for step in range(2001):
cost_val, hy_val, _ = sess.run(
[cost, hypothesis, train], feed_dict={X: x_data, Y: y_data})
if step % 10 == 0:
print(step, "Cost: ", cost_val, "\nPrediction:\n", hy_val)
# Ask my score
print("Your score will be ",
sess.run(hypothesis, feed_dict={X: [[100, 70, 101]]}))
print("Other scores will be ",
sess.run(hypothesis, feed_dict={X: [[60, 70, 110], [90, 100, 80]]}))
coldGraph(sess, 'lab_04_2_multi_variable_matmul_linear_regression', "X", "hypothesis", "save/Const:hypothesis" )
'''
0 Cost: 7105.46
Prediction:
[[ 80.82241058]
[ 92.26364136]
[ 93.70250702]
[ 98.09217834]
[ 72.51759338]]
10 Cost: 5.89726
Prediction:
[[ 155.35159302]
[ 181.85691833]
[ 181.97254944]
[ 194.21760559]
for i in range(len(train_y_o[:len(y_hat_train_o_list)])):
if train_y_o[i] != y_hat_train_o_list[i]:
file_train.write(img_list_train[i] + " Objectness Error. True: " +
str(train_y_o[i]) + " Prediction: " +
str(y_hat_train_o_list[i]) + " " +
str(y_hat_train_o_soft_list[i]) + "\n")
asd = img_list_train[i].split('.')[0] + "_" + str(
train_y_o[i]) + "_" + str(y_hat_train_o_list[i]) + "_" + str(
y_hat_train_o_soft_list[i]) + '.jpg'
shutil.copy(
os.path.join(path_list_train[i], img_list_train[i]),
os.path.join(
'/home/leehanbeen/PycharmProjects/TypeClassifier/SavedImage/Object',
asd))
coldGraph(sess, 'model', 'input', 'hypothesis', 'save/Const:hypothesis')
frozen = tf.graph_util.convert_variables_to_constants(
sess, sess.graph_def, ["hypothesis"]) #41번째 줄의 hypothesis 가 인자로 들어감.
graph_io.write_graph(
frozen, './', 'inference_graph_type.pb',
as_text=False) # 현재 디렉토리에 inference_graph_type.pb 파일 생성.
print("Test Confusion Matrix")
print(confusion_matrix(test_y[:len(y_hat_t_list)], y_hat_t_list))
print(confusion_matrix(test_y_o[:len(y_hat_o_list)], y_hat_o_list))
print("Test Type Accuracy: %.5f Test Object Accuracy: %.5f" %
(avg_acc_t, avg_acc_o))
print("\n\n")
print("Train Confusion Matrix")
print(
print('Learning Finished!')
# Test model and check accuracy
correct_prediction = tf.equal(tf.argmax(hypothesis, 1), tf.argmax(Y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32), name='accuracy')
print('Accuracy:', sess.run(accuracy, feed_dict={
X: mnist.test.images, Y: mnist.test.labels, keep_prob: 1}))
# Get one and predict
r = random.randint(0, mnist.test.num_examples - 1)
prediction = tf.argmax(hypothesis, 1, name='prediction')
print("Label: ", sess.run(tf.argmax(mnist.test.labels[r:r + 1], 1)))
print("Prediction: ", sess.run(prediction, feed_dict={X: mnist.test.images[r:r + 1], keep_prob: 1}))
coldGraph(sess, 'lab_10_5_mnist_nn_dropout', "X", "hypothesis, prediction, accuracy", "save/Const:hypothesis, save/Const:prediction, save/Const:accuracy" )
