Related
I want to see test accuracy in tensorboard, but it seems I get accuracy with training data. I print test accuracy on console, and it is showing about 70%, but in tensorboard, the curve showed accuracy is growing and finally almost 100%.
This is my code:
def train_crack_captcha_cnn(is_train, checkpoint_dir):
global max_acc
X = tf.placeholder(tf.float32, [None, dr.ROWS, dr.COLS, dr.CHANNELS])
Y = tf.placeholder(tf.float32, [None, 1, 1, 2])
output, end_points = resnet_v2_50(X, num_classes = 2)
global_steps = tf.Variable(1, trainable=False)
learning_rate = tf.train.exponential_decay(0.001, global_steps, 100, 0.9)
with tf.device('/device:GPU:0'):
loss = tf.reduce_mean(tf.nn.sigmoid_cross_entropy_with_logits(labels=Y, logits=output))
# optimizer 为了加快训练 learning_rate应该开始大，然后慢慢衰
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(loss, global_step=global_steps)
predict = tf.argmax(output, axis = 3)
l = tf.argmax(Y, axis = 3)
correct_pred = tf.equal(predict, l)
accuracy = tf.reduce_mean(tf.cast(correct_pred, tf.float32))
## tensorboard
tf.summary.scalar('test_accuracy', accuracy)
tf.summary.scalar("loss", loss)
tf.summary.scalar("learning_rate", learning_rate)
saver = tf.train.Saver()
with tf.Session(config=tf.ConfigProto(allow_soft_placement = True)) as sess:
if is_train:
writer = tf.summary.FileWriter("/tmp/cnn_log/log", graph = sess.graph)
sess.run(tf.global_variables_initializer())
step_value = sess.run(global_steps)
while step_value < 100000:
step_value = sess.run(global_steps)
merged = tf.summary.merge_all()
batch_x, batch_y = get_next_batch()
result, _, _loss= sess.run([merged, optimizer, loss], feed_dict={X: batch_x, Y: batch_y})
writer.add_summary(result, step_value)
print('step : {} loss : {}'.format(step_value, _loss))
# 每100 step计算一次准确率
if step_value % 20 == 0:
acc = sess.run(accuracy, feed_dict={X: validation, Y: validation_labels})
print('accuracy : {}'.format(acc))
# 如果准确率大于max_acc,保存模型,完成训练
if acc > max_acc:
max_acc = float(acc) #转换类型防止变为同一个引用
saver.save(sess, checkpoint_dir + "/" + str(step_value) + '-' + str(acc) + "/model.ckpt", global_step=global_steps)
##### predict #####
# predict_y = sess.run(output, feed_dict={X: test})
# data = pd.DataFrame([i for i in range(1, len(predict_y) + 1)], columns = ['id'])
# predict_y = np.argmax(predict_y, axis = 3)
# predict_y = np.reshape(predict_y,(-1))
# print(predict_y)
# predict_y = pd.Series(predict_y, name='label')
# data['label'] = predict_y
# data.to_csv("gender_submission.csv" + str(step), index=False)
##### end #####
writer.close()
else:
ckpt = tf.train.get_checkpoint_state(checkpoint_dir)
if ckpt and ckpt.model_checkpoint_path:
saver.restore(sess, ckpt.model_checkpoint_path)
acc = sess.run(accuracy, feed_dict={X: validation, Y: validation_labels})
print('accuracy : {}'.format(acc))
I add accuracy into tensorboard like this:
tf.summary.scalar('test_accuracy', accuracy)
and every 20 step, I get one accuracy about test data, and print the result to console, which is not the same with data shown on tensorboard.
Why?
I wrote two version code for minst data set in tensorflow. The first one is just similar to the example code with input[None,784]
However, the second piece is what i change. I just modify the input scale to [784,None] and change some corresponding matrix format.
I am confused with the difference in result. I am a beginner for tensorflow. Really wanna your help.
