leechanwoo

import tensorflow as tf
import matplotlib.pyplot as plt
import os
%matplotlib inline

tf.reset_default_graph()
images = "dataset/test_dataset_png/"
image_dir = os.path.join(os.getcwd(), images)
imagenames = [os.path.join(image_dir, f) for f in os.listdir(image_dir)]

leechanwoo

import tensorflow as tf
import matplotlib.pyplot as plt
import os
%matplotlib inline

tf.reset_default_graph()
images = "dataset/test_dataset_png/"
image_dir = os.path.join(os.getcwd(), images)
imagenames = [os.path.join(image_dir, f) for f in os.listdir(image_dir)]

leechanwoo

import tensorflow as tf

def input_fn():
    up = [i for i in range(10)]
    down = [9-i for i in range(10)]
    features = tf.constant([up if i%2 == 0 else down for i in range(1000)], tf.float32)
    label = tf.constant([[1] if i%2 == 0 else [0] for i in range(1000)], tf.float32)
    return features, label

def model(features, labels, mode):

leechanwoo

def input_fn():
    up = [i for i in range(10)]
    down = [9-i for i in range(10)]
    features = tf.constant([up if i%2 == 0 else down for i in range(1000)], tf.float32)
    label = tf.constant([[1] if i%2 == 0 else [0] for i in range(1000)], tf.float32)
    return features, label

leechanwoo

def model(features, labels, mode):
    layer1 = tf.layers.dense(features, 10)
    layer2 = tf.layers.dense(layer1, 10)
    layer3 = tf.layers.dense(layer2, 10)
    layer4 = tf.layers.dense(layer3, 10)
    out = tf.layers.dense(layer4, 1)

    global_step = tf.train.get_global_step()
    loss = tf.losses.sigmoid_cross_entropy(labels, out)
    train_op = tf.train.GradientDescentOptimizer(0.01).minimize(loss, global_step)

leechanwoo

est = tf.estimator.Estimator(model)
est.train(input_fn, steps=5)

leechanwoo

import tensorflow as tf
import matplotlib.pyplot as plt
import numpy as np
%matplotlib inline
tf.reset_default_graph()


sample = 1000
x = np.array([0.01*float(i) for i in range(sample+1)], np.float32)
y = np.sin(x)

leechanwoo

import tensorflow as tf
import matplotlib.pyplot as plt
import numpy as np
%matplotlib inline

tf.reset_default_graph()

# hyper parameters 
samples = 1000
time_step = 100

leechanwoo

import tensorflow as tf
import numpy as np
import os
import matplotlib.pyplot as plt
%matplotlib inline

file_dir = os.path.join(os.getcwd(), "dataset/test_dataset_png")
image_paths = [os.path.join(file_dir, i) for i in os.listdir(file_dir)]

leechanwoo

def gen_dataset():
    up = [i for i in range(10)]
    down = [9-i for i in range(10)]

    with open("./test.csv", 'w') as f:
        writer = csv.writer(f, delimiter=",")
        for i in range(5):
            writer.writerow([1] + up)
            writer.writerow([0] + down)