Stack Overflow
Stack Overflow

Questions tagged [hyperas]

Questions about Hyperas. A tool for hyper-parameter testing and optimization for graphs and neural networks written on Keras. It is wrapper around hyperopt.

Hyperas is a tool for hyper-parameter testing and optimization for graphs and neural networks written on Keras. It is wrapper around hyperopt. Hyperas lets you use the power of hyperopt without having to learn the syntax of it. Instead, just define your keras model as you are used to, but use a simple template notation to define hyper-parameter ranges to tune.

17 questions
3
votes
1 answer

What does max eval parameter in hyperas optim minimize function returns?

I am trying to tune parameters using Hyperas but I can't interpret few details regarding it. Q1) What is max_eval parameter in optim.minimize do? Q2) Does it go through each and every combination of parameters for each max_eval and give me best loss…
Goutham
  • 435
  • 3
  • 16
2
votes
1 answer

Error when using optim.minimize from Hyperas

I'm trying to use optim.minimize from Hyperas. The code is running is google colab, python 3 + GPU. When I run this: best_run, best_model = optim.minimize(model=create_model, data=new_data, algo=tpe.suggest,max_evals=100, trials=Trials(),…
DaniOnd
  • 21
  • 1
2
votes
1 answer

TypeError: hp_choice() takes 2 positional arguments but 7 were given

I'm trying to do hyperparameter optimization to this keras model with the hyperas library, I've never done this before so I basically followed the step-by-step complete example here but I'm getting the error mentioned. Thanks in advance. model =…
Jaime Miranda Ramirez
  • 195
  • 3
  • 18
1
vote
0 answers

Hyperas for regression problems

I am trying to use hyperas for a regression problem. Most of the examples I saw are on classification problems only and I tried to build my model optimization accordingly. However, I am getting an Invalid Loss everytime I try to optimize my…
codeblaze
  • 73
  • 8
1
vote
1 answer

Hyperas not returning best result

I'm using hyperas to optimize a function and it is not returning the best result. During the run the print out reads as follows 100%|██████████| 100/100 [7:01:47<00:00, 411.15s/it, best loss: 5.1005506645909895e-05] but afterwards when I print the…
Novice
  • 855
  • 8
  • 17
1
vote
0 answers

Use hyperopt (or hyperas) with Keras and ImageDataGenerator "flow_from_directory"

I'm making a code to train a CNN (using Keras) with an hyperparameters search using Hyperas. To train the model, I'm using flow_from_directory function of ImageDataGenerator. I read a lot of posts and documentation I found on internet but my code…
rmarion37
  • 73
  • 7
1
vote
2 answers

Decoding problem when using hyperas to find parameters of Keras model, maybe due to the `Trial` function in `hyperopt`

I am using hyperas module to tune my Keras model and return the error: UnicodeDecodeError: 'ascii' codec can't decode byte 0xe8 in position 4785: ordinal not in range(128) The error occurred at calling place, the syntax of trials: if __name__ ==…
Minghao
  • 31
  • 4
1
vote
1 answer

Hyperas loss function for regression problem

I've built a model using Keras for solving the regression problem. I want to perform a hyperparameter optimization on this model. As metrics I used val_mean_absolute_error. In the example, only classification problem is covered (available on…
George P.
  • 181
  • 1
  • 8
0
votes
1 answer

Tensorflow and Keras incompatibilities in imported virtual environment not present in original virtual environment

I am working on my laptop with tensorflow 2.4.1 and keras 2.3.1 in an anaconda virtual environment. Unfortunately I need to run my code on a remote machine, but I am having tons of problems in setting up a working virtual environment there. I even…
Vale
  • 1
0
votes
0 answers

why i have error in name notebook in hyperas?

I am doing an efficient way to build neural network architectures and I am basing it on this…
pepoBKN
  • 11
  • 4
0
votes
0 answers

Google colab syntax error-- Using keras hyperas

I am trying to optimize hyperparameters for the IMBD dataset using keras hyperas but I am getting an error. I used this (https://www.kaggle.com/kt66nf/hyperparameter-optimization-using-keras-hyperas) code as a reference CODE def…
MadiE
  • 1
0
votes
1 answer

Hyperparameter-tuning (Hyperas) and Cross-Validation with Pipeline-Preprocessing

tl;dr I try to optimize and cross-validate my hyperparameters with Hyperas but can't make a preprocessing (scaling, over/undersampling) pipeline with KerasClassifier work I use Hyperas (wrapper for hyperopt) to tune my Neural Network's (built with…
MatsPro
  • 13
  • 4
0
votes
1 answer

Get speed of model evaluation with Keras

I would like to retrieve metrics of speed of the model on validation data, in order to compare different parameters and their impact on speed. For example, the time spent per batch on validation data. Or, since I use hyperopt, the time spent per…
Alchemille
  • 51
  • 4
0
votes
1 answer

CNN Keras using Hyperas error: AttributeError: 'str' object has no attribute 'ndim'

The model compiled and ran, until it got to the line that's evaluating the model at the end of the code. I think that the error is that it received a string, but wasn't expecting a string, but I have no idea on how to fix it. Thanks in advance. def…
Jaime Miranda Ramirez
  • 195
  • 3
  • 18
0
votes
1 answer

Hyperas syntax issue when using choice

I am new to using Hyperas and I am facing a syntax problem. I want to optimize the parameters of my LSTM in keras, for that I am using hyperas to loop on parameters like dropout rate or numbers of neurons as well as to choose between different…
ASUCB
  • 51
  • 6
1
2