Thanks
import tensorflow as tf
import tensorflow.examples.tutorials.mnist.input_data as input_data
mnist = input_data.read_data_sets(r"C:\Ruigy\NN\minst", one_hot=True)
def hidden_layer(X, sizeOutput, non_linear_name = ''):
sizeInput = X.shape[1]
W = tf.Variable(tf.zeros([sizeInput,sizeOutput]))
B = tf.Variable(tf.zeros([sizeOutput]))
Y = tf.matmul(X,W) + B
if non_linear_name == '': return Y
elif non_linear_name == 'softmax': A = tf.nn.softmax(Y)
elif non_linear_name == 'ReLU': A = tf.nn.relu(Y)
return A
X = tf.placeholder(tf.float32, [None, 784],name = 'Input')
Y_LABEL = tf.placeholder(tf.float32, [None, 10], name = 'Label')
Y_linear= hidden_layer(X,Y_LABEL.shape[1])
cross_entropy = tf.reduce_mean(
tf.nn.softmax_cross_entropy_with_logits(labels=Y_LABEL,
logits=Y_linear))
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)
sess = tf.InteractiveSession()
tf.global_variables_initializer().run()
for _ in range(1000):
batch_xs, batch_ys = mnist.train.next_batch(100)
sess.run(train_step, feed_dict={X: batch_xs, Y_LABEL: batch_ys})
correct_prediction = tf.equal(tf.argmax(Y_linear, 1), tf.argmax(Y_LABEL, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
print(sess.run(accuracy, feed_dict={X: mnist.test.images, Y_LABEL: mnist.test.labels}))
The result is 0.9188
import tensorflow as tf
import tensorflow.examples.tutorials.mnist.input_data as input_data
mnist = input_data.read_data_sets(r"C:\Ruigy\NN\minst", one_hot=True)
def hidden_layer(X, sizeOutput, non_linear_name = ''):
sizeInput = X.shape[0]
W = tf.Variable(tf.zeros([sizeInput,sizeOutput]))
B = tf.Variable(tf.zeros([sizeOutput,1]))
Y = tf.matmul(W,X,True) + B
if non_linear_name == '': return Y
elif non_linear_name == 'softmax': A = tf.nn.softmax(Y)
elif non_linear_name == 'ReLU': A = tf.nn.relu(Y)
return A
X = tf.placeholder(tf.float32, [784,None],name = 'Input')
Y_LABEL = tf.placeholder(tf.float32, [10,None], name = 'Label')
Y_linear= hidden_layer(X,Y_LABEL.shape[0])
cross_entropy = tf.reduce_mean(
tf.nn.softmax_cross_entropy_with_logits(labels=Y_LABEL,
logits=Y_linear))
train_step = tf.train.GradientDescentOptimizer(0.5).minimize(cross_entropy)
sess = tf.InteractiveSession()
tf.global_variables_initializer().run()
for _ in range(1000):
batch_xs, batch_ys = mnist.train.next_batch(100)
sess.run(train_step, feed_dict={X: batch_xs.T, Y_LABEL: batch_ys.T})
correct_prediction = tf.equal(tf.argmax(Y_linear, 0), tf.argmax(Y_LABEL, 0))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
print(sess.run(accuracy, feed_dict={X: mnist.test.images.T, Y_LABEL: mnist.test.labels.T}))
The result is 0.6638
I am really confused. where am i wrong ? I just wanna change the format.
Data is to be taken in the same format as given in the dataset. If you want to change format, take a tf.tranpose() for Input after assigning to the placeholder
I am trying to make a character recognition classifier for bangla alphabets. The images are size of 50x50. There are in total of 50 classes. Using the below CNN model to train but I am encountering this error: "ValueError: Validation size should be between 0 and 0. Received: 5000."
How do I resolve this?
