Deep Learning Exp:1 V

 # Convolutional Neural Network


# Installing Theano

# pip install --upgrade --no-deps git+git://github.com/Theano/Theano.git

# Installing Tensorflow

# Install Tensorflow from the website: https://www.tensorflow.org/versions/r0.12/get_started/os_setup.html

# Installing Keras

# pip install --upgrade keras

# Part 1 - Building the CNN

# Importing the Keras libraries and packages

from keras.models import Sequential

from keras.layers import Convolution2D

from keras.layers import MaxPooling2D

from keras.layers import Flatten

from keras.layers import Dense

# Initialising the CNN

classifier = Sequential()


# Step 1 - Convolution

classifier.add(Convolution2D(32, 3, 3, input_shape = (64, 64, 3), activation = 'relu'))


# Step 2 - Pooling

classifier.add(MaxPooling2D(pool_size = (2, 2)))


# Adding a second convolutional layer

classifier.add(Convolution2D(32, 3, 3, activation = 'relu'))

classifier.add(MaxPooling2D(pool_size = (2, 2)))


# Step 3 - Flattening

classifier.add(Flatten())



# Step 4 - Full connection

classifier.add(Dense(units = 128, activation = 'relu'))

classifier.add(Dense(units = 1, activation = 'sigmoid'))



# Compiling the CNN

classifier.compile(optimizer = 'adam', loss = 'binary_crossentropy', metrics = ['accuracy'])



# Part 2 - Fitting the CNN to the images



from tensorflow.keras.preprocessing.image import ImageDataGenerator



train_datagen = ImageDataGenerator(rescale = 1./255,

                                   shear_range = 0.2,

                                   zoom_range = 0.2,

                                   horizontal_flip = True)



test_datagen = ImageDataGenerator(rescale = 1./255)



training_set = train_datagen.flow_from_directory('/content/drive/MyDrive/1_training_set',

                                                 target_size = (64, 64),

                                                 batch_size = 20,

                                                 class_mode = 'binary')



test_set = test_datagen.flow_from_directory('/content/drive/MyDrive/1_test_set',

                                            target_size = (64, 64),

                                            batch_size = 4,

                                            class_mode = 'binary')

classifier.fit(training_set,

                         steps_per_epoch = 20,

                         epochs = 25,

                         validation_data = test_set,

                         validation_steps = 10)



import numpy as np

from tensorflow.keras.preprocessing import image
from PIL import Image


# Load the trained model

# Assuming you have already trained and saved the model as 'classifier'

model = classifier



# Load the image you want to classify

image_path = '/content/drive/MyDrive/1_predict/dog2.jpg'  # Replace with the actual path of your image

img = image.load_img(image_path, target_size=(64, 64))

new_face = Image.open(image_path)
display(new_face)

# Preprocess the image

img_array = image.img_to_array(img)

img_array = np.expand_dims(img_array, axis=0)

img_array /= 255.0  # Rescale to match the normalization done during training



# Make predictions on the image

predictions = model.predict(img_array)

#predicted_class = np.argmax(predictions)

print("Predictions:", predictions)


predicted_class = np.round(predictions)


# Print the predicted class label

print("Predicted class label:", predicted_class)

if(predicted_class==0):
  print('cat')
else: print('dog')


O/P:

Found 416 images belonging to 2 classes.
Found 42 images belonging to 2 classes.

/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 1/25
20/20 ━━━━━━━━━━━━━━━━━━━━ 5s 144ms/step - accuracy: 0.5143 - loss: 0.6963 - val_accuracy: 0.4500 - val_loss: 0.6924
Epoch 2/25
20/20 ━━━━━━━━━━━━━━━━━━━━ 0s 9ms/step - accuracy: 0.6500 - loss: 0.6898 - val_accuracy: 0.5000 - val_loss: 0.6930
Epoch 3/25

/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()

