If you have been following Data Science / Machine Learning, you just can’t miss the buzz around Deep Learning and Neural Networks. Organizations are looking for people with Deep Learning skills wherever they can. From running competitions to open sourcing projects and paying big bonuses, people are trying every possible thing to tap into this limited pool of talent.
Self driving engineers are being hunted by the big guns in automobile industry, as the industry stands on the brink of biggest disruption it faced in last few decades!
If you are excited by the prospects deep learning has to offer, but have not started your journey yet – I am here to enable it. Starting with this article, I will write a series of articles on deep learning covering the popular Deep Learning libraries and their hands-on implementation.
In this article, I will introduce TensorFlow to you. After reading this article you will be able to understand application of neural networks and use TensorFlow to solve a real life problem. This article will require you to know the basics of neural networks and have familiarity with programming. Although the code in this article is in python, I have focused on the concepts and stayed as language-agnostic as possible.
Let’s get started!
Neural Networks have been in the spotlight for quite some time now. For a more detailed explanation on neural network and deep learning read here. Its “deeper” versions are making tremendous breakthroughs in many fields such as image recognition, speech and natural language processing etc.
The main question that arises is when to and when not to apply neural networks? This field is like a gold mine right now, with many discoveries uncovered everyday. And to be a part of this “gold rush”, you have to keep a few things in mind:
Neural networks is a special type of machine learning (ML) algorithm. So as every ML algorithm, it follows the usual ML workflow of data preprocessing, model building and model evaluation. For the sake of conciseness, I have listed out a TO DO list of how to approach a Neural Network problem.
For this article, I will be focusing on image data. So let us understand that first before we delve into TensorFlow.
Images are mostly arranged as 3-D arrays, with the dimensions referring to height, width and color channel. For example, if you take a screenshot of your PC at this moment, it would be first convert into a 3-D array and then compress it ‘.jpeg’ or ‘.png’ file formats.
While these images are pretty easy to understand to a human, a computer has a hard time to understand them. This phenomenon is called “Semantic gap”. Our brain can look at the image and understand the complete picture in a few seconds. On the other hand, computer sees image as just an array of numbers. So the problem is how to we explain this image to the machine?
In early days, people tried to break down the image into “understandable” format for the machine like a “template”. For example, a face always has a specific structure which is somewhat preserved in every human, such as the position of eyes, nose or the shape of our face. But this method would be tedious, because when the number of objects to recognise would increase, the “templates” would not hold.
Fast forward to 2012, a deep neural network architecture won the ImageNet challenge, a prestigious challenge to recognise objects from natural scenes. It continued to reign its sovereignty in all the upcoming ImageNet challenges, thus proving the usefulness to solve image problems.
So which library / language do people normally use to solve image recognition problems? One recent survey I did that most of the popular deep learning libraries have interface for Python, followed by Lua, Java and Matlab. The most popular libraries, to name a few, are:
Now, that you understand how an image is stored and which are the common libraries used, let us look at what TensorFlow has to offer.
Lets start with the official definition,
“TensorFlow is an open source software library for numerical computation using dataflow graphs. Nodes in the graph represents mathematical operations, while graph edges represent multi-dimensional data arrays (aka tensors) communicated between them. The flexible architecture allows you to deploy computation to one or more CPUs or GPUs in a desktop, server, or mobile device with a single API.”
If that sounds a bit scary – don’t worry. Here is my simple definition – look at TensorFlow as nothing but numpy with a twist. If you have worked on numpy before, understanding TensorFlow will be a piece of cake! A major difference between numpy and TensorFlow is that TensorFlow follows a lazy programming paradigm. It first builds a graph of all the operation to be done, and then when a “session” is called, it “runs” the graph. It’s built to be scalable, by changing internal data representation to tensors (aka multi-dimensional arrays). Building a computational graph can be considered as the main ingredient of TensorFlow. To know more about mathematical constitution of a computational graph, read this article.
