- Neural Network Model - Deep Learning with Neural Networks and TensorFlow

Neural Network Model - Deep Learning with Neural Networks and TensorFlow

Welcome to part three of Deep Learning with Neural Networks and TensorFlow, and part 45 of the Machine Learning tutorial series. In this tutorial, we're going to be heading (falling) down the rabbit hole by creating our own Deep Neural Network with TensorFlow.

We're going to be working first wit...
Welcome to part three of Deep Learning with Neural Networks and TensorFlow, and part 45 of the Machine Learning tutorial series. In this tutorial, we're going to be heading (falling) down the rabbit hole by creating our own Deep Neural Network with TensorFlow.

We're going to be working first with the MNIST dataset, which is a dataset that contains 60,000 training samples and 10,000 testing samples of hand-written and labeled digits, 0 through 9, so ten total "classes." I will note that this is a very small dataset in terms of what you would be working with in any realistic setting, but it should also be small enough to work on everyone's computers.

The MNIST dataset has the images, which we'll be working with as purely black and white, thresholded, images, of size 28 x 28, or 784 pixels total. Our features will be the pixel values for each pixel, thresholded. Either the pixel is "blank" (nothing there, a 0), or there is something there (1). Those are our features. We're going to attempt to just use this extremely rudimentary data, and predict the number we're looking at (a 0,1,2,3,4,5,6,7,8, or 9). We're hoping that our neural network will somehow create an inner-model of the relationships between pixels, and be able to look at new examples of digits and predict them to a high degree.

https://pythonprogramming.net
https://twitter.com/sentdex
https://www.facebook.com/pythonprogramming.net/
https://plus.google.com/+sentdex

#computation graph #Deep Learning #TensorFlow #Theano #Neural Network #Artificial Neural Network #Tutorial #Python #ANN #Artificial Intelligence #model
Starbucks product placement at . - Neural Network Model - Deep Learning with Neural Networks and TensorFlow

Starbucks product placement at .

Neural Network Model - Deep Learning with Neural Networks and TensorFlow
2016年07月20日
00:10:20 - 00:32:51
-  I'm watching this in 2057 and I can confirm that average PC has petabytes of RAM... also time travel is a thing now. - Neural Network Model - Deep Learning with Neural Networks and TensorFlow

- I'm watching this in 2057 and I can confirm that average PC has petabytes of RAM... also time travel is a thing now.

Neural Network Model - Deep Learning with Neural Networks and TensorFlow
2016年07月20日
00:11:53 - 00:32:51
made me laugh - Neural Network Model - Deep Learning with Neural Networks and TensorFlow

made me laugh

Neural Network Model - Deep Learning with Neural Networks and TensorFlow
2016年07月20日
00:12:05 - 00:32:51
"training_features = shuffled_tr_features[] - Neural Network Model - Deep Learning with Neural Networks and TensorFlow

"training_features = shuffled_tr_features[]

Neural Network Model - Deep Learning with Neural Networks and TensorFlow
2016年07月20日
00:13:20 - 00:13:20
training_labels = shuffled_tr_labels[]testing_features = shuffled_tr_features[800:]testing_labels = shuffled_tr_labels[800:] " - Neural Network Model - Deep Learning with Neural Networks and TensorFlow

training_labels = shuffled_tr_labels[]testing_features = shuffled_tr_features[800:]testing_labels = shuffled_tr_labels[800:] "

Neural Network Model - Deep Learning with Neural Networks and TensorFlow
2016年07月20日
00:13:20 - 00:32:51
The term is flattened representation - Neural Network Model - Deep Learning with Neural Networks and TensorFlow

The term is flattened representation

Neural Network Model - Deep Learning with Neural Networks and TensorFlow
2016年07月20日
00:13:35 - 00:32:51
I think the proper term would be "unroll" - Neural Network Model - Deep Learning with Neural Networks and TensorFlow

I think the proper term would be "unroll"

Neural Network Model - Deep Learning with Neural Networks and TensorFlow
2016年07月20日
00:13:40 - 00:32:51
I mean come on are we going to drop to a level where we don't even give the computer some good fucking input !XD !! YEAH FIGURE IT OUT BITCH IDK I DON'T HAVE A SINGLE CLUE - Neural Network Model - Deep Learning with Neural Networks and TensorFlow

I mean come on are we going to drop to a level where we don't even give the computer some good fucking input !XD !! YEAH FIGURE IT OUT BITCH IDK I DON'T HAVE A SINGLE CLUE

Neural Network Model - Deep Learning with Neural Networks and TensorFlow
2016年07月20日
00:19:46 - 00:32:51
+sentdex On executing the code mentioned upto  I got the following error:AttributeError: module 'tensorflow.examples.tutorials.mnist.input_data' has no attribute 'real_data_sets'I searched for a solution but since I'm not so fluent with tensor flows, I couldn't understand the process. Please assist if possible. - Neural Network Model - Deep Learning with Neural Networks and TensorFlow

+sentdex On executing the code mentioned upto I got the following error:AttributeError: module 'tensorflow.examples.tutorials.mnist.input_data' has no attribute 'real_data_sets'I searched for a solution but since I'm not so fluent with tensor flows, I couldn't understand the process. Please assist if possible.