MODEL
# Python 3.6.0
# tensorflow 1.1.0
import os
import os.path as path
import tensorflow as tf
from tensorflow.python.tools import freeze_graph
from tensorflow.python.tools import optimize_for_inference_lib
from tensorflow.examples.tutorials.mnist import input_data
MODEL_NAME = 'mnist_convnet'
NUM_STEPS = 3000
BATCH_SIZE = 16
def model_input(input_node_name, keep_prob_node_name):
x = tf.placeholder(tf.float32, shape=[None, 50*50], name=input_node_name)
keep_prob = tf.placeholder(tf.float32, name=keep_prob_node_name)
y_ = tf.placeholder(tf.float32, shape=[None, 50])
return x, keep_prob, y_
def build_model(x, keep_prob, y_, output_node_name):
x_image = tf.reshape(x, [-1, 50, 50, 1])
# 50*50*1
conv1 = tf.layers.conv2d(x_image, 64, 3, 1, 'same', activation=tf.nn.relu)
# 50*50*64
pool1 = tf.layers.max_pooling2d(conv1, 2, 2, 'same')
# 14*14*64
conv2 = tf.layers.conv2d(pool1, 128, 3, 1, 'same', activation=tf.nn.relu)
# 14*14*128
pool2 = tf.layers.max_pooling2d(conv2, 2, 2, 'same')
# 7*7*128
conv3 = tf.layers.conv2d(pool2, 256, 3, 1, 'same', activation=tf.nn.relu)
# 7*7*256
pool3 = tf.layers.max_pooling2d(conv3, 2, 2, 'same')
# 4*4*256
flatten = tf.reshape(pool3, [-1, 4*4*256])
fc = tf.layers.dense(flatten, 1024, activation=tf.nn.relu)
dropout = tf.nn.dropout(fc, keep_prob)
logits = tf.layers.dense(dropout, 50)
outputs = tf.nn.softmax(logits, name=output_node_name)
# loss
loss = tf.reduce_mean(
tf.nn.softmax_cross_entropy_with_logits(labels=y_, logits=logits))
# train step
train_step = tf.train.AdamOptimizer(1e-4).minimize(loss)
# accuracy
correct_prediction = tf.equal(tf.argmax(outputs, 1), tf.argmax(y_, 1))
accuracy = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
tf.summary.scalar("loss", loss)
tf.summary.scalar("accuracy", accuracy)
merged_summary_op = tf.summary.merge_all()
return train_step, loss, accuracy, merged_summary_op
def train(x, keep_prob, y_, train_step, loss, accuracy,
merged_summary_op, saver):
print("training start...")
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
init_op = tf.global_variables_initializer()
with tf.Session() as sess:
sess.run(init_op)
tf.train.write_graph(sess.graph_def, 'out',
MODEL_NAME + '.pbtxt', True)
# op to write logs to Tensorboard
summary_writer = tf.summary.FileWriter('logs/',
graph=tf.get_default_graph())
for step in range(NUM_STEPS):
batch = mnist.train.next_batch(BATCH_SIZE)
if step % 100 == 0:
train_accuracy = accuracy.eval(feed_dict={
x: batch[0], y_: batch[1], keep_prob: 1.0})
print('step %d, training accuracy %f' % (step, train_accuracy))
_, summary = sess.run([train_step, merged_summary_op],
feed_dict={x: batch[0], y_: batch[1], keep_prob: 0.5})
summary_writer.add_summary(summary, step)
saver.save(sess, 'out/' + MODEL_NAME + '.chkp')
test_accuracy = accuracy.eval(feed_dict={x: mnist.test.images,
y_: mnist.test.labels,
keep_prob: 1.0})
print('test accuracy %g' % test_accuracy)
print("training finished!")
def export_model(input_node_names, output_node_name):
freeze_graph.freeze_graph('out/' + MODEL_NAME + '.pbtxt', None, False,
'out/' + MODEL_NAME + '.chkp', output_node_name, "save/restore_all",
"save/Const:0", 'out/frozen_' + MODEL_NAME + '.pb', True, "")
input_graph_def = tf.GraphDef()
with tf.gfile.Open('out/frozen_' + MODEL_NAME + '.pb', "rb") as f:
input_graph_def.ParseFromString(f.read())
output_graph_def = optimize_for_inference_lib.optimize_for_inference(
input_graph_def, input_node_names, [output_node_name],
tf.float32.as_datatype_enum)
with tf.gfile.FastGFile('out/opt_' + MODEL_NAME + '.pb', "wb") as f:
f.write(output_graph_def.SerializeToString())
print("graph saved!")
def main():
if not path.exists('out'):
os.mkdir('out')
input_node_name = 'input'
keep_prob_node_name = 'keep_prob'
output_node_name = 'output'
x, keep_prob, y_ = model_input(input_node_name, keep_prob_node_name)
train_step, loss, accuracy, merged_summary_op = build_model(x, keep_prob, y_, output_node_name)
saver = tf.train.Saver()
train(x, keep_prob, y_, train_step, loss, accuracy, merged_summary_op, saver)
export_model([input_node_name, keep_prob_node_name], output_node_name)
if __name__ == '__main__':
main()
ERROR
ValueError Traceback (most recent call last)
<ipython-input-2-2015e0ea466d> in <module>()
136
137 if __name__ == '__main__':
--> 138 main()
<ipython-input-2-2015e0ea466d> in main()
131 saver = tf.train.Saver()
132
--> 133 train(x, keep_prob, y_, train_step, loss, accuracy, merged_summary_op, saver)
134
135 export_model([input_node_name, keep_prob_node_name], output_node_name)
<ipython-input-2-2015e0ea466d> in train(x, keep_prob, y_, train_step, loss, accuracy, merged_summary_op, saver)
67 print("training start...")