It’s easy to classify TensorFlow as a neural network library, but it’s not just that. Yes, it was designed to be a powerful neural network library. But it has the power to do much more than that. You can build other machine learning algorithms on it such as decision trees or k-Nearest Neighbors. You can literally do everything you normally would do in numpy! It’s aptly called “numpy on steroids”
The advantages of using TensorFlow are:
Every library has its own “implementation details”, i.e. a way to write which follows its coding paradigm. For example, when implementing scikit-learn, you first create object of the desired algorithm, then build a model on train and get predictions on test set, something like this:
# define hyperparamters of ML algorithm clf = svm.SVC(gamma=0.001, C=100.) # train clf.fit(X, y) # test clf.predict(X_test)
As I said earlier, TensorFlow follows a lazy approach. The usual workflow of running a program in TensorFlow is as follows:
Few terminologies used in TensoFlow;
placeholder: A way to feed data into the graphs
feed_dict: A dictionary to pass numeric values to computational graph
Lets write a small program to add two numbers!
# import tensorflow import tensorflow as tf # build computational graph a = tf.placeholder(tf.int16) b = tf.placeholder(tf.int16) addition = tf.add(a, b) # initialize variables init = tf.initialize_all_variables() # create session and run the graph with tf.Session() as sess: sess.run(init) print "Addition: %i" % sess.run(addition, feed_dict={a: 2, b: 3}) # close session sess.close()
Note: We could have used a different neural network architecture to solve this problem, but for the sake of simplicity, we settle on feed forward multilayer perceptron with an in depth implementation.
Let us remember what we learned about neural networks first.
A typical implementation of Neural Network would be as follows:
Here we solve our deep learning practice problem – Identify the Digits. Let’s for a moment take a look at our problem statement.
Our problem is an image recognition, to identify digits from a given 28 x 28 image. We have a subset of images for training and the rest for testing our model. So first, download the train and test files. The dataset contains a zipped file of all the images in the dataset and both the train.csv and test.csv have the name of corresponding train and test images. Any additional features are not provided in the datasets, just the raw images are provided in ‘.png’ format.
As you know we will use TensorFlow to make a neural network model. So you should first install TensorFlow in your system. Refer the official installation guide for installation, as per your system specifications.
We will follow the template as described above. Create a Jupyter notebook with python 2.7 kernel and follow the steps below.
%pylab inline import os import numpy as np import pandas as pd from scipy.misc import imread from sklearn.metrics import accuracy_score import tensorflow as tf
# To stop potential randomness seed = 128 rng = np.random.RandomState(seed)
root_dir = os.path.abspath('../..') data_dir = os.path.join(root_dir, 'data') sub_dir = os.path.join(root_dir, 'sub') # check for existence os.path.exists(root_dir) os.path.exists(data_dir) os.path.exists(sub_dir)
train = pd.read_csv(os.path.join(data_dir, 'Train', 'train.csv')) test = pd.read_csv(os.path.join(data_dir, 'Test.csv')) sample_submission = pd.read_csv(os.path.join(data_dir, 'Sample_Submission.csv')) train.head()
filename | label | |
---|---|---|
0 | 0.png | 4 |
1 | 1.png | 9 |
2 | 2.png | 1 |
3 | 3.png | 7 |
4 | 4.png | 3 |
img_name = rng.choice(train.filename) filepath = os.path.join(data_dir, 'Train', 'Images', 'train', img_name) img = imread(filepath, flatten=True) pylab.imshow(img, cmap='gray') pylab.axis('off') pylab.show()
The above image is represented as numpy array, as seen below
temp = [] for img_name in train.filename: image_path = os.path.join(data_dir, 'Train', 'Images', 'train', img_name) img = imread(image_path, flatten=True) img = img.astype('float32') temp.append(img) train_x = np.stack(temp) temp = [] for img_name in test.filename: image_path = os.path.join(data_dir, 'Train', 'Images', 'test', img_name) img = imread(image_path, flatten=True) img = img.astype('float32') temp.append(img) test_x = np.stack(temp)
split_size = int(train_x.shape[0]*0.7) train_x, val_x = train_x[:split_size], train_x[split_size:] train_y, val_y = train.label.values[:split_size], train.label.values[split_size:]
