Questions tagged [tensorflow]
A Python library for deep learning developed by Google. Use this tag for any on-topic question that (a) involves tensorflow either as a critical part of the question or expected answer, & (b) is not just about how to use tensorflow.
678
questions
0
votes
0
answers
16
views
Best way to approximate head point having only face keypoints
I'm using the BlazeFace model from TensorFlow which only has this few keypoints:
I need those keypoints plus a head keypoint, like this one:
My question is, which would be the best way to ...
0
votes
0
answers
12
views
How to properly mask MultiHeadAttention for sliding window time series data
I have data in the shape (batch, seq_len, features) that is a time series sliding window. In essence, I'm using the most recent ...
- 133
0
votes
0
answers
13
views
How to predict a mathematical progression with keras
I try the following model for a many-to-many recurrent network:
...
1
vote
0
answers
12
views
Tensorflow - calling a model inside a GradientTape scope VS calling it inside a loss function
Is there a difference in the gradient computation between the two code snippets ...
Code 1:
...
- 11
0
votes
0
answers
12
views
Updating temporal embeddings depending on the input
I'm building a forecasting model and I'm using a temporal embedding along with a positional embedding following the same architecture as Informer. ( https://arxiv.org/abs/2012.07436 )
My problem is ...
0
votes
0
answers
11
views
Predict gaps in time-series using LSTM
I have the number of timeseries with missing values (gaps). I want to train the LSTM NN for the prediction gaps task. Each time-series have the different numbers of gaps.
Now, I use the mean value ...
- 101
0
votes
0
answers
9
views
what is average unit activation and how to measure it?
recently I read a research paper about exponential linear units named "FAST AND ACCURATE DEEP NETWORK LEARNING BY EXPONENTIAL LINEAR UNITS (ELUS)". in section 4.1.1 they train 8 layers (128 ...
1
vote
1
answer
13
views
Train a Final Machine Learning Model with Tensorflow
Based on a previous question and on this article, it is suggested that you split the data between train and test (or train/validate/test). But once you have control of your model, you should retrain ...
- 127
0
votes
0
answers
22
views
Understanding tf.feature_column and dimensionality input
I hope this is the correct forum.
I am going over the feature_column package of the TensorFlow [1] and have checked the code that generates a DNN using the feature_column. Assume that there is a ...
- 101
0
votes
0
answers
24
views
Neural Network Regression Making Bad predictions
I have a dataset that has 83 dimentions and 300K observations for the training set. These 300K observations are standardized and fitted to a 3-layer DNN with the following parameters:
...
- 3
0
votes
0
answers
8
views
Image-recognition model makes good predictions only with training examples
Im trying to use a kaggle dataset to train a model that recognizes american fingerspelling language from an image. The problem is that, built the model, if i record the screen with the examples ...
- 1
5
votes
1
answer
279
views
Neural network gives very different accuracies if repeated on same data, why?
I'm running a neural network to classify audio files into 4 classes. This uses 3300 1min files split roughly evenly across classes. I split this into 80:10:10 train:validation:test sets. This trains ...
- 63
0
votes
0
answers
40
views
Choosing the 'best' epoch to stop the training of neural network. Top accuracy not improving, but average is
I'm familiar with concepts like early stopping, and detection of plateau and so on.
Tensorflow CNN training has a possibility of saving only best model too, according to model's accuracy metric (for ...
- 101
0
votes
0
answers
16
views
Loss Jumps while Train a Fully Connected MLP
i am currently trying to train a Fully Connected MLP with vibration data from a machine aggregate for classification. During training, the loss jumps up abruptly in each epoch. Here is an excerpt of ...
0
votes
0
answers
6
views
Optimizing population split predictions
I am trying to find the best way of building a NN to predict population statistics; The problem is defined by a set of $(x_i, y_i)$, such that $x_i \in R^d$ and $y_i \in R^k$.
Furthermore, for each $i$...
- 1
2
votes
0
answers
44
views
Using `relu` as activation function for regression with only positive values
I'm building a deep learning model to predict times of arrival. By definition, the time of arrival is always positive. I'm wondering if I can use a relu as the ...
- 31
2
votes
0
answers
41
views
Why an agent can't learn on cheat data?