68
---> 69 mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
70
71 init_op = tf.global_variables_initializer()
/anaconda3/envs/nlpTFnltk/lib/python3.6/site-packages/tensorflow/contrib/learn/python/learn/datasets/mnist.py in read_data_sets(train_dir, fake_data, one_hot, dtype, reshape, validation_size)
247 raise ValueError(
248 'Validation size should be between 0 and {}. Received: {}.'
--> 249 .format(len(train_images), validation_size))
250
251 validation_images = train_images[:validation_size]
ValueError: Validation size should be between 0 and 0. Received: 5000.
You're using the MNIST tutorial code, which is calling read_data_sets from here; note that validation_size of 5000 comes from that function's default parameters. It's expecting to get data from the following files:
TRAIN_IMAGES = 'train-images-idx3-ubyte.gz'
TRAIN_LABELS = 'train-labels-idx1-ubyte.gz'
TEST_IMAGES = 't10k-images-idx3-ubyte.gz'
TEST_LABELS = 't10k-labels-idx1-ubyte.gz'
Normally it would try to download those files if it doesn't find them, but the fact that you're getting a validation_size of 0 suggests it isn't doing so. This wouldn't help you anyway, since you don't want to use the MNIST data.
Even if you rename your train and test files to match the above filenames, your code won't work because the MNIST code is also calling extract_labels, which has a default parameter num_classes=10 while you want this to be 50. Your best bet is probably to get rid of the MNIST import completely and read about how to set up an input pipeline; it's not difficult compared to the stuff you've done already.
I use tensorflow to run random forest model.
code:
import tensorflow as tf
from tensorflow.contrib.tensor_forest.python import tensor_forest
from tensorflow.python.ops import resources
from tensorflow.examples.tutorials.mnist import input_data
num_steps = 50000 # Total steps to train
batch_size = 1024 # The number of samples per batch
num_classes = 10 # The 10 digits
num_features = 784 # Each image is 28x28 pixels
num_trees = 10
max_nodes = 1000
X = tf.placeholder(tf.float32, shape=[None, num_features])
Y = tf.placeholder(tf.int32, shape=[None])
hparams = tensor_forest.ForestHParams(num_classes=num_classes,
num_features=num_features,
num_trees=num_trees,
max_nodes=max_nodes).fill()
forest_graph = tensor_forest.RandomForestGraphs(params=hparams)
train_op = forest_graph.training_graph(X, Y)
loss_op = forest_graph.training_loss(X,Y)
infer_op = forest_graph.inference_graph(X)
correct_prediction = tf.equal(tf.arg_max(infer_op, 1), tf.cast(Y, tf.int64))
accuracy_op = tf.reduce_mean(tf.cast(correct_prediction, tf.float32))
init_vars = tf.group(tf.global_variables_initializer(), resources.initialize_resources(resources.shared_resources()))
sess = tf.Session()
sess.run(init_vars)
test_x, test_y = mnist.test.images, mnist.test.labels
for i in range(1, num_steps + 1):
batch_x, batch_y = mnist.train.next_batch(batch_size=batch_size)
_, l = sess.run([train_op, loss_op], feed_dict={X:batch_x, Y: batch_y})
if i % 100 == 0 or i == 1:
acc = sess.run(accuracy_op, feed_dict={X:batch_x, Y: batch_y})
print('step %i, loss: %f, acc: %f' % (i, l, acc))
if i % 100 == 0:
print("Test Accuracy:", sess.run(accuracy_op, feed_dict={X: test_x, Y: test_y}))
print("Test Accuracy:", sess.run(accuracy_op, feed_dict={X: test_x, Y: test_y}))
question: how to save model and restore it to predict?
