Questions tagged [keras]
For questions related to Keras, the modular neural networks library written in Python. However, note that programming questions are off-topic here.
256
questions
0
votes
0
answers
16
views
kerascv retinanet for gender identification
I am using KerasCV Retinanet to detect people and their genders in images.
I would like to detect "man", "woman", "boy", "girl" and "baby" in images. ...
- 3
0
votes
0
answers
9
views
I'm trying to build image search like Google Photo-Image with face is given to model & it'll get all the images in database in which he/she is present
When a user upload a selfie, the model search same person in dataset of images of multiple persons and get back all the images in which that person is present.
Step 1: From dataset of images I detect ...
- 1
0
votes
1
answer
79
views
Transfer learning using pretrained tensorflow object detection model [closed]
I am new to AI/ML and wanted to seek guidance as I am totally lost. I will simplify my issue as follows:
Let's say I would like to detect apples and oranges in images.
I would like to leverage a pre-...
- 3
0
votes
0
answers
12
views
How is the accuracy as a metric in a Keras machine learning model calculated? Is it a valuable metric for LSTM
I'm training a LSTM neural network for time series prediction in Keras. During the training of the model, the loss (mse) gradually decreases each epoch, but the accuracy as well as the validation ...
- 1
0
votes
2
answers
33
views
Must I "prime" my normalizer with the same data I trained it with in order to use it?
I trained a Keras Network. During training, I would first initialize a normalizer from the values in the entire dataset, then partition into train, test and validation datasets. After partitioning, I ...
- 149
0
votes
0
answers
28
views
MultiLayer Perceptron not working for regression problem, what could I try?
I am trying to learn the inverse kinematics of a robotic manipulator. To do that I have a simulator with which I acquired data.
My dataset is composed of positions in X, Y and Z and actuator variables ...
0
votes
0
answers
41
views
How to setup correctly a sequence generation task with RL/policy gradient learning?
I've a pretrained model for sequence generation that I'd like to improve with RL but there are several shady points.
So, I have the following model and loss function:
...
- 1
0
votes
1
answer
46
views
Easiest way to train a neural-network with neurons that deviate from $f_{nl}(x \cdot A)$
I want to model how a neural network would behave for a system of input-output devices that are only approximately similar to a neuron. I think I have a resonable plan for how to do this, but I'm ...
- 221
0
votes
0
answers
41
views
Updating custom output layers of an LSTM network
I have a text generation task learning to predict the next word with an LSTM network with multiple output layers.
After the generation of a sentence has finished, I calculate a reward for the whole ...
- 1
1
vote
0
answers
18
views
good period prediction but bad magnitude using keras LSTM neural network
I want to predict the voltage of a battery along time using neural networks. This voltage is read using an ADC and generates a charge/discharge profile that ideally looks like this:
Which goes very ...
- 111
0
votes
0
answers
9
views
Incorporating HiPlot and Keras
I just started to learn about Keras and train some models, and I came across HiPlot which is used for tuning hyperparameters. I was wondering if HiPlot can also be used to see what parameters would ...
- 1
0
votes
0
answers
17
views
Tips for getting LSTM to train for next word predcition
I am trying to train an LSTM network for next work prediction. I have scraped a rather large dataset from Wikipedia of country descriptions. I have done normal preprocessing (removing punctuation and ...
- 101
1
vote
0
answers
108
views
How can an MLP be implemented with convolutional layers?
I am studying the architecture of the network pointnet, specifically the MLPs stages of the pipeline highlighted in red in the following image (taken from the author page here):
It is strange to find ...
2
votes
1
answer
57
views
How can I tell a CNN to ignore nodata values in satellite images?
I'm trying to train an image segmentation model on satellite images. There are two main issues: first, not all of the images are the same size. My understanding is that by using a fully convolutional ...
- 21
0
votes
1
answer
740
views
Keras Subclassing : TypeError: 'KerasTensor' object is not callable Call arguments received by layer [closed]
Implementing UNet but getting an error: type error 'KerasTensor' object is not callable
...
- 27
0
votes
1
answer
24
views
Regression Model diverging after adding a new feature with higher variance and magnitude
In a time series regression problem I'm predicting "change" rather than the actual intended value i.e
Instead of:
...
0
votes
0
answers
29
views
How to use UPSNet or Mask-RCNN? How to format image data for panoptic segmentation?