# plt.imshow(mnist.test.images[r:r + 1].
# reshape(28, 28), cmap='Greys', interpolation='nearest')
# plt.show()
'''
Epoch: 0001 cost = 0.447322626
Epoch: 0002 cost = 0.157285590
Epoch: 0003 cost = 0.121884535
Epoch: 0004 cost = 0.098128681
Epoch: 0005 cost = 0.082901778
Epoch: 0006 cost = 0.075337573
Epoch: 0007 cost = 0.069752543
Epoch: 0008 cost = 0.060884363
Epoch: 0009 cost = 0.055276413
for step in range(10001):
cost_val, _ = sess.run([cost, train], feed_dict={X: x_data, Y: y_data})
if step % 200 == 0:
print(step, cost_val)
# Accuracy report
h, c, a = sess.run([hypothesis, predicted, accuracy],
feed_dict={
X: x_data,
Y: y_data
})
print("\nHypothesis: ", h, "\nCorrect (Y): ", c, "\nAccuracy: ", a)
coldGraph(
sess, 'lab_05_1_logistic_regression', "X",
"hypothesis, predicted, accuracy",
"save/Const:hypothesis, save/Const:predicted, save/Const:accuracy")
'''
0 1.73078
200 0.571512
400 0.507414
600 0.471824
800 0.447585
...
9200 0.159066
9400 0.15656
9600 0.154132
9800 0.151778
10000 0.149496
Hypothesis: [[ 0.03074029]
print('Learning Finished!')
# Test model and check accuracy
correct_prediction = tf.equal(tf.argmax(hypothesis, 1), tf.argmax(Y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32), name='accuracy')
print('Accuracy:', sess.run(accuracy, feed_dict={
X: mnist.test.images, Y: mnist.test.labels}))
# Get one and predict
r = random.randint(0, mnist.test.num_examples - 1)
prediction = tf.argmax(hypothesis, 1, name='prediction')
print("Label: ", sess.run(tf.argmax(mnist.test.labels[r:r + 1], 1)))
print("Prediction: ", sess.run(prediction, feed_dict={X: mnist.test.images[r:r + 1]}))
coldGraph(sess, 'lab_10_3_mnist_nn_xavier', "X", "hypothesis, prediction, accuracy", "save/Const:hypothesis, save/Const:prediction, save/Const:accuracy" )
# plt.imshow(mnist.test.images[r:r + 1].
# reshape(28, 28), cmap='Greys', interpolation='nearest')
# plt.show()
'''
Epoch: 0001 cost = 0.301498963
Epoch: 0002 cost = 0.107252513
Epoch: 0003 cost = 0.064888892
Epoch: 0004 cost = 0.044463030
Epoch: 0005 cost = 0.029951642
Epoch: 0006 cost = 0.020663404
Epoch: 0007 cost = 0.015853033
Epoch: 0008 cost = 0.011764387
Epoch: 0009 cost = 0.008598264
sess.run(train, feed_dict={X: x_data, Y: y_data})
if step % 100 == 0:
print(step, sess.run(cost, feed_dict={
X: x_data,
Y: y_data
}), sess.run([W1, W2]))
# Accuracy report
h, c, a = sess.run([hypothesis, predicted, accuracy],
feed_dict={
X: x_data,
Y: y_data
})
print("\nHypothesis: ", h, "\nCorrect: ", c, "\nAccuracy: ", a)
coldGraph(
sess, 'lab_09_3_xor_nn_wide_deep', "X",
"hypothesis, prediction, accuracy",
"save/Const:hypothesis, save/Const:prediction, save/Const:accuracy")
'''
Hypothesis: [[ 7.80511764e-04]
[ 9.99238133e-01]
[ 9.98379230e-01]
[ 1.55659032e-03]]
Correct: [[ 0.]
[ 1.]
[ 1.]
[ 0.]]
Accuracy: 1.0
'''
print('Epoch:', '%04d' % (epoch + 1), 'cost =', '{:.9f}'.format(avg_cost))
print('Learning Finished!')
