Questions tagged [keras-tuner]

166 questions
2
votes
1 answer

ValueError: Tensor's shape (26, 400) is not compatible with supplied shape [26, 200]

I am working on training a neural network using keras and keras_tuner for hyper parameter tuning and ran into an error that isn't similar to other questions asked in the website before. Here's the code that is relevant according to my…
2
votes
1 answer

Keras-Tuner: Is it possible to use test/validation set in the objective/metric function?

Is it possible to score/evaluate the model performance, using keras-tuner, based on the test set instead of the training set? I'm asking this, because as of now, my understanding is that the metric function used as objective in the tuner.search()…
2
votes
1 answer

Keras Tuner Hyperband - how to set max trials and max epochs?

I have two questions regarding the Keras Tuner Hyperband class (for a regression problem) tuner = kerastuner.tuners.hyperband.Hyperband(hypermodel, objective, max_epochs, …
barhdi
  • 21
  • 1
  • 2
2
votes
1 answer

Keras Tuner error: All callbacks used during a search should be deep-copyable

I am having difficulties applying any callbacks to Keras Tuner hyperparameter optimsier objects. Here is the code I run: from keras.callbacks import TensorBoard, EarlyStopping %load_ext tensorboard BATCH_SIZE = 32 time_stamp =…
2
votes
2 answers

How can I tune the optimization function with Keras Tuner?

How can I tune the optimization function with Keras Tuner? I want to try SGD, Adam and RMSprop. I tried: hp_lr = hp.Choice('learning_rate', values=[1e-2, 1e-3, 1e-4]) hp_optimizer = hp.Choice('optimizer', values=[SGD(learning_rate=hp_lr),…
2
votes
0 answers

Keras tuner doesn't update best objective

class regressionHyperModel(HyperModel): def __init__(self, input_shape): self.input_shape = input_shape def build(self, hp): initializer = hp.Choice(name='kernel', values=['variance_scaling', 'constant', …
2
votes
2 answers

Mlflow and KerasTuner integration

I am trying to integrate together KerasTuner and Mlflow. I'd like to record the loss at each epoch of each trial of Keras Tuner. My approach is: class MlflowCallback(tf.keras.callbacks.Callback): # This function will be called after each…
Titus Pullo
  • 3,751
  • 15
  • 45
  • 65
2
votes
1 answer

Keras tuner is crashing Google Colab Pro

Google Colab Pro crashes and restarts the kernel. It worked for a while, running three different trials, before it crashed. Since then it crashes immediately. Here is the code: import os import pandas as pd train_info =…
JKnecht
  • 231
  • 2
  • 16
2
votes
0 answers

Opimization of CNN for Regression Keras Tuner

I am using Keras Tuner to optimize a CNN model for a regression problem. Basicly I have sequences of DNA that I turned into a matrix in order to use them as images to train a CNN model. What I want to predict is a percentage that depends on those…
2
votes
1 answer

Using Keras Tuner for time series split

Is it possible to use Keras tuner for tuning a NN using Time Series Split , similar to sklearn.model_selection.TimeSeriesSplit in sklearn. For example consider a sample tuner class from…
data_person
  • 4,194
  • 7
  • 40
  • 75
2
votes
1 answer

Possible to adjust search space for batch size depending on model size in Keras Tuner?

I'm using Keras similarly to the end-to-end example here- https://keras-team.github.io/keras-tuner/tutorials/subclass-tuner/ Some of the models that are generated are much larger than others, and the larger ones lead to an OOM error that stops the…
JJ101
  • 171
  • 5
2
votes
1 answer

Keras tuner: mismatch between number of layers used and number of layers reported

Using example from Keras Tuner website, I wrote simple tuning code base_model = tf.keras.applications.vgg16.VGG16(input_shape=IMG_SHAPE, include_top=False, …
nurabha
  • 1,152
  • 3
  • 18
  • 42
1
vote
0 answers

KeyError(f"{name} does not exist.") while using keras tuner

I am using the Keras Tuner for optimizing a CNN. I am able to get the optimal values for the filter and kernel size. But when I try to do the same for the pool size it gives me an error: File "C:\Users\...", line 180, in pp -optimal learning…
A. Gehani
  • 83
  • 7
1
vote
0 answers

How to run Keras-tuner with on multiple CPU cores/threads

I have the sample code and want to run the net evaluation in parallel. I have a Desktop with four cores and it can run two threads per core, so I want to have 8 parameter settings running in parallel. The layers/hypermodels are in a different file,…
martin
  • 11
  • 2
1
vote
1 answer

Cannot Restore Checkpoint without Error Keras Tuner

I'm using Keras Tuner to hyper parameterize my CNN to process EMG data. The code is being run on 4 nvidia gpus and 5 cpus with TensorFlow's mirrored strategy. When I run the tuner, it's able to run through all the trials and each for two epochs.…
1 2
3
10 11