I am trying to see how tf.metrics.accuracy works. I want to compare batch accuracy results of the function given below
with tf.name_scope('Accuracy1'):
correct_prediction = tf.equal(tf.argmax(predictions, 1), tf.argmax(y, 1))
accuracy1 = tf.reduce_mean(tf.cast(correct_prediction, tf.float32), name="accuracy")
with
with tf.name_scope('Accuracy2'):
accuracy2, accuracy_op = tf.metrics.accuracy(labels=tf.argmax(y, 1), predictions=tf.argmax(predictions, 1))
Minimal working example is provided below:
import numpy as np
import pandas as pd
import tensorflow as tf
import math
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
num_steps=28
num_inputs = 28
num_classes = 10
num_neurons = 128
num_layers = 3
batch_size = 500
graph = tf.Graph()
with graph.as_default():
with tf.name_scope("graph_inputs"):
X = tf.placeholder(tf.float32, [None, num_steps, num_inputs], name='input_placeholder')
y = tf.placeholder(tf.float32, [None, num_classes], name='labels_placeholder')
output_keep_prob = tf.placeholder_with_default(1.0, shape=(), name ="output_dropout")
def build_lstm_cell(num_neurons, output_keep_prob):
"""Returns a dropout-wrapped LSTM-cell.
See https://stackoverflow.com/a/44882273/2628369 for why this local function is necessary.
Returns:
tf.contrib.rnn.DropoutWrapper: The dropout-wrapped LSTM cell.
"""
initializer = tf.contrib.layers.xavier_initializer()
lstm_cell = tf.contrib.rnn.LSTMCell(num_units=num_neurons, initializer=initializer, forget_bias=1.0, state_is_tuple=True, name='LSTM_cell')
lstm_cell_drop = tf.contrib.rnn.DropoutWrapper(lstm_cell, output_keep_prob=output_keep_prob)
return lstm_cell_drop
with tf.name_scope("LSTM"):
with tf.name_scope("Cell"):
multi_layer_cell = tf.contrib.rnn.MultiRNNCell([build_lstm_cell(num_neurons, output_keep_prob) for _ in range(num_layers)], state_is_tuple=True)
with tf.name_scope("Model"):
outputs, states = tf.nn.dynamic_rnn(cell=multi_layer_cell, inputs=X, swap_memory=False, time_major = False, dtype=tf.float32)#[Batch_size, time_steps, num_neurons]
with tf.name_scope("Graph_Outputs"):
outputs = tf.transpose(outputs, [1, 0, 2]) # [num_timesteps, batch_size, num_neurons]
outputs = tf.gather(outputs, int(outputs.get_shape()[0]) - 1) # [batch_size, num_neurons]
with tf.variable_scope('Softmax'):
logits = tf.layers.dense(inputs = outputs, units = num_classes, name="logits") #[Batch_size, num_classes]
with tf.name_scope('Predictions'):
predictions = tf.nn.softmax(logits, name="predictions") #[Batch_size, num_classes]
with tf.name_scope('Accuracy1'):
correct_prediction = tf.equal(tf.argmax(predictions, 1), tf.argmax(y, 1))
accuracy1 = tf.reduce_mean(tf.cast(correct_prediction, tf.float32), name="accuracy")
with tf.name_scope('Accuracy2'):
accuracy2, accuracy_op = tf.metrics.accuracy(labels=tf.argmax(y, 1), predictions=tf.argmax(predictions, 1))
with tf.name_scope('Loss'):
xentropy = tf.nn.softmax_cross_entropy_with_logits_v2(logits=logits, labels=y)
loss = tf.reduce_mean(xentropy, name="loss")
with tf.name_scope('Train'):
optimizer= tf.train.AdamOptimizer(learning_rate=0.0001)
trainer=optimizer.minimize(loss, name="training_op")
with tf.Session(graph = graph) as sess:
tf.global_variables_initializer().run()
total_batch = mnist.train.num_examples // batch_size
for batch in range(total_batch):
tf.local_variables_initializer().run()
xBatch, yBatch = mnist.train.next_batch(batch_size)
xBatch = xBatch.reshape((batch_size, num_steps, num_inputs))
sess.run(trainer, feed_dict={X: xBatch, y: yBatch, output_keep_prob: 0.5})
miniBatchAccuracy1 = sess.run(accuracy1, feed_dict={X: xBatch, y: yBatch, output_keep_prob: 0.5})
print('[hand-written] Batch {} accuracy: {}'.format(batch, miniBatchAccuracy1))
accuracy_op_val = sess.run(accuracy_op, feed_dict={X: xBatch, y: yBatch, output_keep_prob: 0.5})
miniBatchAccuracy2 = sess.run(accuracy2)
print("[tf.metrics.accuracy] Batch {} accuracy: {}".format(batch, miniBatchAccuracy2))
sess.close()
I print the accuracy values of each batches using these two approaches and they are different. Should not the results be the same?
