Questions tagged [keras-tuner]
166 questions
0
votes
1 answer
Error regarding "accuracy" in hyper-parameter tuning using Keras-tuner
My original MLP model is as follows:
def create_model(n_hidden_1, n_hidden_2, num_classes, num_features):
# create the model
model = Sequential()
model.add(tf.keras.layers.InputLayer(input_shape=(num_features,)))
…
user366312
- 16,949
- 65
- 235
- 452
0
votes
1 answer
How can I pass arguments into the tuner-model?
The following is my original MLP model:
def create_model(n_hidden_1, n_hidden_2, num_classes, num_features):
# create the model
model = Sequential()
model.add(tf.keras.layers.InputLayer(input_shape=(num_features,)))
…
user366312
- 16,949
- 65
- 235
- 452
0
votes
0 answers
Keras tuner error: logits and labels must have the same first dimension
I'm working on my own dataset and trying to fine-tune the parameters using the Keras tuner.I'm using the basic model-building function:
from tensorflow.keras import layers
from keras_tuner import RandomSearch
def build_model(hp):
model =…
user1506515
- 11
- 1
- 3
0
votes
1 answer
Tensor's shape is not compatible with supplied shape, Error in Keras Tuner
I am using Keras tuner. For the simple following code:
import keras_tuner as kt
from tensorflow.keras.regularizers import l1, l2
from tensorflow.keras.models import Sequential
# x: 100 x 20
# y: 1 x 100
tuner = kt.Hyperband(
…
OmG
- 18,337
- 10
- 57
- 90
0
votes
1 answer
Using Random search in keras_tuner
When I run RandomSearch.search I got error message that logits shape and labels shape are different. I Don't understand what is the error. Any help?
following the error message:
tensorflow.python.framework.errors_impl.InvalidArgumentError: …
T. Elhassan
- 23
- 5
0
votes
1 answer
Installing keras_tuner in a TensorFlow 2.5 environment
I'm trying to use
keras_tuner.RandomSearch to find the best parameters that fit my model.
I installed keras_tuner in my anaconda command prompt using the following command:
conda install -c conda-forge keras-tuner
I then imported the package as…
T. Elhassan
- 23
- 5
0
votes
1 answer
Kerastuner for LSTM
I am working on a text classification problem and trying to use Kerastuner to identify the best configuration for my LSTM network. Below is the code for same:
keras Tuner
def build_model(hp):
num_hidden_layers =1
num_units = 8
dropout_rate…
0
votes
0 answers
Not getting same evaluation scores as my NN design when I gave the same parameters into Hyperband
I have an issue with hyperparameter optimization. I designed a simple NN and I am performing Hyperband class for hyperparameter optimization. Before executing the hyperparameter search, I want to see that if I give Hyperband model the same…
pelo
- 1
0
votes
1 answer
Keras tuner.search search error is giving me an error related to shapes `Shapes (None, 11, 11) and (None, 1000, 11) are incompatible`
I am developing an LSTM model for multi-label text classification with 11 categories.
The keras.tuner gives me an error while the model without tunning runs well.
I would really appreciate if someone can point out the issue behind these errors. I…
Pranav Pandit
- 119
- 9
0
votes
1 answer
Model summary is empty
I am trying to build a neural network using keras functional API and to train the network I am using keras tuner. The model consists of some embedding layers and then some dense layers:
import pandas as pd
import numpy as np
from keras.models import…
egginald
- 11
- 3
0
votes
0 answers
Custom loss with external parameters in Keras Tuner
While my code runs without any problems with Keras Tuner and standard loss functions like 'mse' I am trying to figure out how to write a custom loss function that accept an external argument in addition to true and forecasted y to use inside Keras…
Stefano Ricci
- 1
- 1
0
votes
1 answer
LSTM - RuntimeError: Too many failed attempts to build model
I am trying to use keras tuner to tune an LSTM neural network to detect if an article is a fake news or not, using a kaggle dataset.
However, I keep getting this error: RuntimeError: Too many failed attempts to build model
I have also tried to use…
Nick
- 1
0
votes
1 answer
Hyperparameter optimization of transfer learning model with Keras Tuner
I want to perform hyperparameter optimization on my transfer learning model using Keras Tuner. I am not sure how to do this since I have two stages of training,
freezing the whole network and only train the last layer to converge to the new classes…
masie
- 1
- 1
0
votes
1 answer
How can I get a stateful LSTM to reset its states between epochs during a Keras Tuner search?
I am trying to tune a stateful LSTM using Keras Tuner. I have the code working and it is able to train models, but I still can't figure out how to get the model to reset states between epochs. Normally I would train for 1 epoch at a time in a loop…
WVJoe
- 515
- 7
- 21
0
votes
1 answer
InvalidArgumentError: logits and labels must have the same first dimension, got logits shape [1,10] and labels shape [40]
I'm using Keras-Tuner to auto-identify the best parameters for my CNN. I am using Celeb_a dataset.
you can find the code I am using here
When I try to run it I get the error below.
InvalidArgumentError: logits and labels must have the same…
Jean Camargo
- 340
- 3
- 17