def dense_to_one_hot(labels_dense, num_classes=10): """Convert class labels from scalars to one-hot vectors""" num_labels = labels_dense.shape[0] index_offset = np.arange(num_labels) * num_classes labels_one_hot = np.zeros((num_labels, num_classes)) labels_one_hot.flat[index_offset + labels_dense.ravel()] = 1 return labels_one_hot def preproc(unclean_batch_x): """Convert values to range 0-1""" temp_batch = unclean_batch_x / unclean_batch_x.max() return temp_batch def batch_creator(batch_size, dataset_length, dataset_name): """Create batch with random samples and return appropriate format""" batch_mask = rng.choice(dataset_length, batch_size) batch_x = eval(dataset_name + '_x')[[batch_mask]].reshape(-1, input_num_units) batch_x = preproc(batch_x) if dataset_name == 'train': batch_y = eval(dataset_name).ix[batch_mask, 'label'].values batch_y = dense_to_one_hot(batch_y) return batch_x, batch_y
### set all variables # number of neurons in each layer input_num_units = 28*28 hidden_num_units = 500 output_num_units = 10 # define placeholders x = tf.placeholder(tf.float32, [None, input_num_units]) y = tf.placeholder(tf.float32, [None, output_num_units]) # set remaining variables epochs = 5 batch_size = 128 learning_rate = 0.01 ### define weights and biases of the neural network (refer this article if you don't understand the terminologies) weights = { 'hidden': tf.Variable(tf.random_normal([input_num_units, hidden_num_units], seed=seed)), 'output': tf.Variable(tf.random_normal([hidden_num_units, output_num_units], seed=seed)) } biases = { 'hidden': tf.Variable(tf.random_normal([hidden_num_units], seed=seed)), 'output': tf.Variable(tf.random_normal([output_num_units], seed=seed)) }
hidden_layer = tf.add(tf.matmul(x, weights['hidden']), biases['hidden']) hidden_layer = tf.nn.relu(hidden_layer) output_layer = tf.matmul(hidden_layer, weights['output']) + biases['output']
cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(output_layer, y))
optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost)
init = tf.initialize_all_variables()
with tf.Session() as sess: # create initialized variables sess.run(init) ### for each epoch, do: ### for each batch, do: ### create pre-processed batch ### run optimizer by feeding batch ### find cost and reiterate to minimize for epoch in range(epochs): avg_cost = 0 total_batch = int(train.shape[0]/batch_size) for i in range(total_batch): batch_x, batch_y = batch_creator(batch_size, train_x.shape[0], 'train') _, c = sess.run([optimizer, cost], feed_dict = {x: batch_x, y: batch_y}) avg_cost += c / total_batch print "Epoch:", (epoch+1), "cost =", "{:.5f}".format(avg_cost) print "\nTraining complete!" # find predictions on val set pred_temp = tf.equal(tf.argmax(output_layer, 1), tf.argmax(y, 1)) accuracy = tf.reduce_mean(tf.cast(pred_temp, "float")) print "Validation Accuracy:", accuracy.eval({x: val_x.reshape(-1, input_num_units), y: dense_to_one_hot(val_y)}) predict = tf.argmax(output_layer, 1) pred = predict.eval({x: test_x.reshape(-1, input_num_units)})
This will be the output of the above code
Epoch: 1 cost = 8.93566 Epoch: 2 cost = 1.82103 Epoch: 3 cost = 0.98648 Epoch: 4 cost = 0.57141 Epoch: 5 cost = 0.44550 Training complete! Validation Accuracy: 0.952823
img_name = rng.choice(test.filename) filepath = os.path.join(data_dir, 'Train', 'Images', 'test', img_name) img = imread(filepath, flatten=True) test_index = int(img_name.split('.')[0]) - 49000 print "Prediction is: ", pred[test_index] pylab.imshow(img, cmap='gray') pylab.axis('off') pylab.show()
Prediction is: 8
sample_submission.filename = test.filename sample_submission.label = pred sample_submission.to_csv(os.path.join(sub_dir, 'sub01.csv'), index=False)
And done! We just created our own trained neural network!
Most of the above mentioned are in the sights of TensorFlow developers. They have made a roadmap for specifying how the library should be developed in the future.
TensorFlow is built on similar principles as Theano and Torch of using mathematical computational graphs. But with the additional support of distributed computing, TensorFlow comes out to be better at solving complex problems. Also deployment of TensorFlow models is already supported which makes it easier to use for industrial purposes, giving a fight to commercial libraries such as Deeplearning4j, H2O and Turi. TensorFlow has APIs for Python, C++ and Matlab. There’s also a recent surge for support for other languages such as Ruby and R. So, TensorFlow is trying to have a universal language support.
