deploying the Tensorflow model in Python - python

Need help in implementing the Tensorflow model in real time.
While I am training everything is working fine but when I move on for a realtime forecast or prediction, the output what I received flunked.
I do not know why is this happening.
I used the reference of teh code from here: https://www.kaggle.com/raoulma/ny-stock-price-prediction-rnn-lstm-gru/notebook
And tried to implement or deploy using the same code with few changes.
See the following code:
import numpy as np
import pandas as pd
import sklearn
import sklearn.preprocessing
import datetime
import os
import tensorflow as tf
df = pd.read_csv("Realtime_Values.csv", index_col = 0)
df.info()
def load_data(stock,seq_len):
data_raw = stock.as_matrix() # convert to numpy array
data = []
for index in range(len(data_raw) - seq_len):
data.append(data_raw[index: index + seq_len])
#print(len(data))
data = np.array(data);
x_forecast = data[:,:-1,:]
return x_forecast
def normalize_data(df):
cols = list(df.columns.values)
min_max_scaler = sklearn.preprocessing.MinMaxScaler()
df = pd.DataFrame(min_max_scaler.fit_transform(df.values))
df.columns = cols
return df
model_path ="modelsOHLC"
seq_len = 9
# parameters
n_steps = seq_len-1
n_inputs = 4
n_neurons = 100
n_outputs = 4
n_layers = 4
learning_rate = 0.01
batch_size = 10
n_epochs = 1000
tf.reset_default_graph()
X = tf.placeholder(tf.float32, [None, n_steps, n_inputs])
y = tf.placeholder(tf.float32, [None, n_outputs])
layers = [tf.contrib.rnn.BasicRNNCell(num_units=n_neurons, activation=tf.nn.elu)
for layer in range(n_layers)]
multi_layer_cell = tf.contrib.rnn.MultiRNNCell(layers)
rnn_outputs, states = tf.nn.dynamic_rnn(multi_layer_cell, X, dtype=tf.float32)
stacked_rnn_outputs = tf.reshape(rnn_outputs, [-1, n_neurons])
stacked_outputs = tf.layers.dense(stacked_rnn_outputs, n_outputs)
outputs = tf.reshape(stacked_outputs, [-1, n_steps, n_outputs])
outputs = outputs[:,n_steps-1,:] # keep only last output of sequence
loss = tf.reduce_mean(tf.square(outputs - y)) # loss function = mean squared error
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate)
training_op = optimizer.minimize(loss)
saver = tf.train.Saver()
sess =tf.Session()
sess.run(tf.global_variables_initializer())
if(tf.train.checkpoint_exists(tf.train.latest_checkpoint(model_path))):
saver.restore(sess, tf.train.latest_checkpoint(model_path))
df = normalize_data(df)
x_forecast = load_data(df,seq_len)
y_forecast_pred = sess.run(outputs, feed_dict={X: x_forecast})
print(y_forecast_pred)
Can anyone help me in getting the above code run in real time without any issues?

There is a possibility that the code failed to find the saved weights when program trains the model; thus the predictions are being generated at an untrained state. Your code for training model is:
if (tf.train.checkpoint_exists(tf.train.latest_checkpoint(model_path))):
saver.restore(sess, tf.train.latest_checkpoint(model_path))
To fix this problem:
Add a debugging code such as print("checkpoint exists!")
Place breakpoint through a debugger before or after save.restore(...) to find a checkpoint to restore from.
Look at the model_path to ensure your checkpoints are saved correctly.

