Category "keras"

AttributeError: 'float' object has no attribute 'dtype'

When I try to use a custom activation function in keras (2.2.5), I create a new activation function gelu. add it in activations.py : from . import backend as K

Follow-up question regarding a Keras model issue

So about a week ago I posted this question: Issues running a Keras model with custom layers. The suggestion there was to try to make this question smaller and t

A `Concatenate` layer requires inputs with matching shapes except for the concatenation axis. Received: input_shape=[(None, 28), (None, 28, 28)]

""" Defining two sets of inputs Input_A: input from the features Input_B: input from images my train_features has (792,192) shape my train_images has (792,28,28

@tf.function( input_signature ) on an object's method defined outside of a class scope

Say I have a Custom Layer : class Custom_Layer(keras.layers.Layer): def __init__(self, **kwargs): self.w_0 = tf.Variable(tf.random_uniform_initializ

How can you save a keras model in 64bit format?

how can you save a keras model in 64bit format? This is able to 'put tensorflow' in 64bit 'mode' for the current runtime. But I've found that even just saving t

When predicting, shall we scale unseen inputs, and un-scale outputs of a model?

I am new to Machine Learning, and I followed this tutorial to implement LSTM model in Keras/Tensorflow: https://www.tensorflow.org/tutorials/structured_data/tim

model.predict yeilds more predictions than the number of outputs

I've created a multi-class image classifier using CNN. I am using the keras module specifically and I am using generators to fit and then predict 4 different cl

Binary image classification TypeError: Invalid keyword argument(s) in `compile()`

model.compile( optimizer= keras.optimizers.Adam(), loss= [keras.losses.SparseCategoricalCrossentropy(from_logits= True) ], metrices= ['accuracy']) mode

CNN model accuracy fluctuates

Tensorflow/Keras I have developed a CNN model to classify images as circle, triangle or square. However, my accuracy values have wide fluctuations. Is it someth

Can I feed intermediate result back into the CNN and get my final result? (update)

I am new to machine learning. I got the intermediate result of layer 31 of my CNN using the following code: conv2d = Model(inputs = self.model_ori.input, output

Reverse of keras Text Vectorization layer?

tf.keras.layers.TextVectorization layer maps text features to integer sequences, and since it can be added as a keras model layer it makes it easy to deploy the

Getting ValueError: Data Params Error when using masterful.trainer.train

I followed the tutorial here to try to train my model using CIFAR-100. But I'm getting this error. What do I do? ValueError: Data Params Error: The dataset labe

tensorflow keras savedmodel lost inputs name and add unknow inputs

I'm currently implement the sequantial deep matching model (https://arxiv.org/abs/1909.00385) using tensorflow 2.3. And I included the preprocessing layer as pa

How to ignore regularization losses from sub-layer of tf.keras.Model?

I want to distill knowledge from a teacher student to a student one, so I implemented a class named OCCSE that inherits from tf.keras.Model and accepts both tea

ValueError: Please initialize `TimeDistributed` layer with a `Layer` instance

I'm trying to build a model which can be trained on both audio and video samples but I get this error ValueError: Please initialize `TimeDistributed` layer with

Combine the outputs of a sub model intermediate layer and a parent model

I am trying to make a toy example work; there is a simple submodel: Model: "sub_model" _________________________________________________________________ Layer

What should be the class mode for training a multilabel classification model?

I am working on an image classification task to classify among cars and buses. The problem is that in most car images, there is buses in the background and vice

CNN accuracy plotting

I used a convolutional neural network (CNN) for training a dataset and I want to plotting accuracy for this. Before, I tried to use matplotlib but I couldn't su

Bert embedding layer raises 'ValueError: A target array with shape ' with BiLSTM in keras tensorflow

I've problems integrating Bert Embedding Layer in a BiLSTM model for text classification task. My dataset is in the form where each row has 2 columns: text and

got nan in keras tuner but it works when I train it

I trained my network several times and I already got some results. Then I found out about the Keras tuner and wanted to find the best hyperparameters with it. b