:


#@title
import numpy as np
import pandas as pd
from sklearn.model_selection import train_test_split
from keras.models import Sequential
from keras.layers import Dense, Conv2D, MaxPooling2D, Flatten
from tensorflow.keras.preprocessing.image import ImageDataGenerator
from keras.utils import to_categorical
from PIL import Image
from sklearn.preprocessing import LabelEncoder

# Load the dataset
dataset = pd.read_csv('/content/drive/MyDrive/2_2_Dataset/train.csv')  # Replace 'kaggle_dataset.csv' with the actual dataset file

# Preprocess the dataset
# Assuming the dataset has 'image_path' column for image file paths and 'age_group' column for age group labels


# Define the input image dimensions
image_height = 128
image_width = 128
num_channels = 3

# Load and preprocess images
X = []
for image_path in '/content/drive/MyDrive/2_2_Dataset/'+dataset['ID']:
    print(image_path)
    img = Image.open(image_path)
    #img.show()
    img = img.resize((image_width, image_height))
    img = np.array(img)
    X.append(img)

# Split dataset into images and labels
X = np.array(X)

y = np.array(dataset['Class'])

# Encode labels to integers
label_encoder = LabelEncoder()
y = label_encoder.fit_transform(y)

# Split into training and testing sets
X_train, X_test, y_train, y_test = train_test_split(X, y, test_size=0.2, random_state=42)

# Define the number of classes
num_classes = len(label_encoder.classes_)


# Convert labels to one-hot encoding
y_train = to_categorical(y_train, num_classes)
y_test = to_categorical(y_test, num_classes)

# Define the input image dimensions
image_height = 128
image_width = 128
num_channels = 3

# Define the model architecture
model = Sequential()
model.add(Conv2D(32, (3, 3), activation='relu', input_shape=(image_height, image_width, num_channels)))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Conv2D(64, (3, 3), activation='relu'))
model.add(MaxPooling2D(pool_size=(2, 2)))
model.add(Flatten())
model.add(Dense(128, activation='relu'))
model.add(Dense(num_classes, activation='softmax'))

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

# Data augmentation
datagen = ImageDataGenerator(rotation_range=20, width_shift_range=0.1, height_shift_range=0.1, horizontal_flip=True)

# Train the model
batch_size = 32
epochs = 20
steps_per_epoch = len(X_train) // batch_size
model.fit(datagen.flow(X_train, y_train, batch_size=batch_size), steps_per_epoch=steps_per_epoch, epochs=epochs)

# Evaluate the model
accuracy = model.evaluate(X_test, y_test)[1]
print("Accuracy:", accuracy)


# Save the trained model
model.save('/content/drive/MyDrive/trained_model_C_Dataset.h5')

O/p:

Streaming output truncated to the last 5000 lines. /content/drive/MyDrive/2_2_Dataset/11430.jpg /content/drive/MyDrive/2_2_Dataset/14976.jpg /content/drive/MyDrive/2_2_Dataset/8698.jpg /content/drive/MyDrive/2_2_Dataset/7492.jpg /content/drive/MyDrive/2_2_Dataset/6134.jpg /content/drive/MyDrive/2_2_Dataset/13508.jpg
---
---
---
---
---
/usr/local/lib/python3.11/dist-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)
/usr/local/lib/python3.11/dist-packages/keras/src/trainers/data_adapters/py_dataset_adapter.py:121: UserWarning: Your `PyDataset` class should call `super().__init__(**kwargs)` in its constructor. `**kwargs` can include `workers`, `use_multiprocessing`, `max_queue_size`. Do not pass these arguments to `fit()`, as they will be ignored.
  self._warn_if_super_not_called()

Epoch 1/20
497/497 ━━━━━━━━━━━━━━━━━━━━ 68s 128ms/step - accuracy: 0.5384 - loss: 47.1915
Epoch 2/20
497/497 ━━━━━━━━━━━━━━━━━━━━ 0s 39us/step - accuracy: 0.5000 - loss: 0.9528   
Epoch 3/20

/usr/local/lib/python3.11/dist-packages/keras/src/trainers/epoch_iterator.py:107: UserWarning: Your input ran out of data; interrupting training. Make sure that your dataset or generator can generate at least `steps_per_epoch * epochs` batches. You may need to use the `.repeat()` function when building your dataset.
  self._interrupted_warning()

