Face Attributes ML-thon 2021

# Core libraries. Tensorflow for making Neural Networks import numpy as np import pandas as pd import tensorflow as tf from tensorflow.keras import Model from tensorflow.keras.layers import Dense, Flatten, Input, Dropout from tensorflow.keras.applications import VGG16 from tensorflow.keras.preprocessing.image import ImageDataGenerator from tensorflow.keras.callbacks import * from sklearn.model_selection import train_test_split # Data Visualization import matplotlib.pyplot as plt import seaborn as sns

# Define the folder where all the images are there folder = '../input/face-attributes-ml-thon-2021/images/images/' # Reading the train data train = pd.read_csv('../input/face-attributes-ml-thon-2021/face_attribute_train.csv')

train

plt.title("Wearing Accessories or not") sns.countplot(y='Wearing_Accessories', data=train, color="c") plt.show()

print("Percentage of positives") (train['Wearing_Accessories'] == 1).sum() / len(train) * 100

Percentage of positives

plt.title('Thick Lips or not') sns.countplot(y='Thick_Lips_Nose', data=train, color="c") plt.show()

print("Percentage of positives") (train['Thick_Lips_Nose'] == 1).sum() / len(train) * 100

Percentage of positives

img = plt.imread(folder + "0.jpg") print("Image dimensions") print(img.shape) plt.imshow(img)

Image dimensions
(218, 178, 3)

train_df, val_df = train_test_split(train, test_size=0.1)

datagen = ImageDataGenerator(rescale=1./255.) columns = ['Wearing_Accessories', 'Thick_Lips_Nose'] train_generator = datagen.flow_from_dataframe(train_df, folder, x_col = 'image_id', y_col = columns, class_mode='raw', target_size=(218, 178), batch_size = 128, color_mode = 'rgb', shuffle = True) val_generator = datagen.flow_from_dataframe(val_df, folder, x_col = 'image_id', y_col = columns, target_size =(218, 178), class_mode = 'raw', batch_size = 128, color_mode = 'rgb', shuffle = True)

Found 154979 validated image filenames.
Found 17220 validated image filenames.

def create_model(): # Input dimensions of our image (checked above) x_input = Input(shape=(218, 178, 3)) # VGG16 network vgg = VGG16(weights='imagenet', include_top=False, input_shape=(218, 178, 3)) x = vgg(x_input) # The output of a VGG network is also 3 dimensional. We need to convert it to 1 dimension and then to 2 outputs x = Flatten()(x) #Converting to one dimension by concatenating everything x = Dense(512, activation='relu')(x) x = Dropout(0.2)(x) # Dropout randomly drops neurons in the network to prevent overfitting. This is kind of an arbitrary value x = Dense(128, activation='relu')(x) x = Dense(2, activation='sigmoid')(x) # Define our full model will inputs and outputs model = Model(inputs=x_input, outputs = x) # We will be using Adam, it is the most common optimizer. This also has hyperparameters, but we are ignoring it for now. # Binary Cross Entropy (log loss) is the metric we are optimizing. For our understanding, we are tracking accuracy and AUC (ignore this if you don't know it). Logloss is still the priority model.compile(optimizer = "Adam", loss='binary_crossentropy', metrics=['accuracy', "AUC"]) return model

model = create_model() model.summary() # Plot the architecture of the model

Downloading data from https://storage.googleapis.com/tensorflow/keras-applications/vgg16/vgg16_weights_tf_dim_ordering_tf_kernels_notop.h5
58892288/58889256 [==============================] - 1s 0us/step
Model: "model"
_________________________________________________________________
Layer (type)                 Output Shape              Param #   
=================================================================
input_1 (InputLayer)         [(None, 218, 178, 3)]     0         
_________________________________________________________________
vgg16 (Functional)           (None, 6, 5, 512)         14714688  
_________________________________________________________________
flatten (Flatten)            (None, 15360)             0         
_________________________________________________________________
dense (Dense)                (None, 512)               7864832   
_________________________________________________________________
dropout (Dropout)            (None, 512)               0         
_________________________________________________________________
dense_1 (Dense)              (None, 128)               65664     
_________________________________________________________________
dense_2 (Dense)              (None, 2)                 258       
=================================================================
Total params: 22,645,442
Trainable params: 22,645,442
Non-trainable params: 0
_________________________________________________________________

# Fitting the model on the data. # Epochs is the number of times the model goes through the entire dataset. # You should choose a higher value to give it more time to learn. But too high a value can lead to memorization rather than learning. history = model.fit(train_generator, epochs=5, validation_data = val_generator)

Epoch 1/5
1211/1211 [==============================] - 1165s 955ms/step - loss: 0.6880 - accuracy: 0.3079 - auc: 0.5083 - val_loss: 0.6691 - val_accuracy: 0.2231 - val_auc: 0.5387
Epoch 2/5
1211/1211 [==============================] - 832s 687ms/step - loss: 0.6684 - accuracy: 0.2396 - auc: 0.5149 - val_loss: 0.6702 - val_accuracy: 0.2231 - val_auc: 0.5114
Epoch 3/5
1211/1211 [==============================] - 826s 682ms/step - loss: 0.6682 - accuracy: 0.2290 - auc: 0.5157 - val_loss: 0.6702 - val_accuracy: 0.2231 - val_auc: 0.5114
Epoch 4/5
1211/1211 [==============================] - 834s 689ms/step - loss: 0.6684 - accuracy: 0.2283 - auc: 0.5139 - val_loss: 0.6705 - val_accuracy: 0.2231 - val_auc: 0.5114
Epoch 5/5
1211/1211 [==============================] - 832s 687ms/step - loss: 0.6690 - accuracy: 0.2293 - auc: 0.5146 - val_loss: 0.6703 - val_accuracy: 0.2231 - val_auc: 0.5114

plt.plot(history.history['loss']) plt.plot(history.history['val_loss']) plt.title('Model Loss') plt.ylabel('Loss') plt.xlabel('Epoch') plt.legend(['train', 'validation'], loc='upper left') plt.show()

plt.plot(history.history['accuracy']) plt.plot(history.history['val_accuracy']) plt.title('Model Accuracy') plt.ylabel('Accurcy') plt.xlabel('Epoch') plt.legend(['train', 'validation'], loc='upper left') plt.show()

sub = pd.read_csv("../input/face-attributes-ml-thon-2021/sampleSubmission.csv") sub

test_generator = datagen.flow_from_dataframe(sub, folder, x_col = 'image_id', y_col=None, batch_size=128, class_mode=None, target_size =(218, 178), shuffle=False, color_mode = 'rgb')

Found 30400 validated image filenames.

# Making predictions and storing it in a variable. preds = model.predict(test_generator)

# Adding predictions to the dataframe so that we can easily submit. sub[['Wearing_Accessories', 'Thick_Lips_Nose']] = preds sub

sub.to_csv("submission.csv", index=False)