# Test model and check accuracy
correct_prediction = tf.equal(tf.argmax(hypothesis, 1), tf.argmax(Y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32), name='accuracy')
print('Accuracy:', sess.run(accuracy, feed_dict={X: mnist.test.images, Y: mnist.test.labels}))
# Get one and predict
r = random.randint(0, mnist.test.num_examples - 1)
prediction = tf.argmax(hypothesis, 1, name='prediction')
print("Label: ", sess.run(tf.argmax(mnist.test.labels[r:r + 1], 1)))
print("Prediction: ", sess.run( prediction, feed_dict={X: mnist.test.images[r:r + 1]}))
coldGraph(sess, 'lab_10_1_mnist_softmax', "X", "hypothesis, prediction, accuracy", "save/Const:hypothesis, save/Const:prediction, save/Const:accuracy" )
# plt.imshow(mnist.test.images[r:r + 1].
# reshape(28, 28), cmap='Greys', interpolation='nearest')
# plt.show()
'''
Epoch: 0001 cost = 5.888845987
Epoch: 0002 cost = 1.860620173
Epoch: 0003 cost = 1.159035648
Epoch: 0004 cost = 0.892340870
Epoch: 0005 cost = 0.751155428
Epoch: 0006 cost = 0.662484806
Epoch: 0007 cost = 0.601544010
Epoch: 0008 cost = 0.556526115
Epoch: 0009 cost = 0.521186961
for i in range(total_batch):
batch_xs, batch_ys = mnist.train.next_batch(batch_size)
c, _ = sess.run([cost, optimizer],
feed_dict={
X: batch_xs,
Y: batch_ys
})
avg_cost += c / total_batch
print('Epoch:', '%04d' % (epoch + 1), 'cost =',
'{:.9f}'.format(avg_cost))
print("Learning finished")
coldGraph(
sess, 'lab_07_4_mnist_introduction', "X",
"hypothesis,prediction,accuracy",
"save/Const:hypothesis,save/Const:prediction,save/Const:accuracy")
# Test the model using test sets
print(
"Accuracy: ",
accuracy.eval(session=sess,
feed_dict={
X: mnist.test.images,
Y: mnist.test.labels
}))
# Get one and predict
# r = random.randint(0, mnist.test.num_examples - 1)
r = 1
print("Label: ", sess.run(tf.argmax(mnist.test.labels[r:r + 1], 1)))
# Minimize: Gradient Descent using derivative: W -= learning_rate * derivative
learning_rate = 0.1
gradient = tf.reduce_mean((W * X - Y) * X)
descent = W - learning_rate * gradient
update = W.assign(descent)
# Launch the graph in a session.
sess = tf.Session()
# Initializes global variables in the graph.
sess.run(tf.global_variables_initializer())
for step in range(21):
sess.run(update, feed_dict={X: x_data, Y: y_data})
print(step, sess.run(cost, feed_dict={X: x_data, Y: y_data}), sess.run(W))
coldGraph(sess, 'lab_03_2_minimizing_cost_gradient_update', "X", "cost,hypothesis", "save/Const:cost, save/Const:hypothesis" )
'''
0 1.93919 [ 1.64462376]
1 0.551591 [ 1.34379935]
2 0.156897 [ 1.18335962]
3 0.0446285 [ 1.09779179]
4 0.0126943 [ 1.05215561]
5 0.00361082 [ 1.0278163]
6 0.00102708 [ 1.01483536]
7 0.000292144 [ 1.00791216]
8 8.30968e-05 [ 1.00421977]
9 2.36361e-05 [ 1.00225055]
10 6.72385e-06 [ 1.00120032]
11 1.91239e-06 [ 1.00064015]
}))
# Get one and predict
r = random.randint(0, mnist.test.num_examples - 1)
prediction = tf.argmax(logits, 1, name='prediction')
print("Label: ", sess.run(tf.argmax(mnist.test.labels[r:r + 1], 1)))
print(
"Prediction: ",
sess.run(prediction,
feed_dict={
X: mnist.test.images[r:r + 1],
keep_prob: 1
}))
coldGraph(sess, 'lab_11_2_mnist_deep_cnn', "X",
"hypothesis, prediction, accuracy",
"save/Const:hypothesis, save/Const:prediction, save/Const:accuracy")
# plt.imshow(mnist.test.images[r:r + 1].
# reshape(28, 28), cmap='Greys', interpolation='nearest')
# plt.show()
'''
Learning stared. It takes sometime.