So you saw how to build a simple neural network with TensorFlow. This code is meant for people to understand how to get started implementing TensorFlow, so take it with a pinch of salt. Remember that to solve more complex real life problems, you have to tweak the code a little bit.
Many of the above functions can be abstracted to give a seamless end-to-end workflow. If you have worked with scikit-learn, you might know how a high level library abstracts “under the hood” implementations to give end-users a more easier interface. Although TensorFlow has most of the implementations already abstracted, high level libraries are emerging such as TF-slim and TFlearn.
I hope you found this article helpful. Now, it’s time for you to practice and read as much as you can. Good luck! If you follow a different approach / package / library to get started with Neural Networks, I’d love to interact with you in comments. If you have any more suggestions, drop in your comments below. And to gain expertise in working in neural network don’t forget to try out our deep learning practice problem – Identify the Digits.
Lorem ipsum dolor sit amet, consectetur adipiscing elit,
Hi Faizan, I'm new to deep learning and really appreciate your effort for sharing this article. I've downloaded the mnist dataset you used in this tutorial. There are 4 .gz files only, so I can't understand that how to have the Train.csv, Test.csv and Sample_Submission.csv. Please help advise me more, thanks.
Hi Jerry! Thanks for reading the article. This article is released as a solution to our practice problem "Identify the Digits". So the datasets (Train.csv, Test.csv) belong to that (https://datahack.analyticsvidhya.com/contest/practice-problem-identify-the-digits/). Download the datasets from there. Thanks!
Hi... I am having problem in reading Train and Test CSV files. I am unable to program it properly. I have the files located at E:\AV\TensorFlow\Test.csv and I want the above code to read this path. How do I set the path in the code above. Please help.
Hello Pmitra, There are three main directory paths to specified in the code, * root_dir : This is the main directory in which all your codes and datasets are situated * data_dir : This is where your csv files and images are * sub_dir : This is where the submission you create are stored The structure would look similar to this: root_dir | |-----data_dir |-----| |-----|-----Train |-----|-----| |-----|-----|----- |-----|-----Test.csv |-----sub_dir There are checks provided in the code to check whether you have loaded the correct paths. Having said that, the code provided is for your ease, and you could easily modify it for your purposes. For example, you could set directory paths as: root_dir = "E:\AV\TensorFlow" data_dir = "E:\AV\TensorFlow\data" sub_dir = "E:\AV\TensorFlow\sub" If you have any more problems, feel free to ask!
Hi Fazan, thanks for the really good tutorial. I'm usually work with R and Weka and I am very interested to have a better knowledge of tensorflow. I've had only the need to change two lines in your code to make it works for me: from: index_offset = numpy.arange(num_labels) * num_classes labels_one_hot = numpy.zeros((num_labels, num_classes)) to index_offset = np.arange(num_labels) * num_classes labels_one_hot = np.zeros((num_labels, num_classes)) Thanks again Mino
Updated the code. Thanks for notifying!
Train csv file zip is giving error . kindly check the file plz. Error msg "error occured while loading the zip" https://datahack.analyticsvidhya.com/contest/practice-problem-identify-the-digits/media/train_file/Train_HI6auGp.zip
Hi sahu, the download works fine for me. Could you redownload and try again?
GUI interface of ubuntu was unable to extract the file so i use CLI and solved it. Method 1 But my problem did not end here. %pylab inline is causing error and its showing unresolved reference in my case. I have created tensor flow virtual environment for running this code but its not resolving. method 2 I tried to run the code with ipython and all the dependencies installed but here error is occurring at while checking directories. Please guide me regarding it.
The code is designed to be run on an ipython notebook. Running magic functions (for example %pylab inline) would not work on CLI. For issues with checking directories, refer the comments above.
Hi Faizan, It was great article. Got a so much help and I am new in deep learning. I have a problem with "preproc" method. Why do we need this method and why the value of seed and batch_size is 128. It will be great help for getting an answer. Thanks.
Hey Sumit, I'm glad you like it. The "preproc" method in simple words, is a data preprocessing step in which we do standardization (explained in detail here https://demo3.aifest.org/blog/2016/07/practical-guide-data-preprocessing-python-scikit-learn/) If you preprocess the data before sending it to the network, it helps in training (i.e. neural network converges faster) For batch_size and seed value, they can be set as per your choice. In fact, I would suggest you to try changing the values to see what happens. Let me know if you need more help
predict = tf.argmax(output_layer, 1) pred = predict.eval({x: test.reshape(-1, 784)}) " Cannot evaluate tensor using `eval()`: No default session is registered. Use `with sess.as_default()` or pass an explicit session to `eval(session=sess)`" why this error is showing?