[hand-written] Batch 0 accuracy: 0.09600000083446503
[tf.metrics.accuracy] Batch 0 accuracy: 0.09399999678134918
[hand-written] Batch 1 accuracy: 0.1120000034570694
[tf.metrics.accuracy] Batch 1 accuracy: 0.07800000160932541
[hand-written] Batch 2 accuracy: 0.10199999809265137
[tf.metrics.accuracy] Batch 2 accuracy: 0.09600000083446503
[hand-written] Batch 3 accuracy: 0.12999999523162842
[tf.metrics.accuracy] Batch 3 accuracy: 0.12800000607967377
[hand-written] Batch 4 accuracy: 0.1379999965429306
[tf.metrics.accuracy] Batch 4 accuracy: 0.10199999809265137
[hand-written] Batch 5 accuracy: 0.16200000047683716
[tf.metrics.accuracy] Batch 5 accuracy: 0.1340000033378601
[hand-written] Batch 6 accuracy: 0.1340000033378601
[tf.metrics.accuracy] Batch 6 accuracy: 0.12600000202655792
[hand-written] Batch 7 accuracy: 0.12999999523162842
[tf.metrics.accuracy] Batch 7 accuracy: 0.16200000047683716
...
...
...
...
When measuring the accuracy for both cases, you are passing the dropout rate as 0.5. This is the reason its giving two different values. Set the dropout value at 1.0 and you should see similar values for both cases.
Related
I trained this model to classify the images in the dataset fashion-mnist. When the weights have not been trained the loss value seems normal, but after the first epoch, the loss reduces to 0, and all the input images are classified into class 0.
If regularization added, the weights update slower, but eventually get the same result, say all the images classified to class 0 with a loss value of 0.
import tensorflow as tf
from tensorflow import keras
import numpy as np
EPOCH = 10
BATCH_SIZE = 30
DATA_SIZE = 60000
REGULARIZER = 0.001
def main():
fashion_mnist = keras.datasets.fashion_mnist
(train_images, train_labels), (test_images, test_labels) = fashion_mnist.load_data()
train_images = train_images / 255.0
test_images = test_images / 255.0
train_labels = train_labels.reshape((60000, 1))
train_images = train_images.reshape((60000, 784))
test_images = test_images.reshape((10000, 784))
judge_labels = test_labels.reshape((10000, 1))
x = tf.placeholder(tf.float32, (None, 784))
y_ = tf.placeholder(tf.float32, (None, 1))
w1 = tf.Variable(np.random.rand(784 * 24).reshape([784, 24]) * 10, dtype=tf.float32)
# tf.add_to_collection('losses', tf.contrib.layers.l2_regularizer(REGULARIZER)(w1))
w2 = tf.Variable(np.random.rand(24 * 24).reshape([24, 24]) * 10, dtype=tf.float32)
# tf.add_to_collection('losses', tf.contrib.layers.l2_regularizer(REGULARIZER)(w2))
w3 = tf.Variable(np.random.rand(24 * 10).reshape([24, 10]) * 10, dtype=tf.float32)
# tf.add_to_collection('losses', tf.contrib.layers.l2_regularizer(REGULARIZER)(w3))
bias1 = tf.constant(1, shape=(24,), dtype=tf.float32)
bias2 = tf.constant(1, shape=(24,), dtype=tf.float32)
y1 = tf.nn.relu(tf.matmul(x, w1) + bias1)
y2 = tf.nn.relu(tf.matmul(y1, w2) + bias2)
y = tf.matmul(y2, w3)
predict = tf.argmax(y, axis=1)
y_spy = tf.nn.softmax(y, axis=1)
ce = tf.nn.sparse_softmax_cross_entropy_with_logits(labels=tf.argmax(y_, 1), logits=y)
# loss = tf.reduce_mean(ce) + tf.add_n(tf.get_collection('losses'))
loss = tf.reduce_mean(ce)
train_step = tf.train.GradientDescentOptimizer(0.001).minimize(loss)
with tf.Session() as sess:
init_op = tf.global_variables_initializer()
sess.run(init_op)
print('current out loss: ', end='')
print(sess.run(loss, feed_dict={x: test_images, y_: judge_labels}))
pre = sess.run(predict, feed_dict={x: test_images})
miss = pre - test_labels
print('right number: ', end='')
print((np.sum(miss == 0)))
for epoch in range(EPOCH):
for i in range(DATA_SIZE // BATCH_SIZE):
start = i * BATCH_SIZE
end = (i + 1) * BATCH_SIZE
_ = sess.run([train_step], feed_dict={x: train_images[start:end],
y_: train_labels[start:end]})
print('epochs %d :' % epoch)
print('current in loss: ', end='')
print(sess.run(loss, feed_dict={x: train_images[start:end],
y_: train_labels[start:end]}))
print('current out loss: ', end='')
print(sess.run(loss, feed_dict={x: test_images, y_: judge_labels}))
miss = sess.run(predict, feed_dict={x: test_images}) - test_labels
print('right number: ', end='')
print((np.sum(miss == 0)))
if __name__ == "__main__":
main()
Mistake 1: Loss function should be
ce = tf.nn.sparse_softmax_cross_entropy_with_logits(labels=tf.reshape(y_, [-1]), logits=y)
because labels are flat values for this loss function. (change y placeholder to int32 type)
Mistake 2: The weight are initialled to very large values.
