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
1
vote
1
answer
91
views
why validation accuracy is stuck at 75%?
i am using tensorflow=2.15.0 and keras associated with it I have made a cnn network to identify a total of 2294 images into 10 different classes or, data is divided as 229 images are contained in each ...
0
votes
0
answers
14
views
Evaluation of the loss function
Why the three evaluations of the loss in the following code do not agree?
...
- 311
-1
votes
1
answer
54
views
In order to predict after training on Standardized data, do I need the StandardScaler as well?
Is the scaler saved inside the model.keras file or I need to separately save it?
I want to train an neural network, save it, and ...
- 163
0
votes
0
answers
12
views
Does Keras cache activations if lower layers are frozen?
I've been experimenting a bit with gradually adding layers to a model, while freezing N layers and only leaving the N+1th layer trainable. In my mind, the time to train any layer should be roughly ...
- 101
0
votes
1
answer
37
views
My custom neural network is converging but keras model not
in most cases it is probably the other way round but...
I have implemented a basic MLP neural network structure with backpropagation. My data is just a shifted quadratic function with 100 samples. I ...
0
votes
0
answers
18
views
How to make my validation plots more stable and improve R2 metric?
I'm working on predicting 4 numeric values basing on signal spectrum (spectrum is represented as an array of 800 numeric values in scale 0 to 1). The input values are scaled by using StandardScaler. ...
- 1
0
votes
1
answer
31
views
What exactly is saved when I save a NN?
After we trained a Neural Network, we can save it in order to be able to predict without re-training. So when we use model.save('my_model.keras') what exactly is ...
- 163
0
votes
1
answer
82
views
How to automate the restarting of training of deep learning model in TensorFlow
I am trying to automate the (recursively) restart of a finished deep-learning training session in TensorFlow. Currently, to restart I am manually restarting my kernel and re-running the training code.
...
1
vote
1
answer
33
views
Building a CNN (with Keras for pixelwise classification)
I have a set of 120x120 input images with 3 channels. I want to build a basic CNN to predict the value of each pixel. I have 2 doubts. One is regarding the last layer - should be a Dense layer, or a ...
0
votes
0
answers
18
views
Neural network does not overfit my data. (Primarily linear function)
I am using TensorFlow and Keras. My goal is to approximate a primarily linear function that is partially nonlinear, such that a linear regression yields a Mean Absolute Error (MAE) of 0.13. All ...
0
votes
0
answers
20
views
Keras DNN outputs the same value over and over
I'm creating an ensemble of NNs with the same architecture, but each NN only outputs one value when given X_test data. The data (continuous values transformed to be [-1,1]) yields results as expected ...
0
votes
0
answers
27
views
What is the difference between two different Keras sequential models?
I run two different Keras sequential models on IMDB data:
truncate the input data by the first 100 words and translating to float32 array
convert the input data using categorical array
The "1&...
- 101
0
votes
1
answer
68
views
Training Loss for Classification Model Isn't Decreasing
I'm currently building a video classification model for engagement detection but I'm having some trouble training it. The model takes in two tensors as inputs: a 10x48x48x1 tensor which holds a stack ...
- 3
1
vote
1
answer
56
views
How to balance labeled datas and then carry out execution with a certain ratio?
I'm building a binary classification model using a neural network, with python and the libraries tensorflow and keras.
For that I have an unequal amount of labeled data: Around 2'000'000 labeled with <...
- 13
1
vote
1
answer
51
views
Keras CNN early stopping not working as expected with patience parameter in imbalanced datasets
So I want to stop the cnn when a custom (not implemented in keras) logged metric is not improving with a patience of 5 (I chose macro f1 score) and here's what I did:
Created a callback to log the ...
- 11