This is the newest version of tf's random forest, i use tf 1.2, it works. I found someone use TensorForestEstimator, but it dont work with tf 1.2,
the tf update so frequently !
save model is easy, but restore it kill me. whatever i do, always, case 'FertileStatsResourceHandleOp' error, at last, i add two lines code before restore, it works.
hparams = tensor_forest.ForestHParams(num_classes=num_classes,
num_features=num_features,
num_trees=num_trees,
max_nodes=max_nodes).fill()
forest_graph = tensor_forest.RandomForestGraphs(params=hparams)
the commplete codes as following:
X = tf.placeholder(tf.float32, shape=[None, num_features],name="input_x")
Y = tf.placeholder(tf.int32, shape=[None], name="input_y")
hparams = tensor_forest.ForestHParams(num_classes=num_classes,
num_features=num_features,
num_trees=num_trees,
max_nodes=max_nodes).fill()
forest_graph = tensor_forest.RandomForestGraphs(params=hparams)
train_op = forest_graph.training_graph(X, Y)
loss_op = forest_graph.training_loss(X,Y)
correct_prediction = tf.argmax(infer_op, 1, name="predictions")
accuracy_op = tf.reduce_mean(tf.cast(tf.equal(correct_prediction,tf.cast(Y, tf.int64)), tf.float32),name="accuracy")
init_vars = tf.group(tf.global_variables_initializer(), resources.initialize_resources(resources.shared_resources()))
sess = tf.Session()
sess.run(init_vars)
test_x, test_y = mnist.test.images, mnist.test.labels
saver = tf.train.Saver(save_relative_paths=True, max_to_keep=10)
checkpoint_prefix = 'checkpoints/model'
for i in range(1, num_steps + 1):
batch_x, batch_y = mnist.train.next_batch(batch_size=batch_size)
_, l = sess.run([train_op, loss_op], feed_dict={X:batch_x, Y: batch_y})
if i % 10 == 0 or i == 1:
acc = sess.run(accuracy_op, feed_dict={X:batch_x, Y: batch_y})
print('step %i, loss: %f, acc: %f' % (i, l, acc))
if i % 10 == 0:
print("Test Accuracy:", sess.run(accuracy_op, feed_dict={X: test_x, Y: test_y}))
path = saver.save(sess, checkpoint_prefix, global_step=i)
print("last Saved model checkpoint to {} at step {}".format(path, i))
print("Test Accuracy:", sess.run(accuracy_op, feed_dict={X: test_x, Y: test_y}))
restore model:
hparams = tensor_forest.ForestHParams(num_classes=num_classes,
num_features=num_features,
num_trees=num_trees,
max_nodes=max_nodes).fill()
forest_graph = tensor_forest.RandomForestGraphs(params=hparams)
checkpoint_file = tf.train.latest_checkpoint('checkpoints')
graph = tf.Graph()
with graph.as_default():
session_conf = tf.ConfigProto(allow_soft_placement=True, log_device_placement=False)
sess = tf.Session(config=session_conf)
with sess.as_default():
saver = tf.train.import_meta_graph("{}.meta".format(checkpoint_file), clear_devices=True)
saver.restore(sess, checkpoint_file)
input_x = graph.get_operation_by_name("input_x").outputs[0]
input_y = graph.get_operation_by_name("input_y").outputs[0]
predictions = graph.get_operation_by_name("predictions").outputs[0]
accuracy = graph.get_operation_by_name("accuracy").outputs[0]
acc = sess.run(accuracy, {input_x: test_x, input_y:test_y })
predictions = sess.run(predictions, {input_x: test_x })
print(predictions)
This question already has an answer here:
TensorFlow: slow performance when getting gradients at inputs
(1 answer)
Closed 6 years ago.
Im an electrical engineering student and im trying to model an industrial plant based on the power in a resistor inside a boiller, the temperature of the water in the boiller and the water flow passing through the boiller using python 3.5 and tensorflow.
The matter is that im a beginner at python and tensorflow and i wrote this code that works, but the trainning starts fast and rapidly start to slow down, and by the middle of the trainning its starts to taking ages between steps.
I just need some help on the optimization, and of course, any tips are welcome!
Thank you very much!
