Category "keras"

TensorFlow optimisation during running model speed up Predict

I want to disable a computation of several filters during Predict call with Tensorflow 2 and Keras. Do i have to modify the source code of Tensorflow to achieve

The method np_utils.to_categorical give me an error

np_utils.to_categorical Keras method give me an error when i gived it a a vector of [962] element which contain 3 classes [1,1,1,...,2,2,2,...3,3,3]. The used

How to split a Keras model, with a non-sequential architecture like ResNet, into sub-models?

My model is a resnet-152 i wanna cutting it into two submodels and the problem is with the second one i can't figure out how to build a model from an intermedi

Moving averaging of Loss during Training in Keras

I am using Keras with TensorFlow to implement a deep neural network. When I plot the loss and number of iterations, there is a significant jump in loss after ea

Unable to run anipose due to ImportError: cannot import name 'keras_export' from 'tensorflow.python.util.tf_export'

I've been attempting to install and run anipose in Ubuntu 18.04 I keep getting the same import error though I've made sure keras is installed. I've also searche

Missing val_acc after fitting sequential model

I am missing information about the 'val_acc' attribute when I fit a compiled sequential model. I have a sequential model that is compiled with 'accuracy' metr

ValueError: Input 0 of layer hiddenL1 is incompatible with the layer: its rank is undefined, but the layer requires a define rank

I am trying to create a sequential keras model with custom weights. The weights come from a row in a numpy array. When running the code I get the error: Value

How to predict the stock price for the next 30 days after the LSTM model has predicted the test_set?

I've used a data-set containing closing price of a particular stock for 5 years.It has closing prices for 1231 days. The train_set consists of 987 days and the

How to skip problematic hyperparameter combinations when tuning models using Keras Tuner?

When using Keras Tuner, there doesn't seem to be a way to allow the skipping of a problematic combination of hyperparams. For example, the number of filters in

How to define a specific keras layer weight as non-trainable?

Let's suppose we have a neural nets with three layers : Inputs > Hidden > Outputs and consider that the weigths between the Hidden and Outputs layers are

Difference between 'multi output' vs 'raw' in keras 'flow_from_dataframe'

I'm not sure about when to use raw vs multi output in the keras flow_from_dataframe class_mode parameter, as by the looks of it, they both provide a way to clas

broken tensorflow keras function

I have this function that used to work and broke when I updated or upgrade to tensorflow 2. def df_to_dataset(dataframe, shuffle=True, batch_size=32): datafra

TypeError: Unable to convert function return value to a Python type! The signature was () -> handle

I get an error when I import the TensorFlow. I tried to reinstall it but still, I keep getting this error---> TypeError: Unable to convert function return va

Compilation deep learning model is important if we unfreez the layers for fientuneing?

I am classifying a medical images dataset into normal vs abnormal where I am applying transfer learning with ResNet50v2. I did a little change in the last laye

module 'tensorflow.python.keras.optimizers' has no attribute 'SGD'

I am working with python 3.9, tensorflow 2.7.0 with a modified version of Mask RCNN https://github.com/leekunhee/Mask_RCNN/blob/tensorflow2.0/mrcnn). I am worki

module 'tensorflow.python.keras.optimizers' has no attribute 'SGD'

I am working with python 3.9, tensorflow 2.7.0 with a modified version of Mask RCNN https://github.com/leekunhee/Mask_RCNN/blob/tensorflow2.0/mrcnn). I am worki

What is the best approach for storing multiple vectors per person for face recognition

I want to make a face recognition for employees as work. I already have system that gets image from cameras and outputs face embeddings (128-dimensional vectors

When using padding in sequence models, is Keras validation accuracy valid/ reliable?

I have a group of non zero sequences with different lengths and I am using Keras LSTM to model these sequences. I use Keras Tokenizer to tokenize (tokens start

ValueError: Shapes (None, None) and (None, 28, 28, 10) are incompatible

I am working on a neural network to recognize handwritten digits using the MNIST digits dataset. I wanted to use ImageDataGenerator from Keras to see if I could

Error: import tensorflow.keras.backend as K could not be resolved Pylance(reportMissingImports)

I'm using tensorflow 1.15.0 in docker container and have issue in importing keras sub-modules. from tensorflow import keras import tensorflow.keras.backend as