Have you kept the code in the same level of indentation? with tf.Session() as sess: (indent) ... (indent) ... (indent) ... (indent) predict = tf.argmax(output_layer, 1) (indent) pred = predict.eval({x: test_x.reshape(-1, 784)})
Hi Faizan, Nice article! A stupid question perhaps: I see that you save the prediction results in submission.csv. Is there a way to save the trained network itself (as a config perhaps) so I can use it for subsequent runs without having to retrain the network ? Thanks!
Thanks Anand. Actually that's a good question. The answer is Yes, you can save all the individual weights and biases of a neural network in Tensorflow. There's a function included called train.Saver() which does exactly this for you. Refer here (https://www.tensorflow.org/api_docs/python/state_ops/saving_and_restoring_variables)
Dear SIr, Thanks For your guide, I have tried to modify the code by myself in order to input a matrix that have a different size, And it turns out that this part of the code is not functioning: print "Validation Accuracy:", accuracy.eval({x: val_x.reshape(-1, 841), y:dense_to_one_hot(val_y)}) with the error message ValueError: Cannot feed value of shape (60, 841) for Tensor u'Placeholder_1:0', which has shape '(?, 200)' At the moment, I feel that I don't understand how this accuracy.eval works, Can you please explain more about it? Thank You.
Hey! Its great that you've tried to modify the code to meet your needs. Could you specify which parts you changed? There might be something you've left that's causing the problem. (PS: posting your code here http://nbviewer.jupyter.org/ would be a good choice.) Anyways, so I would describe "eval" method similar to "run" method. viz to compile a computational graph and pass values through it. Here accuracy.eval passes our input feed val_x and val_y through the "accuracy" graph (specified as >>> accuracy = tf.reduce_mean(tf.cast(pred_temp, "float")) ). The main difference between run and eval is that run is a lazy evaluation method, whereas eval does it as soon as it is called. Hope it helps. If there's anything you would like to clarify, feel free to comment here
hi Faizan, really good guide. but i try to execute the code with some changes: i.e: resize the images to 28*28 : temp = [] with open('train.csv') as trainFile: readCSV = csv.reader(trainFile, delimiter=',') for row in readCSV: if (row[0] != 'filename' and row[1] != 'label' ): image_path = os.path.join(data_dir + '/' + row[1], row[0]) img = imread(image_path, flatten=True) img.resize(size, refcheck=False) img = img.astype('float32') temp.append(img) train_x = np.stack(temp) and changed the num of classes to be 50 (as the letters and the signs i have to recognize). i changed also this: input_num_units = 28*28 hidden_num_units = 500 output_num_units = 50 epochs = 5 batch_size = 60 learning_rate = 0.01 and every time i run the code the accuracy is 0. could you help me with that ? :) do you have an idea why? and another qouestion is what is the meaning of seed ? thank you in advance
Hi Igor, Make sure are vectorizing your output (aka train_y). In the article, the function "dense_to_one_hot" does this for you
Hi Fizan, I applied your code into my dataset. My train set has 112 images and 8 labels. size of image is 128*128. And I only train with single layer (not use multilayer as your above code). My problem as below Epoch: 1 cost = 0.00000 Epoch: 2 cost = 0.00000 Epoch: 3 cost = 0.00000 Epoch: 4 cost = 0.00000 Epoch: 5 cost = 0.00000 My code: from collections import Counter import os import numpy as np import pandas as pd from scipy.misc import imread import tensorflow as tf import cv2 seed = 128 rng = np.random.RandomState(seed) root_dir = "/home/trantrunghieu/lv" train = pd.read_csv(os.path.join(root_dir,"train", 'train.csv')) test = pd.read_csv(os.path.join(root_dir,"test",'test.csv')) # sample_submission = pd.read_csv(os.path.join(data_dir, 'Sample_Submission.csv')) train.head() temp = [] for img_name in train.filename: image_path = os.path.join(root_dir, 'train', img_name) img = imread(image_path) img = img.astype('float32') img = tf.reshape(img,[-1]) temp.append(img) train_x = np.stack(temp) for img_name in test.filename: image_path = os.path.join(root_dir, 'test', img_name) img = imread(image_path) img = img.astype('float32') img = tf.reshape(img,[-1]) temp.append(img) test_x = np.stack(temp) # take a split size of 70:30 for train set vs validation set split_size = int(train_x.shape[0]*0.7) train_y = train.label.values[0:] # train_x, val_x = train_x[:split_size], train_x[split_size:] # train_y, val_y = train.label.values[:split_size], train.label.values[split_size:] print(train_y) print (Counter(train_y)) # Define some function def dense_to_one_hot(labels_dense, num_classes=8): """Convert class labels from scalars to one-hot vectors""" num_labels = labels_dense.shape[0] index_offset = np.arange(num_labels) * num_classes labels_one_hot = np.zeros((num_labels, num_classes)) labels_one_hot.flat[index_offset + labels_dense.ravel()] = 1 return labels_one_hot def preproc(unclean_batch_x): """Convert values to range 0-1""" temp_batch = unclean_batch_x / unclean_batch_x.max() return temp_batch def batch_creator(batch_size, dataset_length, dataset_name): """Create batch with random samples and return appropriate format""" batch_mask = rng.choice(dataset_length, batch_size) batch_x = eval(dataset_name + '_x')[[batch_mask]].reshape(-1, input_num_units) batch_x = preproc(batch_x) if dataset_name == 'train': batch_y = eval(dataset_name).ix[batch_mask, 'label'].values batch_y = dense_to_one_hot(batch_y) return batch_x, batch_y input_num_units = 128*128 output_num_units = 8 # define placeholders # placeholder of image x = tf.placeholder(tf.float32, [None, input_num_units]) # placeholder of label y = tf.placeholder(tf.float32, [None, output_num_units]) # set remaining variables epochs = 5 batch_size = 128 learning_rate = 0.01 # Create the model # Weight W = tf.Variable(tf.zeros([input_num_units, output_num_units])) # bias b = tf.Variable(tf.zeros([output_num_units])) output_layer = tf.matmul(x, W) + b cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(output_layer, y)) optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost) init = tf.global_variables_initializer() with tf.Session() as sess: # create initialized variables sess.run(init) for epoch in range(epochs): avg_cost = 0 total_batch = int(train.shape[0]/batch_size) for i in range(total_batch): batch_x, batch_y = batch_creator(batch_size, train_x.shape[0], 'train') _, c = sess.run([optimizer, cost], feed_dict = {x: batch_x, y: batch_y}) avg_cost += c / total_batch # if epoch % 200 ==0: print "Epoch:", (epoch+1), "cost =", "{:.5f}".format(avg_cost) print "\nTraining complete!" Could you help me with this problem? And How is batch_size value assigned? Is it dependent anything? Thank you in advance
I fixed above problem. Cause is that my dataset length is 112 less than batch_size is 128. So total_batch is always 0. But, When I change batch_size to a number less than dataset length( such as 8), a new error appeard as below: Traceback (most recent call last): File "draw_shape.py", line 124, in batch_x, batch_y = batch_creator(batch_size, train_x.shape[0], 'train') File "draw_shape.py", line 71, in batch_creator batch_x = eval(dataset_name + '_x')[[batch_mask]].reshape(-1, input_num_units) ValueError: total size of new array must be unchanged Please help me to fix this prolem.
Hey can you print the shape of batch_mask variable and check if its not zero?
I use tensorflow for the Review and Rating and get only 60% accuracy.I have a data of size 5000 and vary hidden layer from100-1000 and iteration 10000-100000.so how can i improve the accuracy with this data ??
