A Python library for machine learning, in particular for deep learning, originally created by Google.
1
vote
1answer
10 views
Question about bounding boxes to handle false positives
I have trained a model to detect vehicle number plates. The issue is that it returns matches of partial plates, with high confidence. To eliminate partials I want to add two new boxes to the images ...
0
votes
1answer
30 views
Entropy of a Gaussian Process: Log(Determinant(CovarianceMatrix))
I want to be able to compute the entropy of a Gaussian Process. To that end, I have a simple example in GPFLow. I have a latent function which I sample with two different levels of noise, L1 and L2 ...
0
votes
0answers
10 views
Print whole dictionary in TensorFlow of weights to make l2 reg function? [on hold]
I have a dictionary of weights and would like to make an l2 regularization function but want to print out the whole dictionary first to visually see it because it make it easier for me. I know how to ...
0
votes
2answers
37 views
How to train a stock trading neural network so that the 'profit' parameter is maximized?
I am watching some beginner level video training on neural networks using Tensorflow / Keras to get a better understanding of how they work and how to best implement them.
I have some questions on ...
0
votes
0answers
4 views
Using TensorFlow sentence encoder and other parameters as features in SVM
I have 150K tagged samples of technical support chats between customers and technicians. The chats are classified into 2: “resolved”/ “unresolved” sessions (66.6% and 33.3% of the distribution ...
0
votes
0answers
7 views
Implementation of WAE-GAN does not match with the description in the paper
According to the litterature and specifically to this paper, the wasserstein autoencoders is an encoder-decoder architecture. So it must contain encoder and decoder parts.
in the algorithm ...
0
votes
0answers
25 views
Reconstruction loss for variational auto-encoders
In the original paper of variational auto-encoder (VAE), the estimated lower bound is as follows
where the negative of the second term is reconstruction loss. For the case of Gaussian decoder(...
1
vote
1answer
17 views
RMSprop difference rho and decay in Tensorflow
As this post showed nicely, there is a difference between rho and the decay in RMSprop. I can't clearly see what tensorflows RMSprop parameter decays stands for. Is this the learning rate decay? And ...
0
votes
0answers
15 views
Training a multi inputs deep learning model using every combination of inputs?
I am beginner in deep learning. I want to create a multi inputs CNN model in Keras. The model takes two inputs of images to give the two images class. The
two images from differnt datasets that have ...
3
votes
1answer
66 views
How to cluster parts of broken line made of points?
I am studying clustering techniques and i am pretty new at this topic. Here is my problem: I created a 5 lines which are made of points. This lines are supposed to be continuous and they look like ...
1
vote
0answers
30 views
Recognition the same object from different views
I have 33 classes (33 different objects). I need to recognize the object from any view of the object. Like a packet of potato chips, the packet has different appearance from different view (as shown ...
0
votes
0answers
14 views
Training SSD like network for Number and Alphabet detection
I tried to read number plate using the model trained with SSD like network.
My network has only five layers.
I trained with 60,000 images for digits 0-9 and alphabets A-Z.
So one class has 2,000 ...
1
vote
0answers
11 views
Feature ranking for ANN
I am doing a regression analysis on 1 hidden layer feed forward NN and have 18 input features with 1 output. I Intend to do some feature ranking so it can give me an idea of the most important to the ...
0
votes
1answer
32 views
How to deal with really sparse time series data for a binary classification task using RNN or LSTM?
I have a binary classification prediction task and more often than not, the time series data is like really sparse. The number of zeroes in the time series data is almost always more than 99%. I ...
1
vote
0answers
41 views
A mistake in Tensorflow's documation?
Tensorflow's documentation gives an example for text generation using a RNN with eager execution.
To the best of my understanding, this examples defines a simple RNN (with a GRU cell and a projection ...
0
votes
0answers
5 views
Tensorflow finetune and retrain
Suppose I trained a CNN that follows encoder-decoder architecture. For some reasons, after the previous training, I finetuned only decoder part using ...
0
votes
1answer
23 views
Do two TensorFlow models on different python files conflict? [closed]
I have a TensorFlow model that in each training episode I need to run a function on the data in that episode. This function is also a TensorFlow model in another python file that I import to the main ...
