Category "keras"

Can't use Keras MeanIoU to train semantic segmentation model

I'm working on a binary semantic segmentation problem. I built an UNet model with MobileNetV2 backbone. Here is my model code: def upsample(filters, size, apply

converting recurrent to bi recurrent

I want to convert this below RNN into bidirectional RNN, how can I do that? #Call the function and compile the model. model = RNN() model.summary() model.compil

Keras model with 2 inputs

I am dealing with a binary classification problem that feeds a network with two inputs (images), model_vgg16_conv = VGG16(weights='imagenet', include_top=False)

How to generate a sentence around words in Keras?

I know that how to generate next word in keras with lstm but how to predict previous word for example If you have two words like "car" and "running" then It sho

Why the result of categorical cross entropy in tensorflow different from the definition?

I am testing outcomes of tf.keras.losses.CategoricalCrossEntropy, and it gives me values different from the definition. My understanding of cross entropy is: d

Why is VGG16 giving lesser no. of total parameters?

from tensorflow.keras.applications import VGG16 pre_trained_model = VGG16(weights='imagenet', include_top=False, input_shape=(224, 224, 3)) model = Sequential

'ListWrapper' object has no attribute 'get_config' error when doing gridsearch

I have to do grid search on my DNN. But I am getting an error on GridSearchCV function. Here is the code for creating and compiling the model I used and also wh

Low accuracy after testing hyperparameters

I am using VGG19 pre-trained model with ImageNet weights to do transfer-learning on 4 classes with keras. However I do not know if there really is a difference

How to interpret MSE in Keras Regressor

I am trying to build a model to predict house prices. I have some features X (no. of bathrooms , etc.) and target Y (ranging around $300,000 to $800,000) I have

ImportError: Imageio Pillow requires Pillow, not PIL! on M1 Mac

This question might have been asked several times but I am not able to resolve the error. I have pillow, imageio and other libraries installed on my M1 Mac. But

ImportError: Imageio Pillow requires Pillow, not PIL! on M1 Mac

This question might have been asked several times but I am not able to resolve the error. I have pillow, imageio and other libraries installed on my M1 Mac. But

How to input a history of vectors to LSTM based network instead of a single vector?

I am trying to predict a simple pattern using LSTM based network. I input a single vector and get the output vector with the same shape as a prediction. How can

Google Colab error: Import "tensorflow.keras.models" could not be resolved(reportMissingImports)

import tensorflow as tf tf.__version__ !sudo pip3 install keras from tensorflow.keras.models import Sequential from tensorflow.keras.layers import Dense, Conv

one classifier for multi-labels with autokeras, data table

i have a data table with 5 labels. i want to use autokeras to Build one classifier that predict all the labels by same X. i tried: clf0 = ak.StructuredDataCla

Models in Tensorflow Federated get stucked at 0.1 accuracy

I'm trying train a federated model for the mnist dataset. I am using the code avaible at https://www.tensorflow.org/federated/tutorials/simulations for the setu

Why do I get this error while calling predict in Keras?

I'm a newbie to Tensorflow, I've done many models but today when calling predict I get this error : ValueError: Exception encountered when calling layer "sequen

Invalid Argument Error / Graph Execution Error

I'm having multiple errors while running this VGG training code (code and errors shown below). I don't know if its because of my dataset or is it something else

ValueError: `logits` and `labels` must have the same shape

I'm trying to use Imagenet V2 with transfer-learning for multiclass classification (6 classes), but getting the following error. Can anyone please help? ValueEr

Error when loading a custom layer from config

I have a custom preprocessing layer which basically takes the input and applies the preprocessing function of a pretrained network coming from tensorflow.keras.

tf.data pipeline from large numpy arrays for a multiple input, multiple output Keras model and distributed training

This question relates to the optimal setup for a multiple-input multiple-output Keras (Tensorflow) model given corresponding numpy arrays. For example, suppose