20/20 ━━━━━━━━━━━━━━━━━━━━ 5s 190ms/step - accuracy: 0.5505 - loss: 0.6911 - val_accuracy: 0.5750 - val_loss: 0.6922
Epoch 4/25
20/20 ━━━━━━━━━━━━━━━━━━━━ 0s 9ms/step - accuracy: 0.5000 - loss: 0.6957 - val_accuracy: 0.5250 - val_loss: 0.6937
Epoch 5/25
20/20 ━━━━━━━━━━━━━━━━━━━━ 2s 103ms/step - accuracy: 0.4921 - loss: 0.6922 - val_accuracy: 0.5000 - val_loss: 0.6919
Epoch 6/25
20/20 ━━━━━━━━━━━━━━━━━━━━ 0s 14ms/step - accuracy: 0.7000 - loss: 0.6866 - val_accuracy: 0.5000 - val_loss: 0.6912
Epoch 7/25
20/20 ━━━━━━━━━━━━━━━━━━━━ 3s 128ms/step - accuracy: 0.5221 - loss: 0.6913 - val_accuracy: 0.5250 - val_loss: 0.6902
Epoch 8/25
20/20 ━━━━━━━━━━━━━━━━━━━━ 0s 16ms/step - accuracy: 0.7000 - loss: 0.6884 - val_accuracy: 0.5000 - val_loss: 0.6923
Epoch 9/25
20/20 ━━━━━━━━━━━━━━━━━━━━ 4s 109ms/step - accuracy: 0.4940 - loss: 0.6942 - val_accuracy: 0.4750 - val_loss: 0.6906
Epoch 10/25
20/20 ━━━━━━━━━━━━━━━━━━━━ 0s 13ms/step - accuracy: 0.5000 - loss: 0.6893 - val_accuracy: 0.5500 - val_loss: 0.6902
Epoch 11/25
20/20 ━━━━━━━━━━━━━━━━━━━━ 3s 141ms/step - accuracy: 0.5963 - loss: 0.6897 - val_accuracy: 0.5750 - val_loss: 0.6906
Epoch 12/25
20/20 ━━━━━━━━━━━━━━━━━━━━ 0s 12ms/step - accuracy: 0.7500 - loss: 0.6851 - val_accuracy: 0.4500 - val_loss: 0.6897
Epoch 13/25
20/20 ━━━━━━━━━━━━━━━━━━━━ 3s 126ms/step - accuracy: 0.5078 - loss: 0.6903 - val_accuracy: 0.5000 - val_loss: 0.6885
Epoch 14/25
20/20 ━━━━━━━━━━━━━━━━━━━━ 0s 10ms/step - accuracy: 0.4500 - loss: 0.6892 - val_accuracy: 0.4750 - val_loss: 0.6914
Epoch 15/25
20/20 ━━━━━━━━━━━━━━━━━━━━ 5s 136ms/step - accuracy: 0.5723 - loss: 0.6833 - val_accuracy: 0.5250 - val_loss: 0.6849
Epoch 16/25
20/20 ━━━━━━━━━━━━━━━━━━━━ 0s 16ms/step - accuracy: 0.4500 - loss: 0.6908 - val_accuracy: 0.5000 - val_loss: 0.6848
Epoch 17/25
20/20 ━━━━━━━━━━━━━━━━━━━━ 5s 153ms/step - accuracy: 0.5518 - loss: 0.6864 - val_accuracy: 0.5500 - val_loss: 0.6847
Epoch 18/25
20/20 ━━━━━━━━━━━━━━━━━━━━ 0s 16ms/step - accuracy: 0.5500 - loss: 0.6924 - val_accuracy: 0.5000 - val_loss: 0.6836
Epoch 19/25
20/20 ━━━━━━━━━━━━━━━━━━━━ 3s 126ms/step - accuracy: 0.5644 - loss: 0.6847 - val_accuracy: 0.5250 - val_loss: 0.6788
Epoch 20/25
20/20 ━━━━━━━━━━━━━━━━━━━━ 0s 9ms/step - accuracy: 0.4000 - loss: 0.6961 - val_accuracy: 0.5250 - val_loss: 0.6839
Epoch 21/25
20/20 ━━━━━━━━━━━━━━━━━━━━ 2s 112ms/step - accuracy: 0.5238 - loss: 0.6879 - val_accuracy: 0.5750 - val_loss: 0.6849
Epoch 22/25
20/20 ━━━━━━━━━━━━━━━━━━━━ 0s 13ms/step - accuracy: 0.6000 - loss: 0.6776 - val_accuracy: 0.5750 - val_loss: 0.6805
Epoch 23/25
20/20 ━━━━━━━━━━━━━━━━━━━━ 3s 129ms/step - accuracy: 0.6066 - loss: 0.6787 - val_accuracy: 0.6000 - val_loss: 0.6877
Epoch 24/25
20/20 ━━━━━━━━━━━━━━━━━━━━ 0s 9ms/step - accuracy: 0.4500 - loss: 0.6907 - val_accuracy: 0.6250 - val_loss: 0.6805
Epoch 25/25
20/20 ━━━━━━━━━━━━━━━━━━━━ 5s 134ms/step - accuracy: 0.6097 - loss: 0.6700 - val_accuracy: 0.5500 - val_loss: 0.6841

1/1 ━━━━━━━━━━━━━━━━━━━━ 0s 204ms/step
Predictions: [[0.631441]]
Predicted class label: [[1.]]
dog

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