Related

Tensorflow: The prediction of my model is always the same

I have trained a deep CNN that predicts a one-dimentional array and saved the weight variables in the format of .ckpt. But when I give the model new inputs, it always outputs the same array. I have already check the preprocess of the inputs and I'm sure they are alright. Here is the code of my prediction.
import pandas as pd
import numpy as np
import os
import tensorflow as tf
sess = tf.Session()
sess.run(tf.global_variables_initializer())
filename = os.listdir("D:/project/test datasets/image")
new_dir = "D:/project/test datasets/"
for img in filename:
img=os.path.splitext(img)[0]
xs = pd.read_csv(new_dir+img+'.csv',index_col=0)
xs = xs.values.flatten()
xs = np.expand_dims(xs,0)
saver = tf.train.import_meta_graph('model.ckpt.meta')
saver.restore(sess, 'model.ckpt')
graph = tf.get_default_graph()
x = graph.get_tensor_by_name("x:0")
keep_prob = graph.get_tensor_by_name("keep_prob:0")
y_conv = graph.get_tensor_by_name("y_conv:0")
print(sess.run(y_conv,feed_dict={x:xs,keep_prob:1.0}))
And I also find that when I add the code statement y_conv = tf.constant(0) in the end of the loop, the following output will all be 0, which means my prediction y_conv doesn't update in each loop.
I have no idea where is wrong. Any feedback or advice would be greatly appreciated.
Your code looks fine to me. Please can you try in the below format
with tf.Session() as sess:
saver = tf.train.import_meta_graph(savefile)
saver.restore(sess, tf.train.latest_checkpoint(savedir))
graph = tf.get_default_graph()
input_x = graph.get_tensor_by_name("input_x:0")
result = graph.get_tensor_by_name("result:0")
feed_dict = {input_x: x_data,}
predictions = result.eval(feed_dict=feed_dict)

Variables not updated after training in TensorFlow even when initiated with uniform random for a simple logistic regression