Here is the code:
import numpy as np
import tensorflow as tf
input_vec_size = 3
step_size = 0.05
batch_size = 3
test_size = 16
train_end = 1905
eval_end = 290
predict_end = 1396
n_cores = 4
def read_my_file_format(filename_queue):
line_reader = tf.TextLineReader(skip_header_lines=1)
_, csv_row = line_reader.read(filename_queue)
record_defaults = [[0.0], [0.0], [0.0], [0.0]]
time, power_in, temperature, flow = \
tf.decode_csv(csv_row, record_defaults=record_defaults)
features = tf.pack([
power_in,
temperature
])
return features, flow
def input_pipeline(directory, batch_size, n_cores, buffer_size, num_epochs=None):
filename_queue = tf.train.string_input_producer(
tf.train.match_filenames_once(directory),
shuffle=True)
features, flow = read_my_file_format(filename_queue)
x, y = tf.train.batch(
[features, flow], batch_size=batch_size, allow_smaller_final_batch=True)
def init_weights(shape):
return tf.Variable(tf.random_normal(shape, stddev=0.001))
def init_bias(shape): #inicializa bias
initial = tf.constant(0.001, shape=shape) #variancia 0.1
return tf.Variable(initial)
def model(X, w_h, w_h2, w_o, B, B2, B3, p_keep_input, p_keep_hidden):
X = tf.nn.dropout(X, p_keep_input)
h = tf.nn.relu(tf.matmul(X, w_h)+B)
h = tf.nn.dropout(h, p_keep_hidden)
h2 = tf.nn.relu(tf.matmul(h, w_h2)+B2)
h2 = tf.nn.dropout(h2, p_keep_hidden)
return tf.matmul(h2, w_o)+B3
X = tf.placeholder("float", [None, input_vec_size])
Y = tf.placeholder("float", [None, 1])
p_keep_hidden = tf.placeholder("float")
p_keep_input = tf.placeholder("float")
w_h = init_weights([input_vec_size, fclayer_size])
w_h2= init_weights([fclayer_size, fclayer_size])
w_o= init_weights([fclayer_size, 1])
B = init_bias([fclayer_size])
B2 = init_bias([fclayer_size])
B3 = init_bias([1])
py_x = model(X, w_h, w_h2, w_o, B, B2, B3, p_keep_input, p_keep_hidden)
predict_op = py_x[0]
cost = tf.reduce_mean(tf.square(predict_op - Y))
train_op = tf.train.MomentumOptimizer(step_size, 0.5).minimize(cost)
saver = tf.train.Saver()
directory = "./train/*.csv"
x, y = input_pipeline(directory, batch_size, n_cores, buffer_size, num_epochs=None)
directory_eval = "./eval/*.csv"
xe, ye = input_pipeline(directory_eval, test_size, n_cores, buffer_size, num_epochs=None)
directory_predict = "./predict/*.csv"
xp, yp = input_pipeline(directory_predict, test_size, n_cores, buffer_size, num_epochs=None)
with tf.Session() as sess:
tf.initialize_all_variables().run()
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(coord=coord)
print("==================================TREINAMENTO=================================")
for iteraction in range(int(train_end/batch_size)):
trX, trY = sess.run([x,y])
for i in range(0, batch_size):
features, features_past, features_past2 = sess.run(tf.unpack(trX[i])), sess.run(tf.unpack(trX[i-1])), sess.run(tf.unpack(trX[i-2]))
power_in_i = features[0] - 4
temperature_i = features[1]
temperature_i1 = features_past[1]
temperature_i2 = features_past2[1]
trX_now = tf.pack([power_in_i, (temperature_i-temperature_i1), (temperature_i-temperature_i2)])
trX_now = sess.run(trX_now)
X_Batch, Y_Batch = trX_now.reshape([-1, input_vec_size]), trY[i].reshape([-1, 1])
sess.run(train_op, feed_dict={X: X_Batch,
Y: Y_Batch, p_keep_input: 0.95, p_keep_hidden: 0.7})
if(i%batch_size == 0):
predict_train = sess.run(tf.reshape(predict_op, [-1, 1]), feed_dict={X: X_Batch, p_keep_input: 1.0, p_keep_hidden: 1.0})
train_cost = sess.run(cost, feed_dict={py_x: predict_train, Y: Y_Batch})
print("Train Batch:", iteraction,"Sample:", batch_size*iteraction, "X:", X_Batch, "Y:", Y_Batch, "y_:",
predict_train, "Cost:", train_cost)
saver.save(sess, "./model.ckpt")
print('Variaveis salvas com sucesso')
coord.request_stop()
coord.join(threads)
sess.close()
print('=============================Fim do Treinamento=============================')
with tf.Session() as sess:
tf.initialize_all_variables().run()
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(coord=coord)
print("==============================VALIDAÇAO==================================")
saver.restore(sess, "./model.ckpt")
print("Model restored.")
