Questions tagged [keras]
Keras is a neural network library providing a high-level API in Python and R. Use this tag for questions relating to how to use this API. Please also include the tag for the language/backend ([python], [r], [tensorflow], [theano], [cntk]) that you are using. If you are using tensorflow's built-in keras, use the [tf.keras] tag.
keras
42,478
questions
0
votes
0
answers
8
views
CGAN Training Issues: Discriminator Accuracy at 100% and Generator Loss at 0
I am trying to train a Conditional Generative Adversarial Network (CGAN) to generate synthetic leaf images. However, during training, my discriminator's accuracy quickly reaches 100%, and the ...
-1
votes
0
answers
6
views
How to save this RNN model and how use this to build api to translation?
I used sinhala english data set and trained it to translate sinhala english java related questions. It gives good training accuracy but problem is after save it unable to load and use it to develop ...
-2
votes
1
answer
16
views
Combine three trained binary classification models into single multiclassification model in keras
I have three trained binary classification models, they are trained with sigmoid activation at output layer.
First model returning probability scalar from 0 to 1 to check whether image is number ZERO ...
0
votes
0
answers
13
views
num_samples = set(int(i.shape[0]) for i in tree.flatten(data)) IndexError: tuple index out of range (Tensorflow)
When trying to train an Tensorflow LSTM I am getting the following error:
File "C:\Users\user\Documents\LSTM_Volatility.py", line 66, in <module>
model.fit(x_train , ...
0
votes
1
answer
22
views
Hide warnings and/or errors when importing Keras
My script imports the following Keras modules:
from keras.models import Sequential
from keras.layers import Dense, Input
from keras.utils import to_categorical
and every time the same warnings/errors ...
0
votes
0
answers
25
views
Input 0 of layer "dense" is incompatible with the layer: expected axis -1 of input shape to have value 36864, but received input with shape (190,1536)
I am trying to create a model for image classification for grayscale images. and got the error:
ValueError: Exception encountered when calling Sequential.call().
Input 0 of layer "dense" is ...
0
votes
0
answers
7
views
How to preprocess image for INT8 post training quantization?
I am working on a binary classification problem using DenseNet121 on Keras. The original model yields an accuracy of ~93% and when float16 quantized (PTQ), accuracy acceptably drops to ~90%. I was ...
0
votes
1
answer
31
views
Model.evaluate() returning a float, not a list
I have a multi-task neural network. I want to make sure that when I call Model.evaluate() on my model, that the score I see is the sum of the losses. However, it is returning a scalar rather than a ...
0
votes
0
answers
16
views
Cast error while training a keras model constructed using featurespace
I am new to machine learning and using tf/keras to build a simple model to train on Adult database which I downloaded from UCI.
The data has 14 features. I am using keras FeatureSpace API to contruct ...
0
votes
0
answers
21
views
Can you put target value in input x in keras lstm model?
In keras documentation:
Arguments x:
A tf.data.Dataset. Should return a tuple of either (inputs, targets) or (inputs, targets, sample_weights).
A keras.utils.PyDataset returning (inputs, targets) or (...
0
votes
0
answers
19
views
Custom Parametric Activation Function Leading to NaN Loss and Weights
I am trying to create a custom non-linear activation function, and use a 3 3 hidden layer neural network to do MNIST classification. When I use 'Relu' the network trains fine, but when I use my custom ...
0
votes
1
answer
31
views
Error converting Tensorflow model to CoreML model
NotImplementedError Traceback (most recent call last)
Cell In[19], line 1
----> 1 mlmodel = ct.convert(model, convert_to="mlmodel", source="tensorflow")
...
0
votes
0
answers
31
views
Error while exporting Tensorflow model to CoreML
'Sequential' object has no attribute '_get_save_spec'
import tensorflow as tf
import coremltools as ct
print(tf.__version__)
# Load your existing Keras model
model_path = "/Users/name/Desktop/...
0
votes
0
answers
17
views
Error when implementing SHAP on CNN model
So I am trying to implement SHAP to a CNN model I trained on an image dataset on Kaggle. But I keep getting the following Attribute Error:
--------------------------------------------------------------...
0
votes
0
answers
25
views
AttributeError: module 'keras.src.activations' has no attribute 'get'
I am running the following error when I try to optimize a LSTM using keras tuner in Python: AttributeError: module 'keras.src.activations' has no attribute 'get'.
I am using the following versions: | ...