GradientDescentOptimizer is very slow optimizer. Use AdamOptimizer instead
Fixed code:
import tensorflow as tf
from tensorflow import keras
import numpy as np
EPOCH = 10
BATCH_SIZE = 64
DATA_SIZE = 60000
REGULARIZER = 0.001
def main():
fashion_mnist = keras.datasets.fashion_mnist
(train_images, train_labels), (test_images, test_labels) = fashion_mnist.load_data()
train_images = train_images / 255.0
test_images = test_images / 255.0
train_labels = train_labels.reshape((60000, 1))
train_images = train_images.reshape((60000, 784))
test_images = test_images.reshape((10000, 784))
judge_labels = test_labels.reshape((10000, 1))
x = tf.placeholder(tf.float32, (None, 784))
y_ = tf.placeholder(tf.int32, (None, 1))
w1 = tf.Variable(np.random.rand(784 * 24).reshape([784, 24]), dtype=tf.float32)
# tf.add_to_collection('losses', tf.contrib.layers.l2_regularizer(REGULARIZER)(w1))
w2 = tf.Variable(np.random.rand(24 * 24).reshape([24, 24]), dtype=tf.float32)
# tf.add_to_collection('losses', tf.contrib.layers.l2_regularizer(REGULARIZER)(w2))
w3 = tf.Variable(np.random.rand(24 * 10).reshape([24, 10]), dtype=tf.float32)
# tf.add_to_collection('losses', tf.contrib.layers.l2_regularizer(REGULARIZER)(w3))
bias1 = tf.constant(1, shape=(24,), dtype=tf.float32)
bias2 = tf.constant(1, shape=(24,), dtype=tf.float32)
y1 = tf.nn.relu(tf.matmul(x, w1) + bias1)
y2 = tf.nn.relu(tf.matmul(y1, w2) + bias2)
y = tf.matmul(y2, w3)
predict = tf.argmax(y, axis=1)
y_spy = tf.nn.softmax(y, axis=1)
ce = tf.nn.sparse_softmax_cross_entropy_with_logits(labels=tf.reshape(y_, [-1]), logits=y)
# loss = tf.reduce_mean(ce) + tf.add_n(tf.get_collection('losses'))
loss = tf.reduce_mean(ce)
train_step = tf.train.AdamOptimizer(0.001).minimize(loss)
with tf.Session() as sess:
init_op = tf.global_variables_initializer()
sess.run(init_op)
print('current out loss: ', end='')
print(sess.run(loss, feed_dict={x: test_images, y_: judge_labels}))
pre = sess.run(predict, feed_dict={x: test_images})
miss = pre - test_labels
print('right number: ', end='')
print((np.sum(miss == 0)))
for epoch in range(EPOCH):
for i in range(DATA_SIZE // BATCH_SIZE):
start = i * BATCH_SIZE
end = (i + 1) * BATCH_SIZE
_ = sess.run([train_step], feed_dict={x: train_images[start:end],
y_: train_labels[start:end]})
print('epochs %d :' % epoch)
print('current in loss: ', end='')
print(sess.run(loss, feed_dict={x: train_images[start:end],
y_: train_labels[start:end]}))
print('current out loss: ', end='')
print(sess.run(loss, feed_dict={x: test_images, y_: judge_labels}))
miss = sess.run(predict, feed_dict={x: test_images}) - test_labels
print('right number: ', end='')
print((np.sum(miss == 0)))
miss = sess.run(predict, feed_dict={x: test_images})
print (miss[0:10], test_labels[0:10])
if __name__ == "__main__":
main()
Output (selective):
...
Sample predictions: [9 2 4 3 2 4 4 4 7 7], Actual: [9 2 1 1 6 1 4 6 5 7]
...
Sample predictions: [9 2 1 1 6 1 4 6 1 7], Actual: [9 2 1 1 6 1 4 6 5 7]
...
Sample predictions: [7 2 1 1 6 1 4 6 1 7], Actual: [9 2 1 1 6 1 4 6 5 7]
...
Sample predictions: [9 2 1 1 6 1 4 6 1 7], Actual: [9 2 1 1 6 1 4 6 5 7]
...
