RNN is abbreviation of Recurrent Neural Network which is a class of artificial neural net with feedback.

**0**

votes

**0**answers

11 views

### TFLearn RNN output is always constant - New to TFLearn

GOAL: I am trying to develop a NN model that is capable of learning some unknown non-linear quadcopter drone dynamics. The end purpose is for this model to be used inside of a Genetic Algorithm tool ...

**0**

votes

**0**answers

9 views

### Neural Language model: Calculate the conditional probalities

I was trying to compute the probability of a word given its context, i.e., P(word|before_context), where before_context consists of a word sequence. For example, consider a sentence I am a college ...

**0**

votes

**1**answer

6 views

### Use temporal class weights in many-to-one RNNs in Keras

I have a model that uses several many-to-many RNN layers, followed by a single many-to-one layer and a one-to-one decoding layer.So the first RNN layer uses the parameter "return_sequences=True" and ...

**0**

votes

**0**answers

7 views

### using dynamic_rnn with multiRNN gives error

I want to create a dynamic_rnn using tensorflow in python with Multi LSTM cells.form searches on internet I have found this code:import tensorflow as tfbatch_size=30truncated_series_length=4...

**1**

vote

**0**answers

13 views

### How to train a LSTM Neural Network to forecast a full “cycle” of a Time Series?

I have the below data whose "cycles" grow in period over time:My goal is to feed some fraction of this into a LSTM network in order to predict or forecast the remaining points (at least enough to ...

**1**

vote

**0**answers

26 views

### Tensorflow: TFRecordDataset + Embedding_lookup + Dynamic rnn -> memory leak

I am using SequenceExample to prepare features for sequence labeling task. The most important feature is an array containing ids of characters per input token, for example [[0, 1, 3], [1, 4, 5, 6], ......

**0**

votes

**0**answers

16 views

### RNNs - How to min-max scaling out-of-sample for test case

I'm trying to predict Bitcoin price by RNNs with Tensorflow.My model is quite simple RNNs with LSTM : cell=tf.contrib.rnn.BasicLSTMCell(num_units=num_hidden, state_is_tuple=True, activation=tf....

**0**

votes

**0**answers

20 views

### Keras LSTM RNN for Classification

Can an LSTM “count” the number of times a sensor hit a peak reading?I created a simple example in which 2 machines fail as soon as they receive their third sensor rating of 25pts or higher. However, ...

**0**

votes

**0**answers

21 views

### when does input pipeline returns a new data batch?

I am using an input pipeline with queues and TFRecordReader to read a tfrecord file and use the data directly into a dynamic_rnn function.So for example if i have this last step of the input pipeline:...

**2**

votes

**1**answer

24 views

### How to build a recurrent neural net in Keras where each input goes through a layer first?

I'm trying to build an neural net in Keras that would look like this:Where x_1, x_2, ... are input vectors that undergo the same transformation f. f is itself a layer whose parameters must be ...

**0**

votes

**1**answer

9 views

### how to freeze the tensorflow model?

I have a model.py file that save a class of rnn. for example:class TextRNN:def __init__(self, hidden_size, num_classes, learning_rate...):self.input_data=tf.placeholder(tf.int32,[...

**0**

votes

**0**answers

10 views

### Python: Slicing a 2d tensor out of a 3d tensor in Tensorflow

I'm trying to take the last output out of a dynamic RNN outputs tensor with a shape of batch_size x sentence_size x hidden_size, and then use it as an input for a softmax layer.The shape of the last ...

**-1**

votes

**0**answers

12 views

### Speeding up Beam Search with seq2seq

I have a fully working seq2seq attention model with beam search and beam search do give improved results. But it takes > 1min for inferencing with beam search (k=5) because none of it is parallelised. ...

**1**

vote

**0**answers

27 views

### Training on multiple time-series of various length using recurrent layers in Keras

TL;DR - I have a couple of thousand speed-profiles (time-series where the speed of a car has been sampled) and I am unsure how to configure my models such that I can perform arbitrary forecasting (i.e....

**1**

vote

**1**answer

34 views

### What's the difference between data time major and batch major?

Can anyone explain what data time major and batch major mean and what's the difference between them?