I want to use UPSNet (github repo) (paper) to train a model to perform panoptic segmentation on my own dataset. I would also consider using a model based on Mask-RCNN to simply perform instance ...
- 1
0
votes
0
answers
17
views
Hard time trying to fix overfit
I'm trying to make a binary classification model using keras, but it seems to overfit every time. I have tried differents architectures and its seems that a larger model performs better than a smaller ...
2
votes
1
answer
126
views
Why do training and fixing a reservoir yield very similar results (in an echo state network)?
Disclaimer: I asked this question 2 days ago in Cross Validated, but it has been left unanswered.
I am trying to better understand how echo state networks work. To see, how fixing the weights of the ...
user68128
0
votes
0
answers
61
views
Best methods to square rectangular images for OR
I've read previous posts that assert using one of these solutions:
crop and or resize
nn input size independent
In my case, I am using some tensorflow models and afaik they report a fixed size like ...
- 79
1
vote
1
answer
56
views
How to setup a reinforcement learning model that changes the values of $x$ to maximize $y$ in $y = f(x)$?
Assuming a relation such that $y = f(x)$, where $y$ represents a scalar and $x \in 20 \times 1$ vector consisting of zeros and ones, I want to set up a reinforcement learning model that changes the ...
- 111
2
votes
2
answers
141
views
Why is a simple regression problem so hard for an MLP to learn?
Consider a very simple problem, which is to find the maximum value out of a list of 5 numbers between 0 and 1. This is obviously trivial, but serves as a good example for a real-world problem I'm ...
- 191
0
votes
0
answers
101
views
Found input variables with inconsistent numbers of samples
I have an issue. the model gave me an error of Found input variables with inconsistent numbers of samples: But I don't understand why
...
- 1
0
votes
1
answer
49
views
Which type of neural network to use to classify data by which equation most likely generated it?
Problem Summary: Identify which equation a set of data was most likely generated from
Problem Description: Let's say I have two different equations that are functions of variables X and Y and ...
- 133
0
votes
1
answer
112
views
How do I use ResNet for text processing?
I need to implement a deep neural network [residual neural network (ResNet)] that takes some text as an input [length M x N] and then processes it. Now as far as my understanding goes, ResNet is used ...
- 1
2
votes
0
answers
125
views
Why use z_mean to plot the latent space learned by a Variational Autoencoder?
In the Keras website, there is an example code of a Variational Autoencoder.
At the end of such a page, there is an example code that plots the latent space learned from MNIST. The code is as follows:
...
- 149
0
votes
0
answers
32
views
Are there techniques (pygad - tpot-optuna)for best Genatic algorithm optimize hyper prameter cnn 1D
Iam new in mashin learning and i try to optimize tenser flow with keras conv1d model to improve classification by improve hyper kernal and filter
For training dataset csv =(1325,33,1) with outputs ...
- 1
0
votes
0
answers
10
views
Referencing features by name instead of index when feeding inputs
Traditionally the inputs of a model is a matrix of N dimensions.
This works well with inputs that are position-sensitive (For example in CV the placement of the pixels relative to each other can be ...
2
votes
1
answer
65
views
Are the "artifacts" in select Keras MNIST training images really there or is my download corrupt?
I'm having fun with a ludicrously well known and used dataset: mnist.
I am doing it with a huge and well known tool: keras.
Please excuse the red dots, something else I was doing. I have otherwise ...
- 371
0
votes
0
answers
31
views
agent based DNN with a loopback
I have a data problem with no direct reward mechanism,(test/train) good and fault solutions.
Though over a long time period good decisions might be made.
I've been searching for days now for an agent ...
- 101
3
votes
2
answers
1k
views
How embeddings learned from one model can be used in another?
In the website the following explanation is provided about Embedding layer:
The Embedding layer is initialized with random weights and will learn
an embedding for all of the words in the training ...
- 43
1
vote
0
answers
32
views
Loss Function for Binary Classification with Multiple Correct Choices
I have a binary classification problem, where there are multiple correct predictions, however, I would consider the prediction to be correct if the highest confidence prediction of a 1 is correct.
I ...
- 11
0
votes
1
answer
180
views
What data can I obtain from CNN model (H5 file)? [closed]
I created a CNN model and it is saved in h5 format. I used the Netron app, where I obtained the model architecture, however ...
