Stack Overflow
Stack Overflow

Questions tagged [keras-tuner]

166 questions
1
vote
2 answers

Dealing with highly imbalanced datasets using Tensorflow Dataset and Keras Tuner

I have a highly imbalanced dataset (3% Yes, 87% No) of textual documents, containing a title and abstract feature. I have transformed these documents into tf.data.Dataset entities with padded batches. Now, I am trying to train this dataset using…
rvdinter
  • 51
  • 3
1
vote
1 answer

Tune a pre-existing model with Keras Tuner

I am looking at Keras Tuner as a way of doing hyperparameter optimization, but all of the examples I have seen show an entirely fresh model being defined. For example, from the Keras Tuner Hello World: def build_model(hp): model =…
ChrisM
  • 2,128
  • 1
  • 23
  • 41
1
vote
1 answer

View logs from Keras Tuner in Tensorboard

I am tuning a Neural Net with Keras Tuner I am creating logs this way: tuner = RandomSearch( build_model, objective='val_accuracy', max_trials=5, executions_per_trial=3, directory='my_dir', project_name='helloworld') This…
bjornsing
  • 322
  • 6
  • 25
1
vote
1 answer

Model-building function in Keras Tuner did not return a valid Keras Model instance

I am trying to learn CNN following Krish naik Youtube tutorial in one program i am getting this error: RuntimeError: Model-building function did not return a valid Keras Model instance, found
pysaundary
  • 166
  • 2
  • 13
0
votes
0 answers

Developing a CNN architecture for keras-tuner

I just discovered Keras-Tuner and am trying to use it to tune my CNN's hyperparameters, but it looks like there's a mistake in my function to define the model. Here's my function: from keras import models, layers, optimizers, losses, metrics …
curious_cosmo
  • 1,184
  • 1
  • 18
  • 36
0
votes
0 answers

ValueError: Input 0 of layer "sequential" is incompatible with the layer: expected shape=(None, 7732, 3), found shape=(None, 250)

11 I'm working in a project to perform multiclass classification. on Cusing Keras Tensorflow. I'm using the onsumer Finance FRCB dataset.In the first step I create token and embedidings using Keras Tokenizer as follows. %%time # prepare text data…
Rohit Jain
  • 1
0
votes
0 answers

keras_tuner found dict_keys([]) after using custom Callback function

I have a problem using the Keras tuner for hyperparameter tuning while using a custom callback function. In my callback function I basically want to evaluate every trained model and save some specific evaluation parameters as well as the model at…
Lukas
  • 1
  • 1
0
votes
0 answers

Does keras_tuner BayesianOptimization warm start?

I used a keras_tuner.BayesianOptimization on particular search space, and it took a while to find the best model. I'd like to change the search space a bit but allow it to use the previous trials to chose which direction to explore it (given that…
sapo_cosmico
  • 6,274
  • 12
  • 45
  • 58
0
votes
0 answers

Key error when printing tuner.summary() from Keras Tuner

In the following code, when the "print(tuner.summary())" line is commented, the code will run without error, although nothing is printed to the screen. When this line is uncommented, I get the error message below. Code: import numpy as np import…
Innocuous Rift
  • 61
  • 6
0
votes
0 answers

tuning Keras Sequential NN, tuned model doesn't perform well

I am trying to tune my NN hyperparameters. This was my initial NN: model = tf.keras.models.Sequential([ tf.keras.layers.Dense(256, activation=tf.nn.tanh, input_shape=[X_train_norm.shape[1]]), …
shani Friedaman
  • 1
  • 1
0
votes
1 answer

Tensorflow: Graph of the iterator is different from the graph the dataset was created in

While using the Keras_tuner library I got the error in the title. I have no clue how to fix it and could not find any solutions for some time. I am using Tensorflow BatchDatasets and passing them for the Hyperparameter tuning. batch_size =…
Meno
  • 1
  • 2
0
votes
0 answers

Error in the initialisation of initial layer of Keras Tuner

I'm getting the value error of incompatible shape of tensors of my code. The following is my code : from tensorflow import keras from tensorflow.keras.models import Sequential from tensorflow.keras.layers import Dense from tensorflow.keras.layers…
Guna Sekhar Venkata Chennaiah
  • 1
0
votes
0 answers

Keras-tuner doesn't use the whole training dataset, how can one adjust it?

I'm currently stuck in my masterthesis. I'm trying to do a Bayesian Optimization for the hyperparameter tuning with the Keras-Tuner. I have a training dateset containing 4131 samples, but keras-tuner only uses 130 datapoints for the tuning. I'd like…
maximilian
  • 1
0
votes
0 answers

keras tuner difference between max_epochs in hyperband(() and epochs in search()

I am using this in my code: stop_early = tf.keras.callbacks.EarlyStopping(monitor='loss', patience=3) tuner = kt.Hyperband( model_builder, objective='val_loss', max_epochs=100, factor=2, overwrite=True, directory=dir, project_name='x', …
Robbe Van Renne
  • 1
0
votes
1 answer

Integrate batch size in keras tuner

I am new to Keras and have been using KerasTuner for the hyperparameters. This works very well, but I have not yet managed to tune the batch size. There is an official way from Keras, which was discussed here: How to tune the number of epochs and…
AndyEverything
  • 23
  • 4
1 2 3
…
10 11