You can try using a better architecture than MLP, for example, you can use RNN if the review data is textual sentences. I have discussed some of these tweaks in this article: https://demo3.aifest.org/blog/2016/10/tutorial-optimizing-neural-networks-using-keras-with-image-recognition-case-study/
1. Why biases don't have their own weights? 2. hidden_layer = tf.add(tf.matmul(x, weights['hidden']), biases['hidden']) output_layer = tf.matmul(hidden_layer, weights['output']) + biases['output'] Is there any difference between tf.add and +? Thanks
1. Bias have been defined separately from weights. You can refer the code 2. Even when you use "+" operator, it is converted to "tf.add" which is a more optimized function. So for all practical purposes, they are the same
A.A! Thank you for this helpful material. I was working on this project and I found the following error InvalidArgumentError: logits and labels must be same size: logits_size=[512,10] labels_size=[128,10] [[Node: SoftmaxCrossEntropyWithLogits_2 = SoftmaxCrossEntropyWithLogits[T=DT_FLOAT, _device="/job:localhost/replica:0/task:0/cpu:0"](Reshape_6, Reshape_7)]] During handling of the above exception, another exception occurred: InvalidArgumentError Traceback (most recent call last) in () 14 for i in range(total_batch): 15 batch_x, batch_y = batch_creator(batch_size, train_x.shape[0], 'train') ---> 16 _, c = sess.run([optimizer, cost], feed_dict = {x: batch_x, y: batch_y}) 17 18 avg_cost += c / total_batch I tried my best(apply different google solutions) to solve it but it still remain. I will be grateful if you help me to solve it. :
Check if the length of input (batch_x) you are passing is the same as length of output (batch_y)
HI Faizan, I am currently working on image dataset. Eg. Train Dataset has multiple sub folders like Automobiles, Flowers, Bikes and each folders having 100 images of different size. Labels are given as subfloders name. How do i read these images in python from each folders and create single training set. As i read online we need to resize all images into same size to input in tensorflow. I am using windows machine so not be able to use OpenCV3 also. Please help me out.
Hi Deepak. You can use keras for this purpose, as it directly reads subfolders and assigns classes with respect to it
Hi Faizan, Great Post. A quick question , I was going through the nn network from various materials and it got me a bit confused. Why are we not using an relu activation in the output layer ? I did try implement it and my cost stopped reducing after a point leading to poor accuracy(clearly it is incorrect). Can you sum up or point me in a direction where I can better understand this.
In the output layer, your aim is to predict classes (if its a classification problem) or to predict continuous values (if its a regression problem). So you would use an appropriate activation function. In a classification problem, you generally use sigmoid or softmax function, whereas in regression you use a linear function
Hello Faizan,Can u please give a clear picture of what you are doing in the batch_creator function. batch_y = eval(dataset_name).ix[batch_mask, 'label'].values what is the .ix here and what is 'label'? Since I am trying use this code for training my own dataset,it will be useful for me to know this function. thank you.
Hi Atana, .ix is a pandas function (http://pandas.pydata.org/pandas-docs/version/0.19.2/generated/pandas.DataFrame.ix.html) and 'label' represents the label column that is that target variable. Here I am simply trying to extract the respective targets for the batches
Faizan, Can you explain what this part of code is performing, i had encountered an error "logits and labels must be same size: logits_size=[118,3] labels_size=[128,3]". I tracked where was my tensor variable size going incorrect and it was below code which dint calculated expected batch size as per the specified inputs. batch_x = eval(dataset_name + '_x')[[batch_mask]].reshape(-1, (input_num_units)) Some below debug variables size : - batch_mask: 128 dataset_name: train input_num_units: 9216 batch_x: (118, 9216) unclean_batch_x: (118, 9216) unclean_batch_x max: 160.0 batch_y: (128, 3)
The number of elements in batch_x and batch_y should match. In your problem, one is 128 and the other 118. Both should be the same
That was a very informative post as I am just getting started with TF. It would be very much appreciated if you elaborate this line of code: filepath = os.path.join(data_dir, 'Train', 'Images', 'train', img_name)
Hi Sayak, Here I am defining the file path. So instead of directly setting it as "E:\workspace\Train\Images"... , I am writing a more generalized code by using python's "os" library
Getting the following error after running the code for assigning the cost: --------------------------------------------------------------------------- ValueError Traceback (most recent call last) in () ----> 1 cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(output_layer, y)) 2 optimizer = tf.train.AdamOptimizer(learning_rate=learning_rate).minimize(cost) 3 4 init = tf.initialize_all_variables() /home/sayak/anaconda3/envs/py27/lib/python2.7/site-packages/tensorflow/python/ops/nn_ops.pyc in softmax_cross_entropy_with_logits(_sentinel, labels, logits, dim, name) 1605 """ 1606 _ensure_xent_args("softmax_cross_entropy_with_logits", _sentinel, -> 1607 labels, logits) 1608 1609 # TODO(pcmurray) Raise an error when the labels do not sum to 1. Note: This /home/sayak/anaconda3/envs/py27/lib/python2.7/site-packages/tensorflow/python/ops/nn_ops.pyc in _ensure_xent_args(name, sentinel, labels, logits) 1560 if sentinel is not None: 1561 raise ValueError("Only call `%s` with " -> 1562 "named arguments (labels=..., logits=..., ...)" % name) 1563 if labels is None or logits is None: 1564 raise ValueError("Both labels and logits must be provided.") ValueError: Only call `softmax_cross_entropy_with_logits` with named arguments (labels=..., logits=..., ...)