I am learning TensorFlow by implementing a simple logisitic regression classifier that outputs whether a digit is 7 or not when fed an MNIST image. I am using Stochastic gradient descent. The crux of the Tensorflow code is
# Maximum number of epochs
MaxEpochs = 1
# Learning rate
eta = 1e-2
ops.reset_default_graph()
n_x = 784
n_y = 1
x_tf = tf.placeholder(tf.float32, shape = [n_x, 1], name = 'x_tf')
y_tf = tf.placeholder(tf.float32, shape = [n_y, 1], name = 'y_tf')
w_tf = tf.get_variable(name = "w_tf", shape = [n_x, 1], initializer = tf.initializers.random_uniform());
b_tf = tf.get_variable(name = "b_tf", shape = [n_y, 1], initializer = tf.initializers.random_uniform());
z_tf = tf.add(tf.matmul(w_tf, x_tf, transpose_a = True), b_tf, name = 'z_tf')
yPred_tf = tf.sigmoid(z_tf, name = 'yPred_tf')
Loss_tf = tf.nn.sigmoid_cross_entropy_with_logits(logits = yPred_tf, labels = y_tf, name = 'Loss_tf')
with tf.name_scope('Training'):
optimizer_tf = tf.train.GradientDescentOptimizer(learning_rate = eta)
train_step = optimizer_tf.minimize(Loss_tf)
init = tf.global_variables_initializer()
with tf.Session() as sess:
sess.run(init)
for Epoch in range(MaxEpochs):
for Sample in range(len(XTrain)):
x = XTrain[Sample]
y = YTrain[Sample].reshape([-1,1])
Train_sample = {x_tf: x, y_tf: y}
sess.run(train_step, feed_dict = Train_sample)
toc = time.time()
print('\nElapsed time is: ', toc-tic,'s');
It builds the following graph (tensorboard related code has been removed for convenience):
The problem is even though the weights and biases are initialised randomly (non-zero), the neuron isn't being trained. The weight histogram is as follows.
I didnt want to post something so trivial, but I am at my wit's end. Sorry for the long post. Thank you very much in advance for any guidance. A little side note, it is taking 93.35s to run, it only took 10 or so seconds when I did this with numpy (same stochastic implementation), why would this be so?
EDIT:
The bias plot over the course of the training is as follows.
EDIT: The entire code, if the issue is cropping up on something outside what I previously thought.
import tensorflow as tf
import numpy as np
import h5py
from tensorflow.python.framework import ops
import time
mnist = tf.keras.datasets.mnist
(x_train, y_train),(x_test, y_test) = mnist.load_data()
def Flatten(Im):
FlatImArray = Im.reshape([Im.shape[0],-1,1])
return FlatImArray
DigitTested = 7
# Sperating the images with 7s from the rest
TrainIdxs = [];
for i in range(len(y_train)):
if(y_train[i] == DigitTested):
TrainIdxs.append(i)
TestIdxs = [];
for i in range(len(y_test)):
if(y_test[i] == DigitTested):
TestIdxs.append(i)
# Preparing the Datasets for training and testing
XTrain = Flatten(x_train);
YTrain = np.zeros([len(x_train),1]);
YTrain[TrainIdxs] = 1;
XTest = Flatten(x_test);
YTest = np.zeros([len(x_test),1]);
YTest[TestIdxs] = 1;
tic = time.time()
# Maximum number of epochs
MaxEpochs = 1
# Learning rate
eta = 1e-2
# Number of Epochs after which the neuron is validated
ValidationInterval = 1
ops.reset_default_graph() # to be able to rerun the model without overwriting tf variables
n_x = 784
n_y = 1
x_tf = tf.placeholder(tf.float32, shape = [n_x, 1], name = 'x_tf')
y_tf = tf.placeholder(tf.float32, shape = [n_y, 1], name = 'y_tf')
w_tf = tf.get_variable(name = "w_tf", shape = [n_x, 1], initializer = tf.initializers.random_uniform());
b_tf = tf.get_variable(name = "b_tf", shape = [n_y, 1], initializer = tf.initializers.random_uniform());
z_tf = tf.add(tf.matmul(w_tf, x_tf, transpose_a = True), b_tf, name = 'z_tf')
yPred_tf = tf.sigmoid(z_tf, name = 'yPred_tf')
Loss_tf = tf.nn.sigmoid_cross_entropy_with_logits(logits = yPred_tf, labels = y_tf, name = 'Loss_tf')
with tf.name_scope('Training'):
optimizer_tf = tf.train.GradientDescentOptimizer(learning_rate = eta)
train_step = optimizer_tf.minimize(Loss_tf)
writer = tf.summary.FileWriter(r"C:\Users\braja\Documents\TBSummaries\MNIST1NTF\2")
tf.summary.histogram('Weights', w_tf)
tf.summary.scalar('Loss', tf.reshape(Loss_tf, []))
tf.summary.scalar('Bias', tf.reshape(b_tf, []))
merged_summary = tf.summary.merge_all()
init = tf.global_variables_initializer()
with tf.Session() as sess:
sess.run(init)
for Epoch in range(MaxEpochs):
for Sample in range(len(XTrain)):
x = XTrain[Sample]
y = YTrain[Sample].reshape([-1,1])
Train_sample = {x_tf: x, y_tf: y}
MergedSumm, _ = sess.run([merged_summary, train_step], feed_dict = Train_sample)
writer.add_summary(summary = MergedSumm, global_step = Sample)
if((Epoch+1) %ValidationInterval == 0):
ValidationError = 0
for Sample in range(len(XTest)):
x = XTest[Sample]
y = YTest[Sample].reshape([-1,1])
Test_sample = {x_tf: x, y_tf: y}
yPred = sess.run(yPred_tf, feed_dict = Test_sample)
ValidationError += abs(yPred - YTest[Sample])
print('Validation Error at', Epoch+1,'Epoch:', ValidationError);
writer.add_graph(tf.Session().graph)
writer.close()
toc = time.time()
print('\nElapsed time is: ', toc-tic,'s');
Looking at the bias value it looks like you are seeing saturation of the sigmoid function.
This happens when you push your sigmoid input(z_tf) to the extreme ends of the sigmoid function. When this happens, the gradient returned is so low that the training stagnates. The probable cause of this is that it seems you have doubled up on sigmoid functions; sigmoid_cross_entropy_with_logits applies a sigmoid to its input, but you have implemented one yourself already. Try removing one of these.
In addition, by default tf.initializers.random_uniform()) produces random values between 0:1. You probably want to initialise your Weights and biases symmetrically about 0 and at really small values to start with. This can be done by passing arguments minval and maxval to tf.initializers.random_uniform().
They should grow during training and again this prevents sigmoid saturation.