Neural Network Model - Deep Learning with Neural Networks and TensorFlow
2016年07月20日
00:21:40 - 00:32:51
Hey dude, @ when you're using the + symbol inside the call to add, you're actually doing the addition before making the call to add when not separating variables with a comma... - Neural Network Model - Deep Learning with Neural Networks and TensorFlow

Hey dude, @ when you're using the + symbol inside the call to add, you're actually doing the addition before making the call to add when not separating variables with a comma...

Neural Network Model - Deep Learning with Neural Networks and TensorFlow
2016年07月20日
00:27:30 - 00:32:51
Why did he remove remove tf.add() on the output layer @ while keeping the '+' and output biases, saying that there isn't any summation on the output layer? Also +leloss it's the same code in part 4, unfixed - Neural Network Model - Deep Learning with Neural Networks and TensorFlow

Why did he remove remove tf.add() on the output layer @ while keeping the '+' and output biases, saying that there isn't any summation on the output layer? Also +leloss it's the same code in part 4, unfixed

Neural Network Model - Deep Learning with Neural Networks and TensorFlow
2016年07月20日
00:30:48 - 00:32:51
sentdex

sentdex

🎉 1,100,000 人達成! 🎉

【予測】200万人まであと2520日(2029年8月28日)

チャンネル登録 RSS
Python Programming tutorials, going further than just the basics. Learn about machine learning, finance, data analysis, robotics, web development, game development and more.

I have ~1000 videos, all of which do not fit on the front page. Try searching on the channel page, or via https://pythonpr...
Python Programming tutorials, going further than just the basics. Learn about machine learning, finance, data analysis, robotics, web development, game development and more.

I have ~1000 videos, all of which do not fit on the front page. Try searching on the channel page, or via https://pythonprogramming.net. If you cannot find something, just ask!

Bitcoin donations: 1GV7srgR4NJx4vrk7avCmmVQQrqmv87ty6
Paypal donations: [email protected]

Timetable

動画タイムテーブル

動画数:54件

at  what's the difference between "prev_obs.reshape(-1,4,1)[0]" and "prev_obs.reshape(-1,4)" ?if there is none, why do the first one? is that a habit from something else? - Testing Network - Training a neural network to play a game with TensorFlow and Open AI p.4

at what's the difference between "prev_obs.reshape(-1,4,1)[0]" and "prev_obs.reshape(-1,4)" ?if there is none, why do the first one? is that a habit from something else?

Testing Network - Training a neural network to play a game with TensorFlow and Open AI p.4
2017年03月13日
00:03:40 - 00:16:16
at  Lord Sentdex said that we take the 0th element of the list because we are only predicting on one frame.Anyone knows how to make predictions based on multiple frames ? - Testing Network - Training a neural network to play a game with TensorFlow and Open AI p.4

at Lord Sentdex said that we take the 0th element of the list because we are only predicting on one frame.Anyone knows how to make predictions based on multiple frames ?

Testing Network - Training a neural network to play a game with TensorFlow and Open AI p.4
2017年03月13日
00:04:00 - 00:16:16
Hey Sentdex, what do you mean by 'headless' at ? What type of example is headless and what type isn't? - Testing Network - Training a neural network to play a game with TensorFlow and Open AI p.4

Hey Sentdex, what do you mean by 'headless' at ? What type of example is headless and what type isn't?

Testing Network - Training a neural network to play a game with TensorFlow and Open AI p.4
2017年03月13日
00:04:50 - 00:16:16
lol, @ "Harrison, always messing with future Harrison". - Training Model - Training a neural network to play a game with TensorFlow and Open AI p.3

lol, @ "Harrison, always messing with future Harrison".

Training Model - Training a neural network to play a game with TensorFlow and Open AI p.3
2017年03月13日
00:13:30 - 00:14:38
someone gets a score of over 9000! - Intro - Training a neural network to play a game with TensorFlow and Open AI

someone gets a score of over 9000!