Code with train, validation loss and train, validation accuracy and shuffling train data for each epoch
import tensorflow as tf
from tensorflow import keras
import numpy as np
from sklearn.metrics import classification_report, accuracy_score
EPOCH = 30
BATCH_SIZE = 64
DATA_SIZE = 60000
REGULARIZER = 0.001
def main():
fashion_mnist = keras.datasets.fashion_mnist
(train_images, train_labels), (test_images, test_labels) = fashion_mnist.load_data()
train_images = train_images / 255.0
test_images = test_images / 255.0
train_labels = train_labels.reshape((60000, 1))
train_images = train_images.reshape((60000, 784))
test_images = test_images.reshape((10000, 784))
judge_labels = test_labels.reshape((10000, 1))
x = tf.placeholder(tf.float32, (None, 784))
y_ = tf.placeholder(tf.int32, (None, 1))
w1 = tf.Variable(np.random.rand(784 * 24).reshape([784, 24]), dtype=tf.float32)
tf.add_to_collection('losses', tf.contrib.layers.l2_regularizer(REGULARIZER)(w1))
w2 = tf.Variable(np.random.rand(24 * 24).reshape([24, 24]), dtype=tf.float32)
tf.add_to_collection('losses', tf.contrib.layers.l2_regularizer(REGULARIZER)(w2))
w3 = tf.Variable(np.random.rand(24 * 10).reshape([24, 10]), dtype=tf.float32)
tf.add_to_collection('losses', tf.contrib.layers.l2_regularizer(REGULARIZER)(w3))
bias1 = tf.constant(1, shape=(24,), dtype=tf.float32)
bias2 = tf.constant(1, shape=(24,), dtype=tf.float32)
y1 = tf.nn.relu(tf.matmul(x, w1) + bias1)
y2 = tf.nn.relu(tf.matmul(y1, w2) + bias2)
y = tf.matmul(y2, w3)
predict = tf.argmax(y, axis=1)
ce = tf.nn.sparse_softmax_cross_entropy_with_logits(labels=tf.reshape(y_, [-1]), logits=y)
loss = tf.reduce_mean(ce)
train_step = tf.train.AdamOptimizer(0.001).minimize(loss)
with tf.Session() as sess:
init_op = tf.global_variables_initializer()
sess.run(init_op)
idx = np.arange(DATA_SIZE)
for epoch in range(EPOCH):
train_loss = list()
train_predict = list()
np.random.shuffle(idx)
train_images = train_images[idx]
train_labels = train_labels[idx]
for i in range(DATA_SIZE // BATCH_SIZE):
start = i * BATCH_SIZE
end = (i + 1) * BATCH_SIZE
_, loss_, p_ = sess.run([train_step, loss, predict], feed_dict={x: train_images[start:end],
y_: train_labels[start:end]})
train_loss.append(loss_)
train_predict.extend(p_)
test_loss, test_predict = sess.run([loss, predict], feed_dict={x: test_images,
y_: judge_labels})
print ("Epoch: {}, Train Loss: {:.3f}, Test Loss: {:.3f},"\
"Train Acc: {:.3f}, Test Acc: {:.3f}".format(
epoch+1, np.mean(train_loss), test_loss,
accuracy_score(train_labels[0:len(train_predict)], train_predict),
accuracy_score(judge_labels, test_predict)))
if __name__ == "__main__":
main()
Output:
....
Epoch: 27, Train Loss: 0.842, Test Loss: 1.015,Train Acc: 0.816, Test Acc: 0.798
Epoch: 28, Train Loss: 0.832, Test Loss: 0.880,Train Acc: 0.816, Test Acc: 0.806
Epoch: 29, Train Loss: 0.788, Test Loss: 0.886,Train Acc: 0.820, Test Acc: 0.805
Epoch: 30, Train Loss: 0.704, Test Loss: 0.742,Train Acc: 0.826, Test Acc: 0.815
I am trying to train a network on Alabone dataset downloaded from "UCI machine learning repository" site. The dataset is look like:
M,0.455,0.365,0.095,0.514,0.2245,0.101,0.15,15
M,0.35,0.265,0.09,0.2255,0.0995,0.0485,0.07,7
F,0.53,0.42,0.135,0.677,0.2565,0.1415,0.21,9
M,0.44,0.365,0.125,0.516,0.2155,0.114,0.155,10
I,0.33,0.255,0.08,0.205,0.0895,0.0395,0.055,7
I have given the exact same column names as they have mentioned. But when I try to apply a neural network to train it, it always gives very poor accuracy rate about 50% just.
I am new in the field so I don't know if I am using a wrong Activation function?, or executing wrong code?, or didn't have preprocess the data well?.
So please help me to find the mistake I have done.
Here's my whole code:
import numpy as np
import pandas as pd
import tensorflow as tf
from sklearn.model_selection import train_test_split
from sklearn.preprocessing import LabelEncoder
def read_dataset():
df = pd.read_csv("abalone.data.txt")
X = np.array(df.drop("Sex", 1))
y = np.array(df["Sex"])
encoder = LabelEncoder()
encoder.fit(y)
y = encoder.transform(y)
Y = one_hot_encode(y)
# print(X.shape)
return X, Y
def one_hot_encode(label):
n_label = len(label)
n_unique_label = len(np.unique(label))
one_hot_encode = np.zeros((n_label, n_unique_label))
one_hot_encode[np.arange(n_label), label] = 1
return one_hot_encode
X, y = read_dataset()
train_X, test_X, train_y, test_y = train_test_split(X, y, test_size=0.2)
n_nodes_1 = 60
n_nodes_2 = 60
n_nodes_3 = 60
n_nodes_4 = 60