1
vote
0answers
11 views
How does the internal state of Tensorflow's “dtf.nn.dynamic_rnn()” change?
I am trying to do a uni-variate forecasting and I have come across this question quite a lot. This question is regarding TensorFlow's "dtf.nn.dynamic_rnn()".
NOTE: When I say internal state I am ...
0
votes
0answers
15 views
Artificial Neural network - accuracy not altered by different hyper parameters
I am trying to write a program that examines how hyper-parameters effect accuracy in an artificial neural network. However, my accuracy always returns the same and I don't know why.
...
0
votes
1answer
18 views
Tensorflow: Computing gradients across unique network architecture
(First off, I'd like to say, if this specific architecture has a name attached, can you please point me in the right direction?)
I've got a weird, sort-of stacked/nested neural network like the image ...
0
votes
0answers
9 views
Keras gradient flow to compare two models
I am trying to compare two models for the imbalanced dataset. I am having simple LSTM F score of 0.51 vs other LSTM with attention mechanism F score of 0.49. In my opinion the F score should have ...
0
votes
0answers
20 views
Why normalize when all features are on the same scale?
So I'm doing the tensorflow tutorial found here:
https://www.tensorflow.org/tutorials/keras/basic_classification
Basically, my input is a [28x28] matrix (image) that I flatten to a [1x784] vector.
...
-1
votes
0answers
14 views
Is it possible to build a hierarchical pooling beta-binomial model using extra features/regressors?
If we consider the canonical partial pooling "batting rate" problem as soon here https://docs.pymc.io/notebooks/hierarchical_partial_pooling.html, is it possible to formulate the problem such that we ...
1
vote
1answer
36 views
Neural networks to predict a nonlinear curve
I want to model a complex nonlinear function using neural networks (keras).
Training data: input - 8500 x 176 matrix of features, output - 8500 x 8 matrix, each row corresponds to 8 points which ...
0
votes
0answers
6 views
How do tensorflow canned estimators compute loss?
This might seem like a weird question. But for some reason, the documentation lacks any clarification about the subject. For example:
https://www.tensorflow.org/api_docs/python/tf/estimator/...
0
votes
0answers
10 views
My evaluation accuracy curve lays down above the training set accuracy one. Is it normal?
I'm try to build a text classifier using a CNN with word embedding with Keras and Tensorflow.
Graph from tensorboard
Here is a snippet of the code that shows the model construction:
...
0
votes
0answers
17 views
Tensorflow tf.nn.sampled_softmax_loss: Should uniform_candidate_sampler be the default sampler instead of log_uniform_candidate_sampler?
I was reading the documentation for tf.nn.sampled_softmax_loss:
https://www.tensorflow.org/api_docs/python/tf/nn/sampled_softmax_loss
It says for choosing the negative samples, if we don't put ...
0
votes
0answers
86 views
how to visualize feature map of resnet with tensorflow?
I have trained a resnet50 model for classification. Sometime it predicts wrong for some image. So I want to visualization the response map to show what is the feature details it learned. But I did not ...
0
votes
0answers
26 views
Best practices to apply Layer normalization in recurrent networks
I'm trying to add layer normalization (in the encoder-level) to the Listen-attend-and-spell model for speech recognition tasks.
To do so, I have done many experiments (all of them failed) to make my ...
0
votes
0answers
30 views
NaN output from Bidirectional LSTM in Keras
I am creating a bi-directional LSTM using tf.keras APIs:
input_layer = tf.reshape(emb_seqs, [const.TRN_BATCH_SIZE, -1, const.VECTOR_SIZE])
lstm_layer = tf.keras.layers.LSTM(units=LSTM_UNITS, ...
1
vote
0answers
18 views
1
vote
1answer
21 views
What is the purpose or benefits of fully connected layer at the middle of Convolutional Network?
Is there any benefits to have FC layer at the middle of CNN network?
For example, in this network, FC7 has kernel size is 1. What is the benefits of using kernel size 1 in this use?
Those inception ...
0
votes
1answer
41 views
How to get validation accuracy in neural network training?
The following plot shows over fitting in training using training accuracy and validation accuracy during training. How to get that plot in training?
My understanding is that we have training set and ...
