nitin-bommi

# training the model
history = model.fit(train_generator,
                    steps_per_epoch = 1000,  # len(train) / BS
                    epochs = 100,
                    validation_data = validation_generator,
                    validation_steps = 500,  # len(test) / BS
                    verbose = 2
)

# visualising the loss and accuracy

nitin-bommi

class myCallBack(tf.keras.callbacks.Callback):
    def on_epoch_end(self, epoch, logs={}):
        if(logs['accuracy']>0.99):
            print("\n\nAccuracy greater than 99%. Stopping the training")
            self.model.stop_training = True

callbacks = myCallBack()

nitin-bommi

model = tf.keras.models.Sequential([
                  tf.keras.layers.Conv2D(32, (3,3), activation='relu', input_shape=(150, 150, 3)),
                  tf.keras.layers.MaxPooling2D(2, 2),
                  tf.keras.layers.Conv2D(64, (3,3), activation='relu'),
                  tf.keras.layers.MaxPooling2D(2,2),
                  tf.keras.layers.Conv2D(128, (3,3), activation='relu'),
                  tf.keras.layers.MaxPooling2D(2,2),
                  tf.keras.layers.Conv2D(128, (3,3), activation='relu'),
                  tf.keras.layers.MaxPooling2D(2,2),
                  tf.keras.layers.Flatten(),

nitin-bommi

# importing the library
import tensorflow as tf

# generating new images
train_datagen = tf.keras.preprocessing.image.ImageDataGenerator(rescale = 1./255,
                                                                rotation_range = 60,
                                                                width_shift_range = 0.2,
                                                                height_shift_range = 0.2,
                                                                shear_range = 0.2,
                                                                zoom_range = 0.2,

nitin-bommi

# To compute the ROC curve and the area under the curve.
from sklearn.metrics import roc_curve, roc_auc_score

false_positive_rate, true_positive_rate, thresholds = roc_curve(y_train_2, y_scores)

def plot_roc_curve(fpr, tpr, label=None):
    plt.plot(fpr, tpr, linewidth=2, label=label)
    plt.plot([0,1], [0,1], 'k--')
    plt.axis([0,1,0,1])
    plt.xlabel("False Positive Rate", fontsize=16)

nitin-bommi

# To compute the F1 score, simply call the f1_score() function:
from sklearn.metrics import f1_score
f1_score(y_train_5, y_train_pred)

nitin-bommi

# Finding precision and recall
from sklearn.metrics import precision_score, recall_score
precision_score(y_train_5, y_train_pred)
recall_score(y_train_5, y_train_pred)

nitin-bommi

# Creating some predictions.
from sklearn.model_selection import cross_val_predict
y_train_pred = cross_val_predict(sgd_clf, X_train, y_train_5, cv=3)

"""
You could make predictions on the test set, but use the test set only at the very end of your project, once you have a classifier that you are ready to launch.
"""

# Constructing the confusion matrix.
from sklearn.metrics import confusion_matrix

nitin-bommi

# Importing the dataset.
from sklearn.datasets import fetch_openml
mnist = fetch_openml('mnist_784', version=1)

# Creating independent and dependent variables.
X, y = mnist['data'], mnist['target']

# Splitting the data into training set and test set.
X_train, X_test, y_train, y_test = X[:60000], X[60000:], y[:60000], y[60000:]