How to use dataset in TensorFlow session for training

I like to perform image classification on our own large image libary (millions of labeled images) with tensorflow. I´m new to stackoverflow, python and tensorflow and worked myself through a few tutorials (mnist etc.) and got to the point, where i was able to prepare a TensorFlow datset from a dictionary including the absolute path to the images and the according labels. However, i´m stuck at the point using the dataset in a TensorFlow session. Here is my (example) code:
from __future__ import absolute_import
from __future__ import division
from __future__ import print_function
import tensorflow as tf
import numpy as np
import time
import mymodule # I build my module to read the images and labels
from tensorflow.python.framework import ops
from tensorflow.python.framework import dtypes
from tensorflow.contrib.data import Iterator
beginTime = time.time()
batch_size = 100
learning_rate = 0.005
max_steps = 2
NUM_CLASSES = 25
def input_parser(img_path, label):
one_hot = tf.one_hot(label, NUM_CLASSES)
img_file = tf.read_file(img_path)
img_decoded = tf.image.decode_jpeg(img_file, channels = 3)
return img_decoded, one_hot
#Import Training data (returns the dicitonary with paths and labels)
train_dict = mymodule.getFileMap(labelList, imageList)
#Import Test data
test_dict = mymodule.getFileMap(labelList, imageList)
#Get train data
train_file_list, train_label_list = get_file_label_list(train_dict)
train_images_tensor = ops.convert_to_tensor(train_file_list, dtype=dtypes.string)
train_labels_tensor = ops.convert_to_tensor(train_label_list, dtype=dtypes.int64)
#Get test data
test_file_list, test_label_list = get_file_label_list(test_dict)
test_images_tensor = ops.convert_to_tensor(test_file_list, dtype=dtypes.string)
test_labels_tensor = ops.convert_to_tensor(test_label_list, dtype=dtypes.int64)
#Create TensorFlow Datset object
train_data = tf.data.Dataset.from_tensor_slices((train_images_tensor, train_labels_tensor))
test_data = tf.data.Dataset.from_tensor_slices((test_images_tensor, test_labels_tensor))
# Transform the datset so that it contains decoded images
# and one-hot vector labels
train_data = train_data.map(input_parser)
test_data = test_data.map(input_parser)
# Batching --> How to do it right?
#train_data = train_data.batch(batch_size = 100)
#test_data = train_data.batch(batch_size = 100)
#Define input placeholders
image_size = 990*990*3
images_placeholder = tf.placeholder(tf.float32, shape=[None, image_size])
labels_placeholder = tf.placeholder(tf.int64, shape=[None])
# Define variables (these afe the values we want to optimize)
weigths = tf.Variable(tf.zeros([image_size, NUM_CLASSES]))
biases = tf.Variable(tf.zeros([NUM_CLASSES]))
# Define the classifier´s result
logits = tf.matmul(images_placeholder, weigths) + biases
# Define the loss function
loss = tf.reduce_mean(tf.nn.sparse_softmax_cross_entropy_with_logits(logits = logits, labels = labels_placeholder))
# Define the training operation
train_step = tf.train.GradientDescentOptimizer(learning_rate).minimize(loss)
# Operation comparing prediciton with true label
correct_prediciton = tf.equal(tf.argmax(logits, 1), labels_placeholder)
# Operation calculating the accuracy of our predicitons
accuracy = tf.reduce_mean(tf.cast(correct_prediciton, tf.float32))
#Create TensorFlow Iterator object
iterator = Iterator.from_structure(train_data.output_types,
train_data.output_shapes)
next_element = iterator.get_next()
#Create two initialization ops to switch between the datasets
train_init_op = iterator.make_initializer(train_data)
test_init_op = iterator.make_initializer(test_data)
with tf.Session() as sess:
#Initialize variables
sess.run(tf.global_variables_initializer())
sess.run(train_init_op)
for _ in range(10):
try:
elem = sess.run(next_element)
print(elem)
except tf.errors.OutOfRangeError:
print("End of training datset.")
break
Following this and this tutorial i could not solve the problem of how to use the (image and label) dataset in a tensorflow session for training. I was able to print out the datset by iterating through it, but wasn´t able to use it for learning.
I don´t understand how to access the images and labels seperately after they have been merged in the train_data = tf.data.Dataset.from_tensor_slices((train_images_tensor, train_labels_tensor)) operation, as requried by the 2nd tutorial. Also i don´t know how to implement batching correctly.
What i want to do in the session is basically this (from the 2nd tutorial):
# Generate input data batch
indices = np.random.choice(data_sets['images_train'].shape[0], batch_size)
images_batch = data_sets['images_train'][indices]
labels_batch = data_sets['labels_train'][indices]
# Periodically print out the model's current accuracy
if i % 100 == 0:
train_accuracy = sess.run(accuracy, feed_dict={
images_placeholder: images_batch, labels_placeholder: labels_batch})
print('Step {:5d}: training accuracy {:g}'.format(i, train_accuracy))
# Perform a single training step
sess.run(train_step, feed_dict={images_placeholder: images_batch,
labels_placeholder: labels_batch})
# After finishing the training, evaluate on the test set
test_accuracy = sess.run(accuracy, feed_dict={
images_placeholder: data_sets['images_test'],
labels_placeholder: data_sets['labels_test']})
print('Test accuracy {:g}'.format(test_accuracy))
endTime = time.time()
print('Total time: {:5.2f}s'.format(endTime - beginTime))
If anyone can tell me, how to access images and labels in the dataset sepearately and use it for training, i would be really thankful. Also a tip where and how to do the batching would be appreciated.
Thank you.
In your code, next_element is a tuple of two tensors, matching the structure of your datasets: i.e. it is a tuple whose first element is an image, and second element is a label. To access the individual tensors, you can do the following:
next_element = iterator.get_next()
next_image = next_element[0]
next_label = next_element[1]
# Or, in a single line:
next_image, next_label = iterator.get_next()
To batch a tf.data.Dataset, you can use the Dataset.batch() transformation. Your commented out code for this should simply work:
train_data = train_data.batch(batch_size = 100)
test_data = train_data.batch(batch_size = 100)