0
votes
0answers
20 views
Using an LSTM unrolled into multiple timesteps for training, and just a single timestep for inference
I have built an LSTM in TensorFlow that is unrolled into n timesteps and trains successfully on sequences of lengths n.
I would now like to use my trained model to make m daily predictions one by one....
0
votes
1answer
40 views
Keras backend (tensorflow) vs tensorflow [closed]
I do not really understand the difference between Keras backend (when you use tensorflow as backend) and tensorflow.
I saw some posts where people were trying to modify a Keras loss function and to do ...
0
votes
1answer
19 views
Is it possible, that the get.weights command in Keras returns only rounded numbers? [closed]
I am trying to construct a neural network, which i have previously trained in keras, in another program.
Therefore, i use the get.weights command from keras to acces the weights.
Now the problem is, ...
0
votes
1answer
12 views
What are different methods to find the slow decrease in training/validation loss
I am training YOLO network consisting of resnet50 architecture.This problem is to find different text labels on the image and predict bounding boxes
During training, I am seeing very less change in ...
1
vote
0answers
52 views
Computing average precision metric and cost fucntion for object detection task using scikitLearn and Tensorflow
I have a Data set that contains 5 thousand pictures of my object of interest and 5 thousand pictures with out it. I trained a Convolutional Neural Network using Tensor Flow to detect the position of ...
0
votes
0answers
69 views
When training a CNN, the validation loss and validation accuracy never changes. Is this a problem with the dataset?
When training a CNN, the validation loss and validation accuracy never changes. Is this a problem with the dataset?
No matter what architecture or number of layers or set of parameters, the val train ...
0
votes
1answer
37 views
2-output node Neural network. Only the first output node can predict accurate enough results
I have a three hidden layer neural network. Input layer has 116 nodes(means I have 116 features in every training data set) and output layer has 2 nodes(means I have 2 labels in every training data ...
0
votes
0answers
7 views
Best ML model for testing difference patterns in 1D arrays
I have a dataset where each row is a list of percentages per frame of an animation:
...
1
vote
1answer
33 views
Which algorithm for classification problem?
I want to create a ML (DL) model, that predicts the success of Facebook page-posts, based on historical data.
My dataset represents a couple thousands posts, labeled 1 (successful) and 0 (...
1
vote
0answers
84 views
How to implement custom loss function on keras for VAE
I have implemented a custom loss function. While training the model, I want this loss function to be calculated per batch.
...
1
vote
0answers
65 views
Need help writing a neural network for a Pokemon battle
I'm trying to write a neural network that's able to select the optimal course of action in a Pokemon battle. In a battle, there are two different types of actions: use one of the four moves known by ...
2
votes
1answer
27 views
Uses of TensorBoard Projector besides word embedding?
I was wondering, are any examples of using the projector in TensorBoard for anything other than visualizing word embedding in natural language processing? It seems like a pretty general tool for ...
0
votes
1answer
35 views
Preparing test data for sentiment analysis in Tensor Flow
1) I want to do Sentiment Analysis using RNN + Tensor Flow + (Keras)
2) Is it necessary to prepare test data for sentiment analysis, using RNN, (or any Neural Network), in a certain format ? If so is ...
0
votes
0answers
63 views
Modeling a CNN to identify if image “is” or “isn't” something
I'm trying to build a CNN to play a game online. This game to be precise:
https://www.gameeapp.com/game-bot/ibBTDViUP
I've collected images and labels for each image. These labels tell the network ...
1
vote
1answer
38 views
Can a Fully Connected layer transform a 4D tensor to a 3D tensor by itself?
Recently, I was researching some topics in biometrics and I stumbled upon this paper. They have a table there (Table 1) in which they state that they used a modified CNN from this paper (Table 9). In ...
1
vote
1answer
52 views
What is the adventage of using Reinforcement learning in designing CNN?
I am looking at this paper Designing Neural Network Architectures using Reinforcement Learning.
The paper discussed how to find the best network using ...
1
vote
1answer
108 views
Neural network regression: seemingly bounded output
I have been working on a neural network based predictor for a project. The aim is to learn a certain quantity, say the signal strength of a cellular network, for each coordinate set in the dataset. ...