model_path = "C:\\Users\Kashif\Projects\DeepLearning-Tensorflow\Learnings\AlaboneDetection\AlaboneModel"
n_class = 3
input_size = X.shape[1]
x = tf.placeholder(tf.float32, [None, input_size])
y = tf.placeholder(tf.float32, [None, n_class])
def neural_network(x):
hidden_1 = {"weights": tf.Variable(tf.random_normal([input_size, n_nodes_1])),
"biases": tf.Variable(tf.random_normal([n_nodes_1]))}
hidden_2 = {"weights": tf.Variable(tf.random_normal([n_nodes_1, n_nodes_2])),
"biases": tf.Variable(tf.random_normal([n_nodes_2]))}
hidden_3 = {"weights": tf.Variable(tf.random_normal([n_nodes_2, n_nodes_3])),
"biases": tf.Variable(tf.random_normal([n_nodes_3]))}
hidden_4 = {"weights": tf.Variable(tf.random_normal([n_nodes_3, n_nodes_4])),
"biases": tf.Variable(tf.random_normal([n_nodes_4]))}
out_layer = {"weights": tf.Variable(tf.random_normal([n_nodes_4, n_class])),
"biases": tf.Variable(tf.random_normal([n_class]))}
# (input * weights) + biases
layer_1 = tf.add(tf.matmul(x, hidden_1["weights"]), hidden_1["biases"])
layer_1 = tf.nn.relu(layer_1)
layer_2 = tf.add(tf.matmul(layer_1, hidden_2["weights"]), hidden_2["biases"])
layer_2 = tf.nn.relu(layer_2)
layer_3 = tf.add(tf.matmul(layer_2, hidden_3["weights"]), hidden_3["biases"])
layer_3 = tf.nn.relu(layer_3)
layer_4 = tf.add(tf.matmul(layer_3, hidden_4["weights"]), hidden_4["biases"])
layer_4 = tf.nn.relu(layer_4)
output = tf.matmul(layer_4, out_layer["weights"]) + out_layer["biases"]
return output
def train_neural_network(x):
prediction = neural_network(x)
cost_function = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits_v2(logits=prediction, labels=y))
optimizer = tf.train.AdamOptimizer().minimize(cost_function)
init = tf.global_variables_initializer()
loss_trace = []
accuracy_trace = []
#saver = tf.train.Saver()
epochs = 1000
with tf.Session() as sess:
sess.run(init)
for i in range(epochs):
sess.run(optimizer, feed_dict={x: train_X, y: train_y})
loss = sess.run(cost_function, feed_dict={x: train_X, y: train_y})
accuracy = np.mean(np.argmax(sess.run(prediction,feed_dict={x:train_X,y:train_y}),axis=1) == np.argmax(train_y,axis=1))
loss_trace.append(loss)
accuracy_trace.append(accuracy)
print('Epoch:', (i + 1), 'loss:', loss, 'accuracy:', accuracy)
#saver.save(sess, model_path)
print('Final training result:', 'loss:', loss, 'accuracy:', accuracy)
loss_test = sess.run(cost_function, feed_dict={x: test_X, y: test_y})
test_pred = np.argmax(sess.run(prediction, feed_dict={x: test_X, y: test_y}), axis=1)
accuracy_test = np.mean(test_pred == np.argmax(test_y, axis=1))
print('Results on test dataset:', 'loss:', loss_test, 'accuracy:', accuracy_test)
train_neural_network(x)
And here's my last result of final three epochs and final accuracy result.
Epoch: 997 loss: 24.625622 accuracy: 0.518407662376534
Epoch: 998 loss: 22.168245 accuracy: 0.48757856929063154
Epoch: 999 loss: 21.896841 accuracy: 0.5001496557916791
Epoch: 1000 loss: 22.28085 accuracy: 0.4968572283747381
Final training result: loss: 22.28085 accuracy: 0.4968572283747381
Results on test dataset: loss: 23.206755 accuracy: 0.4688995215311005
I am new to tensorflow. Maybe you can try two things:
1.decreasing learning rate.such as 0.0001. because your loss is oscillation
2.increase the number of the layer. because your model maybe under-fitting.
If above ways can't solve your problem, you can print your data and check whether train_X and train_y is correct
I am trying to train an AI program that predicts stock values. Every single time, my cost is 0 and my test is 100%. I can not seem to find what I am doing wrong.
placeholder1 = tf.placeholder(tf.float32, shape=[None, 3])
#trainers
dates_train = np.array(dates[0:8000]).astype(np.float32)
highPrice_train = np.array(highPrice[0:8000]).astype(np.float32)
print(dates_train[0][0])
#testers
dates_test = np.array(dates[8000:9564]).astype(np.float32)
highPrice_test = np.array(highPrice[8000:9564]).astype(np.float32)
def get_training_batch(n):
n = min(n,7999)
idx = np.random.choice(7999,n)
return dates_train[idx],highPrice_train[idx]
n_hidden_1 = 100
n_hidden_2 = 100
weights = {
'h1' : tf.Variable(tf.random_normal([3, n_hidden_1])),
'h2' : tf.Variable(tf.random_normal([n_hidden_1,n_hidden_2])),
'out' : tf.Variable(tf.random_normal([n_hidden_2,1]))
}
biases = {
'b1' : tf.Variable(tf.random_normal([n_hidden_1])),
'b2' : tf.Variable(tf.random_normal([n_hidden_2])),
'out' : tf.Variable(tf.random_normal([1]))
}
layer_1 = tf.nn.sigmoid(tf.add(tf.matmul(placeholder1, weights['h1']), biases['b1']))
