Questions tagged [keras-tuner]
166 questions
1
vote
1 answer
How do you save progress during a Keras Tuner run?
I am currently shifting through a larger search space with Keras Tuner on a free Google Colab instance. Because of usage limits, my search run will be interrupted before completion. I would like to save the progress of my search periodically in…

Denan
- 43
- 5
1
vote
1 answer
Keras BayesianOptimization tuner makes the "best val_loss" worse during tuning
I'm tuning a model with the Keras tuner BayesianOptimization. The tuning objective is val_loss which is calculated after each epoch. As I understand it, the tuner will go through various hyperparameter configurations and train the model while…

douira
- 506
- 1
- 6
- 22
1
vote
2 answers
How to use "LeakyRelu" and Parametric Leaky Relu "PReLU" in Keras Tuner
I am using Keras Tuner and using RandomSearch() to hypertune my regression model. While I can hypertune using "relu" and "selu", I am unable to do the same for Leaky Relu. I understand that the reason "relu" and "selu" string works because, for…

Asim Raja
- 39
- 1
- 6
1
vote
0 answers
Keras Tuner: Accessing the data in the directory created during Hyperparameter Tuning using the Keras Tuner in Google Colab
I am tuning an ANN model using the Keras Tuner, using the Bayesian optimizer as follows:
tuner = BayesianOptimization (
build_model,
objective=kt.Objective('val_auc', direction='max'),
max_trials=30,
executions_per_trial=10,
…

Chris Barnard
- 11
- 2
1
vote
1 answer
Hyperparameter Tuning with Keras Tuner RandomSearch Error
I am using keras tuner to optimize hyperparameters: hidden layers, neurons, activation function, and learning rate. I have time series regression problem with 31 inputs, 32 outputs with N number of data samples.
My original X_train shape is (N,31)…

3Mcollab
- 111
- 1
- 4
1
vote
2 answers
Keras Tuner return validation losses from hyperparameter search
Using Keras-tuner to create a hyperparameter tuning object and calling the search method, it is easy to retrieve the best hyperparameter configurations once the search is complete, however there does not appear to be any in-built way to also return…

SO1999
- 67
- 5
1
vote
2 answers
Keras Hyperband Search Using Directory Iterator
I am using Tensorflow's flow_from_directory to collect a large image dataset and then train on it. I want to use Keras Tuner but when I run
tuner.search(test_data_gen, epochs=50,
validation_split=0.2, callbacks=[stop_early])
It…

DragonflyRobotics
- 297
- 4
- 19
1
vote
0 answers
ValueError: Dimension 0 in both shapes must be equal, but are 3 and 10
I try run this NN but return this error:
ValueError: Dimension 0 in both shapes must be equal, but are 3 and 10. Shapes are [3] and [10]. for '{{node AssignAddVariableOp_2}} = AssignAddVariableOp[dtype=DT_FLOAT](AssignAddVariableOp_2/resource,…
1
vote
1 answer
Keras Tuner Save Best Model
I am currently attempting to used keras tuner to create a model for my CNN, though I am having some issues with saving my model for future use.
As I am used to it, I could regularly just save my model with model.save(filename) to receive a .model…

Fin M.
- 139
- 10
1
vote
0 answers
How can I load a keras-tuner project by name?
I ran multiple projects using keras-tuner and named them. Now I can't figure out how to load the projects to check the best results of each one since the tuner is just the last run and I wanted to check the results with models =…

raulfilipe127
- 13
- 5
1
vote
1 answer
Naming of Keras Tuner Trials directory for TensorBoard
I am using Keras tuner's BayesianOptimization to search for the optimum hyper parameters of a model, I am also using the TensorBoard callback with it to visualise the performance of each model/trial.
However, the trials from the Tuner are…

Mahmoud Gabr
- 109
- 2
- 12
1
vote
0 answers
How to get equivalent behavior of Keras tuner RandomSearch when using Dask
I have an existing hyperparameter search in Keras using kerastuner.tuners.RandomSearch. It looks like this:
tuner = RandomSearch(build_model,
objective='val_loss',
max_trials=18,
executions_per_trial=3,
)
I look at dask documentation…

demongolem
- 9,474
- 36
- 90
- 105
1
vote
2 answers
Google Colab keeps crashing when trying to run keras tuner
This is my first machine learning project, working with a dataset i have created on my own.
Unfortunately Google Colab keeps crashing.
And it seems to have something to do with keras tuner, but i am not sure.
It actually worked for a while.
But now…

JKnecht
- 231
- 2
- 16
1
vote
1 answer
What format do these lists have to be in to be accepted by Keras Tuners Search function?
This Code reads in a set of testing and training guitar jpg images for the neural net to learn and test from.
import numpy as np
import matplotlib.pyplot as plt
import os
import cv2
import random
DATADIR =…

ykseulb
- 11
- 2
1
vote
0 answers
Hyperparameters Tuning with Keras Tuner
I'm working with LSTM network for times series forecasting. I'm using keras tuner for hyperparameters tuning but I always get a null accuracy as the code below shows . Any help would be great.
tuner_H = Hyperband(
build_model,
…

Hejer G
- 11
- 3