I want to train a FinRL model which will trade on an exchange using Ray Tune.
I tried two different tune runs: with future data(you can find this code by "#Future data") and without. I ...
- 21
1
vote
0
answers
71
views
What's the difference between stacked LSTM and encoder-decoder LSTM
I wanted to learn about encoder-decoder LSTM and after some digging around I get that the first LSTM layer in an encoder-decoder-LSTM outputs its hidden state and then the next LSTM layer uses that ...
0
votes
0
answers
12
views
Classifying images with categorical and numerical data in a GAN
I want to create a GAN model that accepts tabular data as well as a corresponding image. The data should be trained all together. For the final processing I want to be able to pass the tabular data ...
- 1
3
votes
1
answer
35
views
Convolutional neural network architecture calculation question
I'm attempting to understand the neural network architecture used in this paper: Visualizing and Understanding Convolutional Networks.
Here's an image of the network achitecture from the paper that is ...
- 33
1
vote
1
answer
70
views
Choosing a model for machine learning problem
Update: See bottom of question for insight into the real application which this small example is attempting to simplify.
Questin:
In the different machine learning libraries, what kind of model suits ...
- 121
1
vote
1
answer
91
views
How to get the probability a prediction is correct from a binary classifier
I have an image binary classifier that where class a = 0 and class b = 1
When I receive a prediction of a single image, is working out the probability that the prediction is correct as simple as:
a: ...
- 11
1
vote
1
answer
38
views
Training MLP by early-stopping without dropout layers
I am training a multi-layer perceptron (MLP) with 4 hidden layers. I got the best hyper-parameters by the following steps using HParams:
Training model by each ...
- 113
1
vote
1
answer
132
views
Multiple time series forecasting: How to split the data for training of a neural network
Use case: I have sales of 90 products during the first 180 days since the product launch. I want to train an LSTM network to predict sales 4 weeks ahead given the last 7 days of sales. The model ...
- 111
1
vote
0
answers
38
views
TensorFlow/keras conversation score prediction
First the question: I'm new to machine learning and have made a first attempt at predicting scores (see problem below). I'm now looking for the right way to set up the model (layers, activations, ...
- 121
1
vote
0
answers
75
views
How does Walk-Forward work with LSTM
I have been looking at how to split my data for training/validation/test for a timeseries using LSTM and have some conflicting thoughts I would like to get a bit more clarity on.
I came across: QA1 ...
- 41
1
vote
0
answers
33
views
the value of accuracy and loss change by the order of the training
https://colab.research.google.com/drive/13wMNCXxKs_uqFVzuJqE2zxhsxWK8Ya4k?usp=sharing
Hello guys
I’m having a hard time trying to figure out what I am doing wrong here.
I used 4 pretrained models from ...
we ing
1
vote
0
answers
32
views
Getting same prediction for all the classes in mobilenetV2 - Tensorflow
I am using mobile net v2 for multiclass image classification problem,
here is how I am loading the data
...
- 11
0
votes
0
answers
43
views
How to shape dataset for multivariate LSTM model for 'multiple timelines'
I'm trying to make a model to predict the gross income of our company's stores based off of a 14-feature data monthly data set that I have for each store. We have 950 stores.
I have no problem ...
- 1
0
votes
1
answer
91
views
Why my training Precision and Recall is higher than Validation Precision and Recall?
I am training a deep learning model for binary image classification using Keras and TensorFlow. My model gave the highest ...
- 19
1
vote
0
answers
18
views
Why my training Precision and Recall is higher than Validation Precision and Recall? [duplicate]
I am training a deep learning model for binary image classification using Keras and TensorFlow. My model gave the highest ...
- 19
2
votes
0
answers
30
views
Fine-tune: ways to determine how many layers to unfreeze
How to determine amount of layers I should unfreeze while fine-tuning deep learning model? Is there any sets of rules or I should just experiment?
- 21
6
votes
3
answers
1k
views
Impose a condition on neural network
I am building a neural network model with TensorFlow and Keras in python. My model is performing well on unseen data in the way I desire and everything is fine. but the problem that I don't have any ...
- 93
1
vote
0
answers
74
views
How to apply Keras Conv1D over 3D dimensional input?