for iteraction in range(int(eval_end/test_size)):
teX, teY = sess.run([xe, ye])
for i in range(0, test_size):
features, features_past, features_past2 = sess.run(tf.unpack(teX[i])), sess.run(tf.unpack(teX[i - 1])), sess.run(tf.unpack(teX[i-2]))
power_in_i = features[0] - 4
temperature_i = features[1]
temperature_i1 = features_past[1]
teX_now = tf.pack([power_in_i, (temperature_i - temperature_i1), (temperature_i-temperature_i2)])
teX_now = sess.run(teX_now)
X_Batch, Y_Batch = teX_now.reshape([-1, input_vec_size]), teY[i].reshape([-1, 1])
predict_eval = sess.run(tf.reshape(predict_op, [-1, 1]), feed_dict={X: X_Batch, p_keep_input: 1.0, p_keep_hidden: 1.0})
eval_cost = sess.run(cost, feed_dict={py_x: predict_eval, Y: Y_Batch})
print("Eval Batch:", iteraction,"Sample:", batch_size*iteraction, "X:", X.eval(feed_dict={X: X_Batch}), "Y:", Y_Batch, "y_:",
predict_eval, "Cost:", eval_cost)
coord.request_stop()
coord.join(threads)
sess.close()
print('=============================FIM DA VALIDAÇAO=============================')
with tf.Session() as sess:
tf.initialize_all_variables().run()
coord = tf.train.Coordinator()
threads = tf.train.start_queue_runners(coord=coord)
print("==============================PREDIÇÃO==================================")
saver.restore(sess, "./model.ckpt")
print("Model restored.")
predict_batch_mean = 0
predict_mean = 0
for iteraction in range(int(predict_end / test_size)):
tpX, tpY = sess.run([xp, yp])
for i in range(0, test_size):
features, features_past, features_past2 = sess.run(tf.unpack(tpX[i])), sess.run(tf.unpack(tpX[i - 1])), sess.run(tf.unpack(tpX[i-2]))
power_in_i = features[0]- 4
temperature_i = features[1]
temperature_i1 = features_past[1]
tpX_now = tf.pack([power_in_i, (temperature_i - temperature_i1), (temperature_i-temperature_i2)])
tpX_now = sess.run(tpX_now)
X_Batch, Y_Batch = tpX_now.reshape([-1, input_vec_size]), tpY[i].reshape([-1, 1])
prediction = sess.run(tf.reshape(predict_op, [-1, 1]), feed_dict={X: X_Batch, p_keep_input: 1.0, p_keep_hidden: 1.0})
print("Predict Batch:", iteraction,"Sample:", batch_size*iteraction, "X:", X.eval(feed_dict={X: X_Batch}), "y_:",
prediction)
predict_batch_mean = (predict_batch_mean + prediction)/i
predict_mean = (predict_mean + predict_batch_mean)/iteraction
print("Predicted Flow:", predict_mean)
coord.request_stop()
coord.join(threads)
sess.close()
My quick guess is that you are creating a lot of new nodes in each iteration through your training: those tf.packs and tf.reshapes are just making your graph bigger and bigger.
Construct the graph once outside the training loop, and I'll bet everything gets happy.
Pandas saved me this time, and im already in love with it!
After some learning, there is the working code. Now its fast, aside of the "not that good" prediction accuracy yet.