Epoch: 0001 cost = 0.385748474
Epoch: 0002 cost = 0.092017397
Epoch: 0003 cost = 0.065854684
Epoch: 0004 cost = 0.055604566
Epoch: 0005 cost = 0.045996377
Epoch: 0006 cost = 0.040913645
Epoch: 0007 cost = 0.036924479
Epoch: 0008 cost = 0.032808939
for step in range(201):
cost_val, W_val, _ = sess.run([cost, W, optimizer],
feed_dict={
X: x_data,
Y: y_data
})
print(step, cost_val, W_val)
# predict
print("Prediction:", sess.run(prediction, feed_dict={X: x_test}))
# Calculate the accuracy
print("Accuracy: ", sess.run(accuracy, feed_dict={X: x_test, Y: y_test}))
coldGraph(
sess, 'lab_07_1_learning_rate_and_evaluation', "X",
"hypothesis, prediction, accuracy",
"save/Const:hypothesis, save/Const:prediction, save/Const:accuracy")
'''
when lr = 1.5
0 5.73203 [[-0.30548954 1.22985029 -0.66033536]
[-4.39069986 2.29670858 2.99386835]
[-3.34510708 2.09743214 -0.80419564]]
1 23.1494 [[ 0.06951046 0.29449689 -0.0999819 ]
[-1.95319986 -1.63627958 4.48935604]
[-0.90760708 -1.65020132 0.50593793]]
2 27.2798 [[ 0.44451016 0.85699677 -1.03748143]
[ 0.48429942 0.98872018 -0.57314301]
[ 1.52989244 1.16229868 -4.74406147]]
3 8.668 [[ 0.12396193 0.61504567 -0.47498202]
[ 0.22003263 -0.2470119 0.9268558 ]
[ 0.96035379 0.41933775 -3.43156195]]
loss = tf.reduce_sum(tf.square(hypothesis - y),
name='loss') # sum of the squares
# optimizer
optimizer = tf.train.GradientDescentOptimizer(0.01)
train = optimizer.minimize(loss, name='train')
# training data
x_train = [1, 2, 3, 4]
y_train = [0, -1, -2, -3]
# training loop
init = tf.global_variables_initializer()
sess = tf.Session()
sess.run(init) # reset values to wrong
for i in range(1000):
# sess.run(train, {x: x_train, y: y_train})
feed_dict = {x: x_train, y: y_train}
sess.run([train], feed_dict=feed_dict)
# evaluate training accuracy
curr_W, curr_b, curr_loss = sess.run([W, b, loss], {x: x_train, y: y_train})
print("W: %s b: %s loss: %s" % (curr_W, curr_b, curr_loss))
curr_loss, curr_hypo = sess.run([loss, hypothesis], {x: 3, y: 3})
print("loss: %s, hypothesis: %s " % (curr_loss, curr_hypo))
coldGraph(sess, 'lab_02_3_linear_regression', "x", "hypothesis",
"save/Const:hypothesis")
print('--------------')
b = sess.run(hypothesis, feed_dict={X: [[1, 3, 4, 3]]})
print(b, sess.run(tf.argmax(b, 1)))
print('--------------')
c = sess.run(hypothesis, feed_dict={X: [[1, 1, 0, 1]]})
print(c, sess.run(tf.argmax(c, 1)))
print('--------------')
all = sess.run(hypothesis,
feed_dict={X: [[1, 11, 7, 9], [1, 3, 4, 3], [1, 1, 0, 1]]})
print(all, sess.run(tf.argmax(all, 1)))
coldGraph(sess, 'lab_06_1_softmax_classifier', "X",
"hypothesis, ud_argmax",
"save/Const:hypothesis, save/Const:ud_argmax")
'''
--------------
[[ 1.38904958e-03 9.98601854e-01 9.06129117e-06]] [1]
--------------
[[ 0.93119204 0.06290206 0.0059059 ]] [0]
--------------
[[ 1.27327668e-08 3.34112905e-04 9.99665856e-01]] [2]
--------------
[[ 1.38904958e-03 9.98601854e-01 9.06129117e-06]
[ 9.31192040e-01 6.29020557e-02 5.90589503e-03]
[ 1.27327668e-08 3.34112905e-04 9.99665856e-01]] [1 0 2]
'''