Tensorflow dimensionality issue with reshape

I have created this code but I am stuck with a dimensionality error
import pandas as pd
import matplotlib.pyplot as plt
import numpy as np
import tensorflow as tf
from tensorflow.contrib.rnn.python.ops import rnn_cell, rnn
from time import time
# 2) Import MNIST data http://yann.lecun.com/exdb/mnist/
from tensorflow.examples.tutorials.mnist import input_data
mnist = input_data.read_data_sets("MNIST_data/", one_hot=True)
x_train = mnist.train.images
# Define the appropriate model and variables (USER INPUTS)
batch = 100 # Define the size of the batch
units = 32 # Number of units of each network
recurrent_layers = 1 # Number of layers
nnclasses = 10 # MNIST classes (0-9)
steps = x_train.shape[1] # 784
feed = 1 # Number of pixels to be fed into the model
recurrent_layers = 1 # Define the size of the recurrent layers
dropout = 1 #
x = tf.placeholder(tf.float32,[None, None]) # batch(100)x784
x_resh = tf.reshape(x,[-1,steps,1]) # (100, 784, 1)
keep_prob = tf.placeholder(tf.float32,shape=[])
def weight_variable(shape):
initial = tf.truncated_normal(shape, stddev=0.1)
return tf.Variable(initial)
w_fc = weight_variable([units, nnclasses])
cell = tf.contrib.rnn.GRUCell(units)
cell = tf.contrib.rnn.DropoutWrapper(cell, input_keep_prob = keep_prob)
cell = tf.contrib.rnn.MultiRNNCell([cell] * recurrent_layers)
cell = tf.contrib.rnn.DropoutWrapper(cell, output_keep_prob = keep_prob)
outputs, final_state = tf.nn.dynamic_rnn(cell, x_resh, dtype=tf.float32)
output = outputs[:,:-1, :]
logits = tf.matmul(tf.reshape(output,[-1,tf.shape(w_fc)[0]]), w_fc) # [78300, 10]
y = tf.reshape(x[:,1:], [-1, nnclasses]) # [7830, 10]
K = [tf.shape(y)[0], tf.shape(logits)[0]]
sess = tf.InteractiveSession()
sess.run(tf.global_variables_initializer())
def binarize(images, threshold=0.1):
return (threshold < images).astype('float32')
batch_x, _ = mnist.train.next_batch(batch)
batch_x = binarize(batch_x, threshold=0.1)
return = sess.run(K, feed_dict={x: batch_x, keep_prob: 1.0})
Which returns [7830, 78300]. The issue is these two numbers should have been the same. They are the rows of y and logits, and if they are not similar I cannot compare them in a cross entropy setting. Can someone please let me know where the process is wrong? Actually, the (y) should return [78300, 10] but I do not know why.
y = tf.reshape(x[:,1:], [-1, nnclasses]) # [7830, 10]
Your x tensor is of shape batch(100)x784, so x[:1,:] is 100x783. This is a total of 78,300 elements. 78300x10 would be 783,000, you simply don't have enough data in x to make it that shape.
Do you mean to use logits as a parameter of y? Assuming y is your output, using x as a param means you've bypassed the entire network.