layer_2 = tf.nn.sigmoid(tf.add(tf.matmul(layer_1, weights['h2']), biases['b2']))
y = tf.matmul(layer_2,weights['out']) + biases['out']
placeholder2 = tf.placeholder(tf.float32,shape=[None,1])
print("Mean")
print(sum(highPrice)/len(highPrice))
mean = tf.reduce_mean(highPrice)
print(mean)
cross_entropy = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits_v2(logits=y, labels=placeholder2))
print("Printing cross_entropy")
print(cross_entropy)
rate = 0.01
optimizer = tf.train.GradientDescentOptimizer(rate).minimize(cross_entropy)
print(optimizer)
prediction = tf.nn.softmax(y)
print(prediction)
##Training
correct_prediction = tf.equal(tf.argmax(prediction, 1), tf.argmax(placeholder2,1))
accuracy = 100 * tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
print(accuracy)
epochs = 1000
batch_size = 10
sess = tf.InteractiveSession()
sess.run(tf.global_variables_initializer())
cost = []
accu = []
test_accu = []
for ep in range(epochs):
x_feed,y_feed = get_training_batch(batch_size)
y_feed = np.reshape(y_feed,[10,1])
_,cos,predictions,acc = sess.run([optimizer, cross_entropy, prediction, accuracy], feed_dict={placeholder1:x_feed, placeholder2:y_feed})
highPrice_test = np.reshape(highPrice_test,[1564,1])
test_acc = accuracy.eval(feed_dict={placeholder1:dates_test, placeholder2:highPrice_test})
cost.append(cos)
accu.append(acc)
test_accu.append(test_acc)
if(ep % (epochs // 10) == 0):
print('[%d]: Cos: %.4f, Acc: %.1f%%, Test Acc: %.1f%%' % (ep,cos,acc,test_acc))
plt.plot(cost)
plt.title('cost')
plt.show()
plt.plot(accu)
plt.title('Train Accuracy')
plt.show()
plt.plot(test_accu)
plt.title('Test Accuracy')
plt.show()
index = 36
p = sess.run(prediction, feed_dict = {placeholder1:dates_train[index:index +1]})[0]
[0]: Cos: 0.0000, Acc: 100.0%, Test Acc: 100.0%
[100]: Cos: 0.0000, Acc: 100.0%, Test Acc: 100.0%
That is my output for every single test. I expect there to be a cost and accuracy should not be 100%
It seems the problem is that softmax_cross_entropy_with_logits_v2 needs more than 1 output class: Cost function always returning zero for a binary classification in tensorflow. If I change highPrice to 2 dimensional it works.
As a side note, if I understand your problem correctly, you are trying to predict the exact stock price. A better way may be to just predict whether it is going up or down, so you can create categorical labels say (up, no change, down).
import tensorflow as tf
y_dimensions = 2
placeholder1 = tf.placeholder(tf.float32, shape=[None, 3])
dates = np.array([pd.date_range('2012-10-01', periods=10000, freq='10min'),
pd.date_range('2012-10-01', periods=10000, freq='20min'),
pd.date_range('2012-10-01', periods=10000,
freq='30min')]).T
highPrice = np.random.random((10000, y_dimensions)) * 100
# training set
dates_train = np.array(dates[0:8000]).astype(np.float32)
highPrice_train = np.array(highPrice[0:8000]).astype(np.float32)
print("dates train", dates_train[0])
# testing set
dates_test = np.array(dates[8000:9564]).astype(np.float32)
highPrice_test = np.array(highPrice[8000:9564]).astype(np.float32)
def get_training_batch(n):
n = min(n, 7999)
idx = np.random.choice(7999, n) # create size n sample from range 7999
#print("len batch:", len(idx))
return dates_train[idx], highPrice_train[idx]
n_hidden_1 = 100
n_hidden_2 = 100
weights = {
'h1': tf.Variable(tf.random_normal([3, n_hidden_1])),
'h2': tf.Variable(tf.random_normal([n_hidden_1, n_hidden_2])),
'out': tf.Variable(tf.random_normal([n_hidden_2, y_dimensions]))
}
biases = {
'b1': tf.Variable(tf.random_normal([n_hidden_1])),
'b2': tf.Variable(tf.random_normal([n_hidden_2])),
'out': tf.Variable(tf.random_normal([1]))
}
layer_1 = tf.nn.sigmoid(
tf.add(tf.matmul(placeholder1, weights['h1']), biases['b1']))
layer_2 = tf.nn.sigmoid(
tf.add(tf.matmul(layer_1, weights['h2']), biases['b2']))
y = tf.matmul(layer_2, weights['out']) + biases['out']
placeholder2 = tf.placeholder(tf.float32, shape=[None, y_dimensions])
print("Mean:", sum(highPrice) / len(highPrice))
mean = tf.reduce_mean(highPrice)
print("TF mean:", mean)
# labels are high prices, logits are model output
cross_entropy = tf.reduce_mean(
tf.nn.softmax_cross_entropy_with_logits_v2(logits=y,
labels=placeholder2))
print("cross_entropy:", cross_entropy)
rate = 0.01
optimizer = tf.train.GradientDescentOptimizer(rate).minimize(cross_entropy)
print("optimizer:", optimizer)
prediction = tf.nn.softmax(y)
print("Prediction:", prediction)
##Training
correct_prediction = tf.equal(tf.argmax(prediction, 1),
