Category "tensorflow"

Dependencies issue while installing model card toolkit

Model Card --> Model Card toolkit I want to install a model card toolkit in my python virtual environment through this command: pip install model-card-toolk

Keras model `logits` and `labels` must have same shape (None, 2) vs (None, 1)

I have a keras model trained for occupancy detection of parking spaces, which I load using keras.models.load_model(PATH_TO_MODEL). The input for the model is a

Handwriting detection with keras : using a `tf.Tensor` as a Python `bool` is not allowed in Graph execution

I've tried to run a code example (hosted on keras.io) regarding the handwriting recognition task. While playing with the code, I faced a TensorFlow-related issu

Importing Adam and ImageDataGenerator on google colab failed

I'm implementing a UNet neural network but I'm having some issues while importing libraries. I found a solution for a couple of them, but I still have a problem

Dividing a large file into smaller ones for training

I have a very large file and I want to divide it into smaller ones for training. I've read about pickle files, so I split the large file into training-validatio

tensorflow load_weights( ) gives different prediction when loaded from a different path

I am training a DCN model for ranking purpose. After training, I use model.save_weights(filepath) to save the weights. And I load the weights using model.load_w

fedprox tensorflow federated (TypeError: cannot unpack non-iterable LearningProcessOutput object)

iterative_process = tff.learning.algorithms.build_unweighted_fed_prox( model_fn, proximal_strength= 0.5, client_optimizer_fn=lambda: tf.keras.optim

How can fit a keras model with a dataframe of numpy arrays?

I want to train a model with self-generated matrices (word vectors). My data have the following datatypes: print(type(X)) print(type(X[0])) print(type(X[0][0]))

How can i do many things to configure data with keras

I am a beginner learning deep learning by Keras. The ImageDataGenerator class in Keras and the flow_from_directory function made it easy to label images. But al

Unexpected behavior in tf.data.Dataset map function

I am working on a problem where I need to apply some transformation to my dataset using the map function that tf.data.Dataset provides. The idea is to apply thi

Model Accuracy is High but Val_Accuracy is low

I'm trying to improve my val accuracy as it is very low. I have tried changing the batch_size, the number of images being used for validation and training. Adde

Python-TensorFlow app FileNotFoundError: [Errno 2] No such file or directory

I am trying to test a simple Flask-TensorFlow Image Classifier app from docker container. The Docker containers were successfully deployed in an Ubuntu 22.10 EC

Failed to build h5py on mac M1

I am trying to install AlphaFold in a python virtual env. While trying to install dependencies, I get this error: ERROR: Could not find a version that satis

facing problems in installing tensorflow

I am facing problem in instaling tensorflow, please help me. Here is the error that I get: ^3.1 npm ERR! code 1 npm ERR! path C:\Users\dell\node_modules\@tensor

facing problems in installing tensorflow

I am facing problem in instaling tensorflow, please help me. Here is the error that I get: ^3.1 npm ERR! code 1 npm ERR! path C:\Users\dell\node_modules\@tensor

How to construct an equivalent multivariate normal distribution in tensorflow-probability, using TransformedDistribution?

How to construct an equivalent multivariate normal distribution in tensorflow-probability, using TransformedDistribution and tfb.ScaleMatvecLinearOperator? I'm

Import Error: cannot import name 'BatchNormalization' from 'keras.layers.normalization'

I am getting the following error message when trying to run this AlexNET python code. Traceback (most recent call last): File "C:\Users\PycharmProjects\Local-

Why is my accuracy is zero after set backbone trainable?

I trained my model with frozen backbone like: model.get_layer('efficientnet-b0').trainable = False Now, I unfreeze backbone, compile model, start training and

Add MC Holdout layers to trained model in Keras

I am looking for a solution for a problem that has arisen when building a generic ANN for image classification in R. What I want to do is either: Design and com

Why converted images now shown as grayscale?

I am working on image compression problem, i want to convert the images from 3 channel to 1 channle , i used tf.image.rgb_to_grayscale(img_data_array, name=None