dipanjanS

base_df = spark.read.text(raw_data_files)
base_df.printSchema()

dipanjanS

import glob

raw_data_files = glob.glob('*.gz')
raw_data_files

dipanjanS

m = re.finditer(r'.*?(spark).*?', "I'm searching for a spark in PySpark", re.I)
for match in m:
    print(match, match.start(), match.end())

dipanjanS

# configure spark variables
from pyspark.context import SparkContext
from pyspark.sql.context import SQLContext
from pyspark.sql.session import SparkSession
    
sc = SparkContext()
sqlContext = SQLContext(sc)
spark = SparkSession(sc)

# load up other dependencies

dipanjanS

import model_evaluation_utils as meu
import pandas as pd

basic_cnn_metrics = meu.get_metrics(true_labels=test_labels, predicted_labels=basic_cnn_pred_labels)
vgg_frz_metrics = meu.get_metrics(true_labels=test_labels, predicted_labels=vgg_frz_pred_labels)
vgg_ft_metrics = meu.get_metrics(true_labels=test_labels, predicted_labels=vgg_ft_pred_labels)

pd.DataFrame([basic_cnn_metrics, vgg_frz_metrics, vgg_ft_metrics], 
             index=['Basic CNN', 'VGG-19 Frozen', 'VGG-19 Fine-tuned'])

dipanjanS

# Load Saved Deep Learning Models
basic_cnn = tf.keras.models.load_model('./basic_cnn.h5')
vgg_frz = tf.keras.models.load_model('./vgg_frozen.h5')
vgg_ft = tf.keras.models.load_model('./vgg_finetuned.h5')

# Make Predictions on Test Data
basic_cnn_preds = basic_cnn.predict(test_imgs_scaled, batch_size=512)
vgg_frz_preds = vgg_frz.predict(test_imgs_scaled, batch_size=512)
vgg_ft_preds = vgg_ft.predict(test_imgs_scaled, batch_size=512)

dipanjanS

test_imgs_scaled = test_data / 255.
test_imgs_scaled.shape, test_labels.shape

# Output
((8268, 125, 125, 3), (8268,))

dipanjanS

tensorboard_callback = tf.keras.callbacks.TensorBoard(logdir, histogram_freq=1)
reduce_lr = tf.keras.callbacks.ReduceLROnPlateau(monitor='val_loss', factor=0.5,
                              patience=2, min_lr=0.000001)

callbacks = [reduce_lr, tensorboard_callback]
train_steps_per_epoch = train_generator.n // train_generator.batch_size
val_steps_per_epoch = val_generator.n // val_generator.batch_size
history = model.fit_generator(train_generator, steps_per_epoch=train_steps_per_epoch, epochs=EPOCHS,
                              validation_data=val_generator, validation_steps=val_steps_per_epoch, 
                              verbose=1)

dipanjanS

vgg = tf.keras.applications.vgg19.VGG19(include_top=False, weights='imagenet', 
                                        input_shape=INPUT_SHAPE)
# Freeze the layers
vgg.trainable = True

set_trainable = False
for layer in vgg.layers:
    if layer.name in ['block5_conv1', 'block4_conv1']:
        set_trainable = True
    if set_trainable:

dipanjanS

img_id = 0
sample_generator = train_datagen.flow(train_data[img_id:img_id+1], train_labels[img_id:img_id+1],
                                      batch_size=1)
sample = [next(sample_generator) for i in range(0,5)]
fig, ax = plt.subplots(1,5, figsize=(16, 6))
print('Labels:', [item[1][0] for item in sample])
l = [ax[i].imshow(sample[i][0][0]) for i in range(0,5)]