tf.argmax(placeholder2, 1))
accuracy = 100 * tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
print("accuracy:", accuracy)
epochs = 300
batch_size = 10
sess = tf.InteractiveSession()
sess.run(tf.global_variables_initializer())
cost = []
accu = []
test_accu = []
for ep in range(epochs):
x_feed, y_feed = get_training_batch(batch_size)
y_feed = np.reshape(y_feed, [batch_size, y_dimensions])
_, cos, predictions, acc = sess.run(
[optimizer, cross_entropy, prediction, accuracy],
feed_dict={placeholder1: x_feed, placeholder2: y_feed})
highPrice_test = np.reshape(highPrice_test, [1564, y_dimensions])
test_acc = accuracy.eval(
feed_dict={placeholder1: dates_test, placeholder2: highPrice_test})
# create history
cost.append(cos)
accu.append(acc)
test_accu.append(test_acc)
# every 10 epochs
if ep % (epochs // 10) == 0:
print('[%d]: Cos: %.4f, Acc: %.1f%%, Test Acc: %.1f%%' % (
ep, cos, acc, test_acc))
plt.plot(cost)
plt.title('cost')
plt.show()
plt.plot(accu)
plt.title('Train Accuracy')
plt.show()
plt.plot(test_accu)
plt.title('Test Accuracy')
plt.show()
index = 78
p = sess.run(prediction,
feed_dict={placeholder1: dates_train[index:index + 1]})[0]
print("final x input for prediction:", dates_train[index:index + 1])
print("final y prediction:", p)
Output:
[0]: Cos: 232.5091, Acc: 50.0%, Test Acc: 50.4%
[30]: Cos: 1119.8948, Acc: 70.0%, Test Acc: 49.6%
[60]: Cos: 554.2071, Acc: 50.0%, Test Acc: 50.4%
[90]: Cos: 668.4500, Acc: 60.0%, Test Acc: 50.4%
[120]: Cos: 1485.1707, Acc: 20.0%, Test Acc: 50.4%
[150]: Cos: 2667.8867, Acc: 50.0%, Test Acc: 50.4%
[180]: Cos: 806.8883, Acc: 50.0%, Test Acc: 50.4%
[210]: Cos: 105.7802, Acc: 50.0%, Test Acc: 49.6%
[240]: Cos: 2002.2031, Acc: 50.0%, Test Acc: 50.4%
[270]: Cos: 3357.0098, Acc: 20.0%, Test Acc: 50.4%
Based on the layer function
def neuron_layer(X, n_neurons, name, activation_fn=None):
with tf.name_scope(name):
n_inputs = int(X.get_shape()[1])
stddev = 2 / np.sqrt(n_inputs)
init = tf.truncated_normal((n_inputs, n_neurons), stddev=stddev)
W = tf.Variable(init, name="kernel")
b = tf.Variable(tf.zeros([n_neurons]), name="bias")
Z = tf.matmul(X, W) + b
if activation_fn is not None:
return activation_fn(Z)
else:
return Z
The following network for a binary classification problem is constructed:
n_hidden1 = 100
n_hidden2 = 120
n_outputs = 1 # single value prediction
n_inputs = X_test.shape[1]
reset_graph()
X = tf.placeholder(tf.float32, shape=(None, n_inputs), name="X")
y = tf.placeholder(tf.float32, shape=(None), name="y")
layer1 = neuron_layer(X, n_hidden1, "layer1", activation_fn=tf.nn.relu)
layer2 = neuron_layer(layer1, n_hidden2, "layer2", activation_fn=tf.nn.relu)
prediction = neuron_layer(layer2, n_outputs, "output",activation_fn=tf.nn.sigmoid)
cost = tf.losses.log_loss(y,prediction)
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
correct_prediction = tf.equal(tf.argmax(prediction, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
init = tf.global_variables_initializer()
The training routine
learning_rate = 0.01
n_epochs = 20
batch_size = 60
num_rec = X_train.shape[0]
n_batches = int(np.ceil(num_rec / batch_size))
acc_test = 0. # assign the result of accuracy testing to this variable
with tf.Session() as sess:
sess.run(init)
for epoch in range(n_epochs):
for batch_index in range(n_batches):
X_batch,y_batch = random_batch(X_train,Y_train,batch_size)
_,opt = sess.run([optimizer,cost], feed_dict={X: X_batch, y: y_batch})
loss, acc = sess.run([cost, accuracy], feed_dict={X: X_batch,y: y_batch})
print("epoch " + str(epoch) + ", Loss= " + \
"{:.6f}".format(loss) + ", Training Accuracy= " + \
"{:.5f}".format(acc))
print("Optimization Finished!")
_, acc_test = sess.run([cost, accuracy], feed_dict={X:X_test,y:Y_test})
generates the following output:
epoch 0, Loss= -6.756775, Training Accuracy= 1.00000 Optimization
Finished!
[. . .]
epoch 19, Loss=
-6.769919, Training Accuracy= 1.00000 Optimization Finished!
and the the accuracy on the test set acc_test is 1.0.
The batches are generated by
def random_batch(X_train, y_train, batch_size):
np.random.seed(42)
rnd_indices = np.random.randint(0, len(X_train), batch_size)
X_batch = X_train[rnd_indices]
y_batch = y_train[rnd_indices]
return X_batch, y_batch
the input shapes are
print(X_batch.shape,y_batch.shape,X_test.shape,Y_test.shape)
>(60, 3) (60, 1) (2500, 3) (2500, 1)
Obviously, the accuracy on the training and test tests can't be correct. Where could be the problem in the network, training or evaluation procedure?