Intro - Training a neural network to play a game with TensorFlow and Open AI
2017年03月13日
00:02:20 - 00:12:32
The links you mentioned at  are missing - Intro - Training a neural network to play a game with TensorFlow and Open AI

The links you mentioned at are missing

Intro - Training a neural network to play a game with TensorFlow and Open AI
2017年03月13日
00:05:00 - 00:12:32
/x pass dtype wherever u r making np.array()2. if u r getting like target_1/y use tf.compat.v1.reset_default_graph() just after the wherever u have imported tensorflow.Some points which I faced and their solution:1. if u r working on newer numpy, always pass dtype = object in the parameter of np.array()2. I am using tensorflow 2.xx    tflearn 0.05(something like this).3. If u have version compatibility issues with tf2.0.0   I made a virtual env using conda then used pip to install latest of everything. - Training - Using Convolutional Neural Network to Identify Dogs vs Cats p. 3

/x pass dtype wherever u r making np.array()2. if u r getting like target_1/y use tf.compat.v1.reset_default_graph() just after the wherever u have imported tensorflow.Some points which I faced and their solution:1. if u r working on newer numpy, always pass dtype = object in the parameter of np.array()2. I am using tensorflow 2.xx tflearn 0.05(something like this).3. If u have version compatibility issues with tf2.0.0 I made a virtual env using conda then used pip to install latest of everything.

Training - Using Convolutional Neural Network to Identify Dogs vs Cats p. 3
2017年02月23日
00:00:00 - 00:19:02
[<?, ?it/s] ".I don't know how to fix it can you please help me to solve this error and thank you in advance - Building the Network - Using Convolutional Neural Network to Identify Dogs vs Cats p. 2

[<?, ?it/s] ".I don't know how to fix it can you please help me to solve this error and thank you in advance

Building the Network - Using Convolutional Neural Network to Identify Dogs vs Cats p. 2
2017年02月23日
00:00:00 - 00:09:05
[<?, ?it/s] and there seems to be nothing happening. Could you please help me on this. - Building the Network - Using Convolutional Neural Network to Identify Dogs vs Cats p. 2

[<?, ?it/s] and there seems to be nothing happening. Could you please help me on this.

Building the Network - Using Convolutional Neural Network to Identify Dogs vs Cats p. 2
2017年02月23日
00:00:00 - 00:09:05
[<00:00, 804.72it/s] - Building the Network - Using Convolutional Neural Network to Identify Dogs vs Cats p. 2

[<00:00, 804.72it/s]

Building the Network - Using Convolutional Neural Network to Identify Dogs vs Cats p. 2
2017年02月23日
00:00:31 - 00:09:05
tqdm is available on kaggle kernel. ( in video) - Intro and preprocessing - Using Convolutional Neural Network to Identify Dogs vs Cats p. 1

tqdm is available on kaggle kernel. ( in video)

Intro and preprocessing - Using Convolutional Neural Network to Identify Dogs vs Cats p. 1
2017年02月23日
00:08:28 - 00:12:51
pciBusID: .0totalMemory: 4.00GiB freeMemory: 3.29GiB - Installing CPU and GPU TensorFlow on Windows

pciBusID: .0totalMemory: 4.00GiB freeMemory: 3.29GiB

Installing CPU and GPU TensorFlow on Windows
2016年12月12日
00:01:00 - 00:18:16
gpuz says you were using about 11GB of memory. What's up with that? Do you have like 2 6GB cards in SLI?edit: Oh shit. Nevermind. Just watched your gear video. Titan X 12GB - Installing CPU and GPU TensorFlow on Windows

gpuz says you were using about 11GB of memory. What's up with that? Do you have like 2 6GB cards in SLI?edit: Oh shit. Nevermind. Just watched your gear video. Titan X 12GB

Installing CPU and GPU TensorFlow on Windows
2016年12月12日
00:17:06 - 00:18:16
Why is the data being reshaped at ? - TFLearn - Deep Learning with Neural Networks and TensorFlow p. 14

Why is the data being reshaped at ?

TFLearn - Deep Learning with Neural Networks and TensorFlow p. 14
2016年10月05日
00:11:00 - 00:27:42
Aren't you supposed to shift down by 2 then? - Convolutional Neural Networks Basics - Deep Learning withTensorFlow 12

Aren't you supposed to shift down by 2 then?

Convolutional Neural Networks Basics - Deep Learning withTensorFlow 12
2016年09月19日
00:04:27 - 00:09:11
That's how Microsoft logo was designed - Convolutional Neural Networks Basics - Deep Learning withTensorFlow 12

That's how Microsoft logo was designed

Convolutional Neural Networks Basics - Deep Learning withTensorFlow 12
2016年09月19日
00:04:38 - 00:09:11
ValueError: Input graph and Layer graph are not the same: Tensor("split_", shape=(?, 28), dtype=float32) is not from the passed-in graph. - RNN Example in Tensorflow - Deep Learning with Neural Networks 11

ValueError: Input graph and Layer graph are not the same: Tensor("split_", shape=(?, 28), dtype=float32) is not from the passed-in graph.

RNN Example in Tensorflow - Deep Learning with Neural Networks 11
2016年09月14日
00:02:00 - 00:14:20
] at ? - RNN Example in Tensorflow - Deep Learning with Neural Networks 11

] at ?

RNN Example in Tensorflow - Deep Learning with Neural Networks 11
2016年09月14日
00:08:51 - 00:14:20