- 103
0
votes
1
answer
153
views
Help on Deep Sarsa algorithm that work with pytorch (Adam optimiser) but not with keras/Tensorflow (Adam optimiser)
I have a deep sarsa algorithm wich work great on Pytorch on lunar-lander-v2 and I would use with Keras/Tensorflow. It use mini-batch of size 64 wich are used 128 time to train at each episode.
There ...
- 1
1
vote
1
answer
2k
views
keras model accuracy not improving
I am trying to do multi class(16) classification, however no matter what parameters or number of layers I use my accuracy is not improving, its in 30s the max I got was 43.
I have tried early stopping ...
- 11
1
vote
1
answer
129
views
Why does my neural network perform different on the same images during training and testing?
I use tensorflow keras to build a neural network that classifies images of covid-19 rapid tests into three classes (Negative, Positive, Empty).
During training the ...
1
vote
1
answer
378
views
How exactly does Keras calculate the validation accuracy?
After each epoch, Keras provides the following evaluations (depending on how the model is compiled):
train_accuracy
train_loss
validation_loss
validation_accuracy
Keras evaluates the performance of ...
- 111
0
votes
1
answer
192
views
Shuffling vs Non-shuffling train/test set yields drastically different results
I am currently working with a very deep NN (200mio. to 350mio. params). My data set is roughly of shape (2mio, 350), i.e. 2mio samples and 350 features. In fact, the features are time series. As input ...
0
votes
1
answer
476
views
Time taken to solve cartpole environment using DQN
I am trying to solve the cartpole environment (GitHub) using DQN agent. I have been building my own DQN agent by following a tutorial by Jon Krohn.
I am able to solve the environment with a maximum ...
1
vote
0
answers
267
views
Why can't I reproduce my results in keras using random seed? [closed]
I was doing a task using RNN to predict a time series movement.
I want to make my results reproducible. So I strictly followed this post:
https://stackoverflow.com/questions/32419510/how-to-get-...
- 121
2
votes
3
answers
225
views
Is it possible to learn the number of layers?
Is it possible, in a transformer or other deep architecture, to include the number of layers as a parameter of the model so it could be learned?
In fact, I have a keras layer that I use to change the ...
- 51
-1
votes
1
answer
151
views
Denoise autoencoder not training properly [closed]
I'm trying to make a denoise autoencoder wherein the encoder part is vgg16 and decoder is opposite of vgg16(encoder) network. My dataset consists of 5K images in grayscale.
Now while training, the ...
-1
votes
1
answer
1k
views
can't find a viable import class for keras.utils.Sequence [closed]
I am using Google Colab. tensorflow version = 2.8.0, and keras is the same. I am trying to get a BalancedDataGenerator(Sequence) class created, but I can't get <...
0
votes
2
answers
96
views
Overfitting problem - poor performance on test data
I'm facing the problem of overfitting and I can't deal with it - I tried experimenting with optimizer, but nothing seems appropriate. My model has extremely poor performance on testing data and the ...
- 1
0
votes
1
answer
596
views
Do the values over 0.5 mean my model classified the data as a "1" label and vice versa?
I am doing binary classification using an LSTM and my output layer is 1 neuron with a sigmoid function. My labels are either 0 or 1.
...
- 3
1
vote
1
answer
719
views
Which approach can I use to generate forged signatures from real ones?
I am in internship period and I'm working on a signature verification problem.
This process needs real and forged signatures. All I have are the real signatures (like 30 signatures per person), and I ...
0
votes
1
answer
209
views
Where can I find authentic references on "categorical cross entropy" and "categorical accuracy metric"?
My Python source code uses TensorFlow and Keras to implement a neural network.
The Keras source code uses something called "categorical cross-entropy" and "categorical accuracy metric&...
- 299
-1
votes
1
answer
892
views
Low accuracy and high loss in multi-class classification [closed]
I'm trying to classify images in 17 flowers dataset which consist of 1360 images of 17 classes (80 images per class); I have to use DNNs only therefore I made my model with the following settings:
<...
- 1
1
vote
1
answer
519
views
Weights initialization once the Neural Network is trained
I am trying to understand how weights are initialized in a Neural Network using Keras deep learning framework and what happens if I train a Neural Network and then I want to train it again: are the ...
0
votes
1
answer
102
views
Why does validation accuracy stop rising so soon?
I have implemented a GRU to deal with youtube comment data. I am a bit confused about why the validation score seems to even out around 70% and then keeps rising, this doesn't look like overfitting ...
- 1