Questions tagged [keras-tuner]
166 questions
0
votes
0 answers
Keras-Tuner: Dependent hyperparameters
I have a simple use case, but I cannot find any solution to this problem anywhere:
I have two hyperparameters which I want to tune with keras-tuner:
Amount of nodes of the first hidden layer
Amount of nodes of the second hidden layer
Now, I want…
Code Pope
- 5,075
- 8
- 26
- 68
0
votes
1 answer
Tensorsflow keras tuner will run once but not again
my code will run only one time after that it will only display how many images found in each flow from directory. It run the tuner once and then won't run it again, maybe it thinks I have already ran the code and don'tt need to again. I think it has…
benjam
- 1
0
votes
0 answers
Does keras tuner support ragged tensors?
Appologies if this has been covered elsewhere but after a few days of hunting I can't seem to find a suitable answer.
I am working with ragged tensors comprising short sections of waveform data. I wanted to be able to utilize the keras tuner.
From…
webber.96
- 1
- 1
0
votes
0 answers
Error when trying to save the checkpoints hyperband
I am running hyperparameter tunning using Hyperband and Keras_tunner, I have the following network :
import tensorflow as tf
from tensorflow import keras
from tensorflow.keras.models import Sequential, Model
from tensorflow.keras.layers import…
Stetco Oana
- 101
- 1
- 1
- 11
0
votes
0 answers
Keras_tuner AttributeError: 'Sequential' object has no attribute 'distribute_strategy'
I am trying keras tuner for the first time. Here is my code:
import os
import sys
import pandas as pd
import numpy as np
import matplotlib.pyplot as plt
import tensorflow
import tensorflow.keras
from tensorflow.keras.models import Sequential
from…
0
votes
1 answer
Using keras tuner for hyperparameter tuning and extracting trial statistics with Tensorboard workaround
I'm using keras tuner for hyperparameter tuning my sequential neural network in keras. My aim is to let keras tuner do a lot of trials and then save all statistics - loss, hyperparameters, trial numbers and epochs - to a file, so I can plot them…
Tobitobitobi
- 57
- 9
0
votes
0 answers
tensorflow.python.framework.errors_impl.FailedPreconditionError: keras_tuner/untitled_project/trial_1; Directory not empty
I am trying to use keras_tuner with cross-validation for hyperparameter optimization. My code looks as follows:
for i in range(5):
train_df = df[df['fold'] != i]
valid_df = df[df['fold'] == i]
.
.
…
Dushi Fdz
- 161
- 3
- 22
0
votes
1 answer
KeyError: {objective} in Keras Tuner regression search
I am trying to use Keras Tuner to do hyperparameter tuning on a regression ANN. When I do a hyperparameter search, I receive KeyError: 'val_mean_absolute_error.
Here is my code:
def build_model(hp):
model = keras.Sequential()
for i in…
Tim
- 1
- 1
0
votes
0 answers
how to use percision as well as recall as objective in keras tuner
I am new to Tensorflow ,I donot know how to get objective set to at least 10% val_recall with maximum val_precision in keras tuner.
can somebody please let me know what needs to be done for f1score as a metric in keras-tuner.
Currently it is set to…
Granth
- 325
- 4
- 17
0
votes
1 answer
Keras Tuner how to do basic grid search
Keras Tuner offers several tuning strategies in the form of tuner classes. I fail to find an implementation for the most basic tuning strategy, which is a grid search. Did I oversee it? If not, is there a way to force the strategy on one of the…
Viktor
- 583
- 1
- 3
- 10
0
votes
1 answer
Keras Tuner on autoencoder - Add condition : first hidden layer units greater than or equal next hidden layer units
I want to use Keras-tuner to tune an autoencoder hyperparameters.
It is a symetric AE with two layers. I want the number of units in the first layer always greater than or equal the units in the second layer. But I don't know how implement it with…
Larel5000
- 1
- 2
0
votes
0 answers
kerastuner tune hyperparameter that selects a subset of input features
I have a toy problem, where I have some data (X,Y) where the labels Y are frequencies, and X are cosine functions with frequency Y: X=cos(Y*t+phi)+N, where t is a time vector, phi is some random phase shift and N is additive noise. I am developing a…
john g.
- 1
0
votes
1 answer
How can I extract all arguments I am passing to a TensorFlow function?
It is difficult to retrain my models in new data because I never remember my initial optimizer, loss function, and hyperparameters. How can I extract all arguments I am passing to a TensorFlow function? Let's say from the code below, how to extract…
deijany91
- 9
- 4
0
votes
1 answer
Simple Tensor Flow Example with keras_tuner
I am new to Tensorflow and keras_tuner. I am working with PyCharm, Anaconda3, Python 3.9.12.
Below you can find a minimal working example. The code trains in the first part a simple reference ANN with fixed hyperparameters, using one input and…
Zeit
- 13
- 5
0
votes
0 answers
ValueError: Tensor conversion requested dtype float64 for Tensor with dtype float32
Trying to use Keras Tuner to optimize my hyperparameters. I build the following model:
def build_model(hp):
model = Sequential(name='ESN_NE')
model.add(InputLayer((timesteps, input_dim), name='input_layer'))
…
Murilo
- 533
- 3
- 15