Hi, write this code line instead: cost = tf.reduce_mean(tf.nn.softmax_cross_entropy_with_logits(logits=output_layer, labels=y))
Hi This blog is very useful for me. and which type Neural Network it is, i mean it CNN or RNN. Regards, Kishore
hi, its a simple neural network; a multi layer perceptron
Hi Faizan, Thank you for the article. It is really practical. My problem is I can't download the data from the practice problem page. I clicked Data on the left, but it does nothing. Thank you
Problem fixed. Thank you.
Hi Faizan, Recently i started learning, about deep learning, neural network and possible way to accelerate all computation through GPU, and i went through lots of IEEE paper and then i come across this blog and i must appreciate that this is the only place (being beginner) where i found all required information presented very cleanly right from start, till character prediction. Great work!!
Thanks Vijay
CAN Anyone tell why this code is not producing poper output import tensorflow as tf x=tf.placeholder(tf.float32,shape=[None,1]) y_=tf.placeholder(tf.float32,shape=[None,1]) W=tf.Variable(tf.zeros([1,1])) b=tf.Variable(tf.zeros([1])) y=tf.matmul(x,W)+b init=tf.global_variables_initializer() cross_entropy=tf.nn.softmax_cross_entropy_with_logits(labels=y_,logits=y) train_step=tf.train.GradientDescentOptimizer(0.6).minimize(cross_entropy) sess=tf.InteractiveSession() sess.run(init) for e in range(100): sess.run([train_step,cross_entropy],feed_dict={x:[[1],[2]],y_:[[1],[2]]}) print(sess.run([W,b])) correct_prediction=tf.equal(tf.arg_max(y,1),tf.arg_max(y_,1)) accuracy=tf.reduce_mean(tf.cast(correct_prediction,tf.float32)) print(accuracy.eval(feed_dict={x:[[2]], y_: [[6]]})) sess.close()
Hi, Assuming there's no syntax errors/indentation errors; What error does the code show?
I face this problem, I don't know why other people did not face it. temp = [] for img_name in test.filename: image_path = os.path.join(data_dir, 'Train', 'Images', 'test', img_name) img = imread(image_path, flatten=True) img = img.astype('float32') temp.append(img) test_x = np.stack(temp) Error OutPut AttributeError Traceback (most recent call last) in () 9 10 temp = [] ---> 11 for img_name in test.filename: 12 image_path = os.path.join(data_dir, 'Train', 'Images', 'test', img_name) 13 img = imread(image_path, flatten=True) ~\Anaconda3\envs\tensorflow\lib\site-packages\pandas\core\generic.py in __getattr__(self, name) 3079 if name in self._info_axis: 3080 return self[name] -> 3081 return object.__getattribute__(self, name) 3082 3083 def __setattr__(self, name, value): AttributeError: 'DataFrame' object has no attribute 'filename' I checked the test.csv file and there is no filename field. I may have wrong test.csv file, can you please mention me the correct file to download. Thanks
Hi Sohail, You can find the dataset here: https://datahack.analyticsvidhya.com/contest/practice-problem-identify-the-digits/
hello sir, I am rewriting this code to train another set of data which is image dataset of 20,000. But the image size varying in every image so I am unable to create the training and test set. can you please suggest a solution.
Hey - you can force all the images to be of the same size using scipy's misc package
Hi ! The datasets (Train.csv, Test.csv) belong to that (https://datahack.analyticsvidhya.com/contest/practice-problem-identify-the-digits/) can not to be download .How can I get it ? . Thanks!
Hi - You would have to register to the hackathon to access the dataset