sadanalog

# set temporary IP
ip a
sudo ip addr add <ipv4_addr>/<netmask> dev <interface>
sudo ip route add default via <gateway_ip>

# set temporary DNS
sudo nano /etc/resolv.conf
# nameserver 8.8.8.8

# set permanent IP

sadanalog

# Clear variable
cnn_model = None
# Call a create model function
cnn_model = create_model(image_shape=(256, 4096, 1))
# Declare the a callback function
# Early stopping callback
earlystopping = EarlyStopping(monitor='val_accuracy', patience=2)
# ModelCheckpoin callabck
filepath = project_path + "/model/weights_best.hdf5"
checkpoint = ModelCheckpoint(filepath, monitor='val_accuracy', verbose=1, save_best_only=True, mode='max')

sadanalog

# set number of split
kfold_splits = 4
# set number of epoch
n_epoch = 10
# set batch size
batch_size = 10
 
# create StratifiedKFold
skf = StratifiedKFold(n_splits=kfold_splits, shuffle=True)
for index, (train_indices, val_indices) in enumerate(skf.split(X, y)):

sadanalog

from tensorflow.keras import datasets, layers, models, optimizers, regularizers, callbacks
from tensorflow.keras.callbacks import EarlyStopping, ModelCheckpoint

def create_model(image_shape=(256, 4096, 1), print_summary=False):
    # initial model
    model = models.Sequential()

    # CONV layer: filter 16, stride 7x7
    model.add(layers.Conv2D(16, (7, 7),input_shape=image_shape))
    # Batch Normalization layer -> avoid overfitting

sadanalog

# We random by shuffling the order of defect-free and defect images
np.random.shuffle(non_defect_images)
np.random.shuffle(defect_images)
# The class size is the min length compared with defect-free and defect images
class_size = defect_images.shape[0] if defect_images.shape[0] <= non_defect_images.shape[0] else non_defect_images.shape[0]
# Declare dataset by concat defect_images and non_defect_images with length 0 to class_size
dataset = np.concatenate((defect_images[:class_size], non_defect_images[:class_size]))
# Create an empty matrix X with is matrix of 256x4096 and has dataset length row
X = np.empty([dataset.shape[0], 256, 4096]).astype(int)
# Create vector y which has dataset length

sadanalog

defect_images_path = project_path + "/dataset/Defect_images"
non_defect_images_path1 =  project_path + "/dataset/NoDefect_images/2306881-210020u"
non_defect_images_path2 =  project_path + "/dataset/NoDefect_images/2306894-210033u"
non_defect_images_path3 =  project_path + "/dataset/NoDefect_images/2311517-195063u"
non_defect_images_path4 =  project_path + "/dataset/NoDefect_images/2311694-1930c7u"
non_defect_images_path5 =  project_path + "/dataset/NoDefect_images/2311694-2040n7u"
non_defect_images_path6 =  project_path + "/dataset/NoDefect_images/2311980-185026u"
non_defect_images_path7 =  project_path + "/dataset/NoDefect_images/2608691-202020u"
mask_images_path =  project_path + "/dataset/Mask_images"

sadanalog

def load_file(file_path, label):
    # declare the folder name
    folder_name = file_path.split("/")[-1]
    # declare output list
    out_list = []
    # load every file that .png format
    for image_path in glob.glob(file_path + "/*.png"):
        # read image file
        image = imageio.imread(image_path)
        # declare temporary dict dtype

sadanalog

(still a work-in-progress)

Shortlinks:

• Cluster Health
  • Index Level
  • Shard Level
• Nodes Overview
• Indices Overview
• Cluster Maintenance

sadanalog

# -*- coding: utf-8 -*-
"""
This script will delete all of the tweets in the specified account.
You may need to hit the "more" button on the bottom of your twitter profile
page every now and then as the script runs, this is due to a bug in twitter.

You will need to get a consumer key and consumer secret token to use this
script, you can do so by registering a twitter application at https://dev.twitter.com/apps

@requirements: Python 2.5+, Tweepy (http://pypi.python.org/pypi/tweepy/1.7.1)