Questions tagged [keras]
Keras is a popular, open-source deep learning API for Python built on top of TensorFlow and is useful for fast implementation. Topics include efficient low-level tensor operations, computation of arbitrary gradients, scalable computations, export of graphs, etc.
2,723
questions
0
votes
0
answers
10
views
Recommendations for a machine learning trading system [closed]
I recently completed a project that I have been working on to predict the movement of a stocks price either up or down then using a portfolio optimization algorithm to create a expected sharpe ratio ...
0
votes
0
answers
14
views
LSTM not recognizing increasing and decreasing patterns
I am struggling to get an LSTM to recognize different patterns in sequences. As a very simple example, I would like my LSTM to recognize and predict both increasing and decreasing sequences. For ...
0
votes
0
answers
14
views
Understanding Divergence in LSTM Units with Zero Initialization and Shared Weights?
I'm trying to understand how LSTM units can diverge over time when they start with zero initialization and share the same weights. Here are the key points of my confusion:
Initialization: All units ...
0
votes
1
answer
51
views
How to Incorporate Label Titles and Parent Folder Information in a Multiclass Classification Model Using Keras?
I'm building a multiclass classification system using Keras.
I am working with a dataset that includes text data and its metadata. Both the text and the metadata are sequences of words. The output of ...
0
votes
0
answers
10
views
How to pass feature value to custom loss in Keras
I am using a custom loss to train my model and want to use feature value to have a differential loss, something like
...
0
votes
0
answers
16
views
Feature importance and classes importance
I have the following trained time series classification tensorflow model :
...
0
votes
0
answers
12
views
Keras: Relationship extraction
I am trying to manage how to extract logical relations from medical sentences. E.g.:
INPUT: "Candidiasis is infection by Candida species (most often C. albicans), manifested by mucocutaneous ...
0
votes
0
answers
32
views
Keras multi-label model predictions always sum to ~1
I believe I've configured this model correctly for multi-label classification, but it would seem that it insists on behaving like a multi-class model, since the predictions it outputs always sum to 1 (...
1
vote
0
answers
46
views
Why can't I replicate the results from this paper?
I'm trying to train a model to evaluate chess positions, following the methodology from this paper (note that the author presents several different architectures, but I'm only looking at the ANN with ...
0
votes
0
answers
18
views
Apply Swin transformer to 1d arrays
My input features are 1d arrays of shape (1000,)
I can tokenize the arrays using tf.extract_patches
...
1
vote
1
answer
38
views
Validation accuracy can't increase above 70%
I am building a classifying model to predict images over 3 classes. The data is balanced, with 10.5k images for train ( 3.5k for each ), 3k validation images ( 1k each ).
I increased my ...
1
vote
0
answers
30
views
Validation accuracy stuck in tf keras
So I have a model to classify images into 3 classes. I have 10.5k train images ( 3.5 per each category ) and 3k ( 1k per each category ) validation images but I can't increase my val_acc no matter ...
1
vote
0
answers
17
views
How to include variable input shape in convLSTM2D?
I am classifying time series of 72x72 images in 4 filters (just like RGB). Things work well ...
0
votes
0
answers
12
views
Vision Transformer model training and Validation accuracy stuck at 50
I have built Vision Transformers from scratch using Tensorflow keras for Binary classification of Fake and Real images.The dataset is balanced, 50% Real images and 50% fake images. But when i run this ...
0
votes
0
answers
14
views
Why does the TensorFlow docs use a different GAN generator loss?
As per the original paper that introduced GANs, the generator loss is given as:
$$
L_{G} = L _{BCE}(\mathbf{\vec 0}, \mathbf{D}(\mathbf{G}(\mathbf{\vec z}))) = \log(1 - \mathbf{D}(\mathbf{G}(\mathbf{\...
0
votes
0
answers
19
views
What is the shape of the hidden/cell state of convLSTM2D?
I am new to convLSTM2D and I understand how it works, however, I am confused about the shape of the hidden states at different epochs ...
0
votes
1
answer
57
views
Is it possible to train a neural network to feed into a Random Forest Classifier or any other type of classifier like XGBoost or Decision Tree?
I want to create a model architecture to predict future stock price movement as such:
The Goal of this model is to predict if the price will go UP or DOWN within the next 3 months.
I have tried a few ...
0
votes
0
answers
33
views
Multi-step CNN-LSTM Encoder Decoder Model is not fitting well on peak values
I am trying to predict 4 values concurrently for next 24 hours
n_lookback = 48
n_forecast = 24
I am breaking the sequences like this:
...
0
votes
0
answers
14
views
Keras siamese model history is empty
I am making a siamese neural network with triplet loss using keras, and have encountered an odd problem. I tried saving my history twice: once in a callback (saved as a dictionary), and once after ...
0
votes
0
answers
20
views
Getting nearly 100% accuracy using Binary Classification in Tensorflow but incredibly wrong prediction levels for email messages
I'm creating a Chrome Extension to read user emails via Gmail's API, and then passing in user emails to a trained Keras model in Flask to determine whether the email was written by an AI or a Human, ...
0
votes
0
answers
9
views
Overfitting - Imbalance Classification using Deep-feed forward network
I have an unbalanced dataset, so I used SMOTEENN on the training set to resample, after training DFF,i could see the model is overfitting, could someone help me solve this?
Thank You.
...
2
votes
1
answer
51
views
Custom loss function in python
I am trying to implement a custom loss function inspired by https://arxiv.org/pdf/2305.10464.pdf. That is:
$ L(\mathbf{x}) = (1-y) \left\lVert \mathbf{x_{true} - \mathbf{x_{pred}}} \right\rVert^2 + y \...
0
votes
0
answers
41
views
Tensorflow SegNet architecture
I was unable to find a complete description of the SegNet architecture for image segmentation (specifically, the decoder layers). Therefore, I would like to clarify the correctness of my ...
1
vote
1
answer
50
views
Does using different optimizer change the loss landscape
I plot the landscape using this code, and I notice the landscape shape has changed a lot. My understanding is that the optimizer does not change the loss landscape. But now I'm confused if its just ...
0
votes
1
answer
26
views
How do I ensure final output shape matches input shape for a semantic segmentation task?
I trying to replicate the semantic segmentation example
https://keras.io/examples/vision/oxford_pets_image_segmentation/
but train on my own data. I have 8 labels (7 features + background). My images ...
0
votes
0
answers
37
views
Calculate AUC-ROC and AUC-PRC for an LSTM Model
I have the following simple Bidirectional LSTM model for a binary classification task:
...
1
vote
0
answers
19
views
How can I change my input shape in the architecture for the cnn(transfer learning)?
I have already made a model and trained it, and then saved the model along with its weights. The input shape in that model is [900,300,1] which is [height,width,channel].
I want to use the same model ...
0
votes
0
answers
24
views
Tensorflow keras training/validation loss digits of precision
I have my model defined with certain structure and now just permuting between filter counts and number of layers of structure.
I am watching the output of model.fit() such as
...
0
votes
0
answers
10
views
Using a neural network to predict disease outcomes in individual cases
I'm working on a research project with the goal of using a neural network to predict disease outcomes for patients. I've built a neural network using Tensorflow and Keras and I've trained and tested ...
0
votes
1
answer
23
views
Connecting Flatten layer to Dense layer
I'm struggling with my neural network.
In short, I need to recreate a model from anywhere on the internet, I've found a model that combines BiLSTM, LSTM and GRU. However, based on the error I got when ...