Heres the code:
import numpy as np
import pandas as pd
import tensorflow as tf
#VARIAVEIS
input_vec_size = 6
layer1_size = 512
fclayer_size = 1024
step_size = 0.02
test_size = 16
train_end = 1905
eval_end = 290
predict_end = 1396
#READS TRAIN FILE
def read_data(directory):
data=pd.read_csv(directory, sep=',',header=None)
return data
#Batch Maker
def get_batch(data, i, data_size):
j = i + (input_vec_size - 1 - data_size)*(i//(data_size - input_vec_size + 1)) + input_vec_size - 1
# print(j, i//(data_size - 5))
features = [(data[1][j] - 4) / 16,
(data[2][j] - data[2][j - 1])*10,
(data[2][j] - data[2][j - 2])*10,
(data[2][j] - data[2][j - 3])*10,
(data[2][j] - data[2][j - 4])*10,
(data[2][j] - data[2][j - 5])*10]
features = np.reshape(features, [-1, input_vec_size])
flow = data[3][j]/1500
flow = np.reshape(flow, [-1,1])
return features, flow
#Inicializaçao de variaveis
def init_weights(shape):
return tf.Variable(tf.random_normal(shape, stddev=0.001))
def init_bias(shape): #inicializa bias
initial = tf.constant(0.001, shape=shape) #variancia 0.1
return tf.Variable(initial)
#Definindo Modelo DNN
def model(X, w_h, w_h2, w_o, B, B2, p_keep_input, p_keep_hidden):
X = tf.nn.dropout(X, p_keep_input)
h = tf.nn.relu(tf.matmul(X, w_h)+B)
h = tf.nn.dropout(h, p_keep_hidden)
h2 = tf.nn.relu(tf.matmul(h, w_h2))
h2 = tf.nn.dropout(h2, p_keep_hidden)
return tf.matmul(h2, w_o)
#PLaceholders
X = tf.placeholder("float", [None, input_vec_size])
Y = tf.placeholder("float", [None, 1])
p_keep_hidden = tf.placeholder("float")
p_keep_input = tf.placeholder("float")
#Estados iniciais das variaveis
w_h = init_weights([input_vec_size, layer1_size])
w_h2= init_weights([layer1_size, fclayer_size])
w_o= init_weights([fclayer_size, 1])
B = init_bias([layer1_size])
B2 = init_bias([fclayer_size])
#Modelo
py_x = model(X, w_h, w_h2, w_o, B, B2, p_keep_input, p_keep_hidden)
#Operaçao de previsão
predict_op = tf.reshape(py_x[0], [-1,1])
#Funçao custo
cost = tf.reduce_mean(tf.square(predict_op - Y))
#Operação de treinamento
train_op = tf.train.AdadeltaOptimizer(step_size).minimize(cost)
#Utilizado para salvar as variaveis apos o treinamento
saver = tf.train.Saver()
with tf.Session() as sess:
tf.initialize_all_variables().run()
directory = '~/PycharmProjects/modelagemELT430/train/G2.csv'
data = read_data(directory)
for i in range(0, 10*(train_end - input_vec_size + 1)):
features, flow = get_batch(data, i, train_end)
# features = sess.run(features)
sess.run(train_op, feed_dict={X: features,
Y: flow, p_keep_input: 0.9, p_keep_hidden: 0.6})
predict_train = sess.run(predict_op,
feed_dict={X: features, p_keep_input: 1.0, p_keep_hidden: 1.0})
train_cost = sess.run(cost, feed_dict={py_x: predict_train, Y: flow})
print("Train Sample:", i, "X:", features, "Y:", flow*1500, "y_:",
predict_train*1500, "Cost:", train_cost)
saver.save(sess, "./model.ckpt")
print('Variaveis salvas com sucesso')
sess.close()
print('=============================Fim do Treinamento=============================')
with tf.Session() as sess:
tf.initialize_all_variables().run()
directory = '~/PycharmProjects/modelagemELT430/eval/G2E.csv'
data = read_data(directory)
print("==============================VALIDAÇAO==================================")
saver.restore(sess, "./model.ckpt")
print("Model restored.")
for i in range(0, eval_end - input_vec_size + 1):
features, flow = get_batch(data, i, eval_end)
predict_eval = sess.run(predict_op,
feed_dict={X: features, p_keep_input: 1.0, p_keep_hidden: 1.0})
eval_cost = sess.run(cost, feed_dict={py_x: predict_eval, Y: flow})
print("Eval Sample:", i, "X:", features, "Y:",flow*1500, "y_:",predict_eval*1500, "Cost:", eval_cost)
sess.close()
print('============================Fim da Validação=================================')
with tf.Session() as sess:
tf.initialize_all_variables().run()
directory = '~/PycharmProjects/modelagemELT430/predict/G2P.csv'
data = read_data(directory)
print("==============================Predição==================================")
saver.restore(sess, "./model.ckpt")
print("Model restored.")
for i in range(0, predict_end - input_vec_size + 1):
features, flow = get_batch(data, i, predict_end)
predict = sess.run(predict_op,
feed_dict={X: features, p_keep_input: 1.0, p_keep_hidden: 1.0})
eval_cost = sess.run(cost, feed_dict={py_x: predict, Y: flow})
print("Predict Sample:", i, "X:", features, "y_:",predict*1500)
sess.close()
print('============================Fim da Prediçao=================================')