Basic Tensorflow Example - Prediction of a Line

I'm trying to create this super simple example with Tensorflow and I clearly don't fully understand the API for Tensorflow.
I have the following code. It's not mine originally - I found it from some demo, but I can't remember where I found it, or else I would give the author credit. Apologies.
Saving the Trained Line Model
import tensorflow as tf
import numpy as np
# Create 100 phony x, y data points in NumPy, y = x * 0.1 + 0.3
x_data = np.random.rand(100).astype(np.float32)
y_data = x_data * 0.1 + 0.3
# Try to find values for W and b that compute y_data = W * x_data + b
W = tf.Variable(tf.random_uniform([1], -1.0, 1.0), name='W')
b = tf.Variable(tf.zeros([1]), name='b')
y = W * x_data + b
# Minimize the mean squared errors.
loss = tf.reduce_mean(tf.square(y - y_data))
optimizer = tf.train.GradientDescentOptimizer(0.5)
train = optimizer.minimize(loss)
# Before starting, initialize the variables. We will 'run' this first.
init = tf.global_variables_initializer()
# Create a session saver
saver = tf.train.Saver()
# Launch the graph.
sess = tf.Session()
sess.run(init)
# Fit the line.
for step in range(201):
sess.run(train)
if step % 20 == 0:
print(step, sess.run(W), sess.run(b))
saver.save(sess, 'linemodel')
Ok that's all fine. I just want to load in the model and then query my model to get a predicted value. Here is my attempted code:
Loading and Querying the Trained Line Model
# This is going to load the line model
import tensorflow as tf
sess = tf.Session()
new_saver = tf.train.import_meta_graph('linemodel.meta')
new_saver.restore(sess, tf.train.latest_checkpoint('./')) # latest checkpoint
all_vars = tf.global_variables()
for v in all_vars:
v_ = sess.run(v)
print("This is {} with value: {}".format(v.name, v_))
# this works
# None of the below works
# Tried this as well
#fetches = {
# "input": tf.constant(10, name='input')
#}
#feed_dict = {"input": tf.constant(10, name='input')}
#vals = sess.run(fetches, feed_dict = feed_dict)
# Tried this and it didn't work
# query_value = tf.constant(10, name='query')
# print(sess.run(query_value))
This is a really basic question, but how can I just pass in a value and use my line almost like a function. Do I need to change the way the line model is being constructed? My guess is that the computation graph is not set up where the output is an actual variable that we can get. Is this correct? If so, how should I modify this program?
You have to create tensorflow graph again and load saved weights into it. I added couple of lines to your code and it gives desired outputs. Please check it.
import tensorflow as tf
import numpy as np
sess = tf.Session()
new_saver = tf.train.import_meta_graph('linemodel.meta')
new_saver.restore(sess, tf.train.latest_checkpoint('./')) # latest checkpoint
all_vars = tf.global_variables()
# load saved weights into new variables
W = all_vars[0]
b = all_vars[1]
# build TF graph
x = tf.placeholder(tf.float32)
y = tf.add(tf.multiply(W,x),b)
# Session
init = tf.global_variables_initializer()
print(sess.run(all_vars))
sess.run(init)
for i in range(2):
x_ip = np.random.rand(10).astype(np.float32) # batch_size : 10
vals = sess.run(y,feed_dict={x:x_ip})
print vals
Output:
[array([ 0.1000001], dtype=float32), array([ 0.29999995], dtype=float32)]
[-0.21707924 -0.18646611 -0.00732027 -0.14248954 -0.54388255 -0.33952206 -0.34291503 -0.54771954 -0.60995424 -0.91694558]
[-0.45050886 -0.01207681 -0.38950539 -0.25888413 -0.0103816 -0.10003483 -0.04783082 -0.83299863 -0.53189355 -0.56571382]
I hope this helps.

Categories