The model is overfitting due to which you are getting abnormally high accuracy at initial epochs, to avoid overfitting you can use regularization methods or increase dataset by augmenting. Use ImageDataGenerator for augmentation, it will provide images to model in batches. Try setting dropout to 0.2. Enable early stopping in callbacks, it will terminate training when model performance degrades. Try playing with patience in early stopping.
i am doing binary classification in NN tensorflow without encoding the labels.. everything is fine except the accuracy function always return 1.0
Output is
Epoch 0 completed out of 10 loss: 5536.991802096367
Epoch 1 completed out of 10 loss: 1777.5951525866985
Epoch 2 completed out of 10 loss: 1442.1777643710375
Epoch 3 completed out of 10 loss: 1315.4084038436413
.
.
.
Epoch 9 completed out of 10 loss: 968.3492169082165
Accuracy: 1.0
import matplotlib.pyplot as plt
import pandas as pd
import matplotlib.dates as mdates
import numpy as np
from matplotlib import style
import csv,math,time
from sklearn import preprocessing, cross_validation
import tensorflow as tf
df2=pd.read_csv("Book.csv",encoding="latin-1",index_col=0)
df2['iday'].replace(0,1,inplace=True)
df2['imonth'].replace(0,1,inplace=True)
df2['Datetime'] = pd.to_datetime(dict(year=df2.iyear, month=df2.imonth, day=df2.iday))
print(df2.tail());
df=df2[['Datetime','country','longitude','latitude','suicide','attacktype1','targtype1','nkill','nwound','weaptype1','success']]
df.set_index('Datetime', inplace=True)
df.fillna(value=-99999, inplace=True) #cleaning data!!!
XX = np.array(df.drop(['success'], 1)) #
XX = preprocessing.scale(XX) #dividing dataset into features and label
#df.dropna(inplace=True) #dropping those rows which contain nulls
yy = np.array(df['success'])
yy=yy.reshape(-1,1)
X_train, X_test, y_train, y_test = cross_validation.train_test_split(XX, yy,random_state=2) #training
n_nodes_hl1 = 100
n_nodes_hl2 = 100
n_nodes_hl3 = 100
n_input=X_train.shape[1]
print(X_train.shape)
print(yy.shape)
n_classes=y_train.shape[1]
batch_size = 100
x = tf.placeholder('float', [None, n_input])
y = tf.placeholder('float')
def neural_network_model(data):
hidden_1_layer = {'weights':tf.Variable(tf.random_normal([n_input, n_nodes_hl1])),
'biases':tf.Variable(tf.random_normal([n_nodes_hl1]))}
hidden_2_layer = {'weights':tf.Variable(tf.random_normal([n_nodes_hl1, n_nodes_hl2])),
'biases':tf.Variable(tf.random_normal([n_nodes_hl2]))}
hidden_3_layer = {'weights':tf.Variable(tf.random_normal([n_nodes_hl2, n_nodes_hl3])),
'biases':tf.Variable(tf.random_normal([n_nodes_hl3]))}
output_layer = {'weights':tf.Variable(tf.random_normal([n_nodes_hl3, n_classes])),
'biases':tf.Variable(tf.random_normal([n_classes])),}
l1 = tf.add(tf.matmul(data,hidden_1_layer['weights']), hidden_1_layer['biases'])
l1 = tf.nn.relu(l1)
l2 = tf.add(tf.matmul(l1,hidden_2_layer['weights']), hidden_2_layer['biases'])
l2 = tf.nn.relu(l2)
l3 = tf.add(tf.matmul(l2,hidden_3_layer['weights']), hidden_3_layer['biases'])
l3 = tf.nn.relu(l3)
output = tf.matmul(l3,output_layer['weights']) + output_layer['biases']
return output
def train_neural_network(x):
prediction = neural_network_model(x)
# OLD VERSION:
#cost = tf.reduce_mean( tf.nn.softmax_cross_entropy_with_logits(prediction,y) )
# NEW:
cost = tf.reduce_mean( tf.nn.sigmoid_cross_entropy_with_logits(logits=prediction, labels=y) )
optimizer = tf.train.AdamOptimizer().minimize(cost)
hm_epochs = 10
with tf.Session() as sess:
# OLD:
#sess.run(tf.initialize_all_variables())
# NEW:
sess.run(tf.global_variables_initializer())
for epoch in range(hm_epochs):
total_batch = int(len(X_train) / batch_size)
print(total_batch)
x_batches = np.array_split(X_train, total_batch)
y_batches = np.array_split(y_train, total_batch)
epoch_loss = 0
for i in range(total_batch):
epoch_x, epoch_y =x_batches[i], y_batches[i]
_, c = sess.run([optimizer, cost], feed_dict={x: epoch_x, y:
epoch_y})
epoch_loss += c
print('Epoch', epoch, 'completed out
of',hm_epochs,'loss:',epoch_loss)
correct = tf.equal(tf.argmax(prediction, 1), tf.argmax(y, 1))
accuracy = tf.reduce_mean(tf.cast(correct, 'float'))
print('Accuracy:',accuracy.eval({x:X_test, y:y_test}))
train_neural_network(x)