VedPDubey

model = tf.keras.Sequential([
    tf.keras.layers.Conv2D(16, 3, activation='relu', input_shape=(150,150,3)),
    tf.keras.layers.MaxPool2D(pool_size=(2,2)),
    tf.keras.layers.Conv2D(32, 3, activation='relu'),
    tf.keras.layers.MaxPool2D(pool_size=(2,2)),
    tf.keras.layers.Dropout(0.2),
    tf.keras.layers.Conv2D(32, 5, activation='relu'),
    tf.keras.layers.MaxPool2D(pool_size=(2,2)),
    tf.keras.layers.Dropout(0.3),
    tf.keras.layers.Conv2D(64, 3, activation='relu'),

VedPDubey

epochs = 200
batch_size = 32

history = model.fit(train_images,train_labels,
                    batch_size=batch_size,
                   steps_per_epoch=len(train_images)//batch_size,
                   epochs=epochs,
                   verbose=1, 
                   validation_data=(val_images,val_labels),
                   validation_steps=len(val_images)//batch_size,

VedPDubey

model = Sequential([
    Input(shape=(96,96,3)),
    ZeroPadding2D((5,5)),
    Conv2D(32, 3, activation='relu'),
    BatchNormalization(),
    MaxPool2D(pool_size=(2,2)),
    Dropout(0.3),
    Conv2D(32, 3, activation='relu'),
    MaxPool2D(pool_size=(2,2)),
    Dropout(0.3),

VedPDubey

def custom_predictions(path):
    img = ig.load_img(path, target_size=(64, 64))
    plt.imshow(img)
    img = np.expand_dims(img, axis=0)
    img.reshape(1,64,64,3)
    prediction = np.argmax(model.predict(img))
    plt.title(labels[prediction])
    plt.show()

VedPDubey

labels = ["00-damage","01-whole"]

it = iter(testing_set)
batch = next(it) # Gets a batch of 16 test images

fig, axes = plt.subplots(3, 3, figsize=(10,10))
fig.tight_layout()
fig.subplots_adjust(hspace=.25)

for i in range(3):

VedPDubey

model = tf.keras.Sequential([
    tf.keras.layers.Conv2D(32, 3, activation='relu', input_shape=(64,64,3)),
    tf.keras.layers.MaxPool2D(pool_size=(2,2)),
    tf.keras.layers.Dropout(0.3),
    tf.keras.layers.Conv2D(32, 3, activation='relu'),
    tf.keras.layers.MaxPool2D(pool_size=(2,2)),
    tf.keras.layers.Dropout(0.3),
    tf.keras.layers.Conv2D(32, 3, activation='relu'),
    tf.keras.layers.MaxPool2D(pool_size=(2,2)),
    tf.keras.layers.Dropout(0.3),

VedPDubey

train_dir = 'data1a/training'
test_dir = 'data1a/validation'

train_data = ImageDataGenerator(rescale = 1./255,shear_range = 0.2, zoom_range = 0.2, horizontal_flip = True)

#defining training set, here size of image is reduced to 150x150, batch of images is kept as 128 and class is defined as 'categorical'.
training_set = train_data.flow_from_directory(train_dir, batch_size = 32, target_size = (64,64), class_mode = 'categorical')

#applying same scale as training set, but only feature scaling is applied. image augmentation is avoided to prevent leakage of testing data.
test_data = ImageDataGenerator(rescale = 1./255)

VedPDubey

test_pred = model.predict(test_images)
test_pred = np.argmax(test_pred,axis=1)
test_actual = np.argmax(test_labels,axis=1)

rnd_idx = random.sample(range(0,400),8)

class_labels = {i:class_name for (class_name,i) in class_name_labels.items()}

for i,idx in enumerate(rnd_idx):
    plt.imshow(test_images[idx])

VedPDubey

def show_final_history(history):
    
    plt.style.use("ggplot")
    fig, ax = plt.subplots(1,2,figsize=(15,5))
    ax[0].set_title('Loss')
    ax[1].set_title('Accuracy')
    ax[0].plot(history.history['loss'],label='Train Loss')
    ax[0].plot(history.history['val_loss'],label='Validation Loss')
    ax[1].plot(history.history['accuracy'],label='Train Accuracy')
    ax[1].plot(history.history['val_accuracy'],label='Validation Accuracy')

VedPDubey

epochs = 50
batch_size = 16

history = model.fit(train_images,train_labels,
                    batch_size=batch_size,
                   steps_per_epoch=len(train_images)//batch_size,
                   epochs=epochs,
                   verbose=1, 
                   validation_data=(val_images,val_labels),
                   validation_steps=len(val_images)//batch_size,