497/497 ━━━━━━━━━━━━━━━━━━━━ 79s 129ms/step - accuracy: 0.5732 - loss: 0.9334
Epoch 4/20
497/497 ━━━━━━━━━━━━━━━━━━━━ 0s 27us/step - accuracy: 0.6250 - loss: 0.8409   
Epoch 5/20
497/497 ━━━━━━━━━━━━━━━━━━━━ 64s 128ms/step - accuracy: 0.5641 - loss: 0.9466
Epoch 6/20
497/497 ━━━━━━━━━━━━━━━━━━━━ 0s 26us/step - accuracy: 0.7500 - loss: 0.7550   
Epoch 7/20
497/497 ━━━━━━━━━━━━━━━━━━━━ 82s 128ms/step - accuracy: 0.5776 - loss: 0.9314
Epoch 8/20
497/497 ━━━━━━━━━━━━━━━━━━━━ 0s 47us/step - accuracy: 0.7188 - loss: 0.7428   
Epoch 9/20
497/497 ━━━━━━━━━━━━━━━━━━━━ 81s 128ms/step - accuracy: 0.5702 - loss: 0.9321
Epoch 10/20
497/497 ━━━━━━━━━━━━━━━━━━━━ 0s 25us/step - accuracy: 0.6250 - loss: 0.9372  
Epoch 11/20
497/497 ━━━━━━━━━━━━━━━━━━━━ 63s 128ms/step - accuracy: 0.5738 - loss: 0.9334
Epoch 12/20
497/497 ━━━━━━━━━━━━━━━━━━━━ 0s 35us/step - accuracy: 0.6250 - loss: 0.8514   
Epoch 13/20
497/497 ━━━━━━━━━━━━━━━━━━━━ 83s 129ms/step - accuracy: 0.5807 - loss: 0.9264
Epoch 14/20
497/497 ━━━━━━━━━━━━━━━━━━━━ 0s 28us/step - accuracy: 0.5312 - loss: 0.8849 
Epoch 15/20
497/497 ━━━━━━━━━━━━━━━━━━━━ 82s 129ms/step - accuracy: 0.5750 - loss: 0.9312
Epoch 16/20
497/497 ━━━━━━━━━━━━━━━━━━━━ 0s 24us/step - accuracy: 0.5938 - loss: 0.8832  
Epoch 17/20
497/497 ━━━━━━━━━━━━━━━━━━━━ 80s 126ms/step - accuracy: 0.5702 - loss: 0.9422
Epoch 18/20
497/497 ━━━━━━━━━━━━━━━━━━━━ 0s 26us/step - accuracy: 0.7188 - loss: 0.7283  
Epoch 19/20
497/497 ━━━━━━━━━━━━━━━━━━━━ 65s 131ms/step - accuracy: 0.5709 - loss: 0.9336
Epoch 20/20
497/497 ━━━━━━━━━━━━━━━━━━━━ 0s 25us/step - accuracy: 0.4688 - loss: 1.0196  
125/125 ━━━━━━━━━━━━━━━━━━━━ 2s 9ms/step - accuracy: 0.5840 - loss: 0.9143

WARNING:absl:You are saving your model as an HDF5 file via `model.save()` or `keras.saving.save_model(model)`. This file format is considered legacy. We recommend using instead the native Keras format, e.g. `model.save('my_model.keras')` or `keras.saving.save_model(model, 'my_model.keras')`. 

Accuracy: 0.5858864784240723



Comments

Post a Comment

Popular posts from this blog

11. List of Capstone Projects for SOC - Deep Learning

 List of Capstone Projects for SOC - Deep Learning  1. Build your Own Neural Net from Scratch. 2. Image Classification with CIFAR-10 Dataset.(Multi Class Classification) CNN 3. Human Face Detection.( detecting the bounding boxes of the human faces from a given Image)  YOLO  4. Traffic Sign Classification.(Collect Various traffic Signal Images and train Neural Network Model) CNN 5. Text Summarizer. RNN 6. Chatbot Using Deep Learning ( Training/Generative) 7. Colouring old B&W photos (Deep Neural Networks OpenCV) 8. Animal detection by training from multiple classes (CNN) 9. Face detection
Read more

8. Advanced CNN (Build AlexNet using Advanced CNN)

  Building and training an AlexNet-like model using the CIFAR-10 dataset in TensorFlow/Keras: Program to build the model: import tensorflow as tf from tensorflow.keras.layers import Conv2D, MaxPooling2D, Flatten, Dense, Dropout from tensorflow.keras.datasets import cifar10 from tensorflow.keras.utils import to_categorical from sklearn.model_selection import train_test_split # Load and preprocess CIFAR-10 dataset (x_train, y_train), (x_test, y_test) = cifar10.load_data() x_train = x_train.astype( 'float32' ) / 255.0 x_test = x_test.astype( 'float32' ) / 255.0 y_train = to_categorical(y_train, num_classes= 10 ) y_test = to_categorical(y_test, num_classes= 10 ) # Split into training and validation sets x_train, x_val, y_train, y_val = train_test_split(x_train, y_train, test_size= 0.1 , random_state= 42 ) # Define the model architecture '''model = tf.keras.Sequential([     Conv2D(96, (11, 11), strides=(4, 4), activation='relu', input_shape=(32...
Read more