Context: I'm predicting whether a machine will break down within 1 hour, and I have sensors located at 4 different parts of the machine, which give me historical readings of different metrics. ...
- 21
0
votes
0
answers
21
views
Can Grad-CAM be used for CNNs with a flatten layer?
I would like to visualize CNNs with a flatten layer.
I looked into Grad-CAM, which is one of the most popular visualization methods for CNNs, but I thought it could only be used for CNNs with a global ...
- 1
0
votes
0
answers
12
views
Neural Network for identifying handwritten letters is super inaccurate
I am trying to make a neural network that classifies letters. I have it training and it gets to 96% accuracy but when I get it to classify things, it either guesses correctly or guesses R. When I try ...
- 1
0
votes
0
answers
53
views
Why applying Grad-CAM to the input layer is not common?
Grad-CAM is a popular tool that could be applied to the last convolutional layer to understand the inner structure of the deep neural network.
It is general to apply Grad-CAM onto the last ...
김의담
0
votes
0
answers
18
views
How to determine the number of hidden layers a model needs? [duplicate]
I built a multi-layer perception model, from online tutorials. They are very good tutorials. However, when I come down to build my own model, with 32 variables(input layer), one output(regression ...
0
votes
0
answers
31
views
Tuning Neural Network in R [duplicate]
I working in R and I try to fit neural network with TensorFlow and Keras. Generally I am not satisficed with result from model.
I tried to fit this model sequential model.
...
- 133
0
votes
0
answers
70
views
Many-to-many time-series prediction problem
I would like some advice on how to implement an RNN or LSTM for my problem. I am working in Keras Tensorflow.
My data describes the moisture % histogram of a sample of material. There are 42 features ...
- 101
0
votes
1
answer
36
views
Interpretation of plots from neural network
I am working on a Keras and TensorFlow in R and I trying to make good predictions for a regression problem.
Below you can see how is look like plots two plots one for loss function and second for mean ...
- 133
1
vote
0
answers
155
views
How to deal with zeros in neural network? [closed]
I am working on a Keras and TensorFlow in R and I try to make good predictions for a regression problem (not classification).
In my dataset there are several features and my target variable has a lot ...
- 133
0
votes
0
answers
62
views
Techniques for estimation of GEV distribution parameters [duplicate]
I am fitting distributions on observation data to make generalizations about the frequencies of different types of natural events. Right now I am focused on the generalized extreme value (GEV) ...
- 101
0
votes
0
answers
278
views
What if weights of model is output of neurons?
If instead of, giving axon's weights some number value, why not give it output value from other neuron. I think, taking output from neuron in previous layer and setting it as weight in current layer ...
0
votes
0
answers
84
views
Loss Function of a Variational Autoencoder when using Implicit Reparameterization Gradients (Dirichlet distributed latent space)
I would like to implement a VAE with a Dirichlet distributed latent space in Python.
Since the reparametrization trick does not work for the Dirichlet Distribution I would use Implicit ...
0
votes
1
answer
92
views
How to interpret the model weights extracted from tensorflow2 keras LSTM model?
I fitted a tensorflow.keras.layers.LSTM model and extracted the model weights via get_weights(). However, I find it hard to ...
- 15
0
votes
1
answer
61
views
Is it possible in deep learning to train on a subset of training set in order to find the best hyper-parameters?
In classic machine learning, it is not uncommon to do a search for hyper-parameters by training different configurations on a small subset of training set. Usually, for each set of hyper-parameters, a ...
- 101
0
votes
0
answers
24
views
Confidence intervals for next frame video prediction
I'm using a ConvLSTM network for next frame video prediction. The output is a deterministic prediction of an image in the future. My question is: can a ConvLSTM model give me an interval of prediction ...
- 1
15
votes
5
answers
1k
views
Can I enforce monotonically increasing neural net outputs (min, mean, max)?
Hi I'm using a DL model (TensorFlow) to predict daily minimum, mean, and maximum values of a target dataset. I was thinking that the model would have 3 outputs for each day, (min, mean, max).
Is there ...
- 251
0
votes
0
answers
10
views
CNN model is not improving and has zero validation accuracy [duplicate]
I'm trying to create a model to classify images. there are 21 different classes they each have around 800 images. images are in different sizes and aspect ratios and they are resized to (64,64) pixels....
