All Questions
Tagged with tf.keras scikit-learn
19
questions
9
votes
4
answers
7k
views
Cannot clone object <tensorflow.python.keras.wrappers.scikit_learn.KerasClassifier object
This is with regards to TF 2.0.
Please find below my code that performs GridSearch along with Cross Validation using sklearn.model_selection.GridSearchCV for the mnist dataset that works perfectly ...
5
votes
1
answer
2k
views
How to use KerasClassifier validation split and using scitkit learn GridSearchCV
I want to try to test some hyperparameters, thats i want to use the GridSearchCV, because it seems like thats the way to do it.
But i also want to use the validation split. To use Callsbacks like ...
- 326
2
votes
2
answers
2k
views
ImageDataGenerator.flow_from_directory to a dataset that can be used in Kfold
I am trying to use the cross validation approach for the model I use for classifying images into 3 classes. I use the following code to import images:
train_datagen = ImageDataGenerator(rescale=1./255)...
2
votes
1
answer
1k
views
how to create train, test & validation split of tf.data.Dataset in tf 2.1.0
the following code is copied from :
https://www.tensorflow.org/tutorials/load_data/images
the code aims to create dataset of images downloaded from the web and stored into folders depending upon ...
1
vote
1
answer
110
views
ImageDataGenerator Predict Class - Why are the predictions not correctly converting from probabilities to predicted class?
I have a directory set up like this:
images
-- val
--class1
--class2
-- test
--all_classes
-- train
--class1
--class2
In each dir is a set of images. I want to predict if each ...
- 1,447
1
vote
1
answer
1k
views
How to export a model created from KerasClassifier and Gridsearchcv using joblib or pickle?
def network(optimizers='rmsprop'):
model = tf.keras.models.Sequential()
model.add(tf.keras.layers.Embedding(vocab_size, 100, weights=[embedding_matrix], input_length=length, trainable=True))
...
- 421
1
vote
0
answers
107
views
Kernel dying in juypter notebook
My kernel is dying everytime i run the following code. There is no error or anything so i dont know what is happening. I am running python 3.8.8 on the new macbook m1.
from sklearn.model_selection ...
- 29
0
votes
1
answer
692
views
Missing Positional Argument X
I'm currently working to set up a randomized search to help find the best parameters for a model. But I've hit an error that I can't find anywhere on google: Missing positional argument 'x' in the ....
- 319
0
votes
1
answer
8k
views
AttributeError: 'numpy.ndarray' object has no attribute 'transform'
I want to create a sklearn pipeline that consists of two steps:
Custom transformer function
Keras classification model
This is my data set (of course, I'm providing a reduced subset to show the data ...
- 2,928
0
votes
1
answer
509
views
KerasClassifier object has no attribute model
I'm using CalibratedClassifierCV to calibrate the probabilities of my CNN model. I'm using the following code:
from tensorflow.keras.models import load_model
from tensorflow.keras.wrappers....
- 6,092
0
votes
0
answers
40
views
RandomForestClassifier should be a binary classifier
I have written a code that performs rogue device detection using Random Forest and Decision Tree classifiers. The models were successfully trained. However, it returns an error at inference: "...
- 47
0
votes
0
answers
24
views
Class_Weight for Multiclass classification in Neural Network
I am working on a Neural Network for Multiclass classification where class labels are -1,0,1.
These class labels imbalanced hence I am using class_weights. And I am getting below error message-
...
- 57
0
votes
0
answers
28
views
My True/false statements in my dataframe change overtime in the code (tenserflow.kerax)
So im ussing NASA asteroids dataset with tenserflow.kerax for some university assignment
The first thing i wanted was to standardize the data so i use
(1)
df = dfprime
ss = StandardScaler()
df_scaled =...
0
votes
0
answers
92
views
What do KerasRegressor object at 0x7f466c02fe20> & rv_frozen object at 0x7f46ed175580> thrown by sklearn.model_selection.RandomizedSearchCV.fit mean?
I am trying to optimize the hyperparameters of a neural network in (Cent OS 8, Anaconda, Jupyter Notebook, Python) with the method sklearn.model_selection.RandomizedSearchCV.fit but the call to this ...
- 65
0
votes
0
answers
125
views
Loss not changing and accuracy remains 0 after calling fit()
I'm new to keras and tensorflow, I have a model that I am trying to train where the loss does not change after epoch #1.
my data is the sequence of numbers which I want NN to learn and predict the ...
- 63
0
votes
0
answers
303
views
How to use sklearn.metrics.classification_report with generator?
I would like to use sklearn.metrics.classification_report but I cannot use it directly as my testing data is provided by a python generator. The python generator is given below.
Let me give you the ...
- 190
0
votes
0
answers
97
views
SKlearn votingClassifier() cloned model showing NOneType for parameter
I have a base estimator class I created that trains a NN from TF.keras
something like:
TF_NN(BaseEstimator):
def __init__(self,...,parameter='defaultstring', metric='accuracy', ...):
...
- 337
-2
votes
1
answer
158
views
What should be the input-shape number when i am adding the input layer in my ANN, considering that I have preprocessed the data with OneHotEncoder?
My dataset has categorical and numerical features. The dataset has 7 independent variables and 1 dependent variable (called as a product). The dataset looks like this:
In general, there are 3 ...
- 33