Category "tensorflow"

Keras history callback loss does not match with console output of loss

I am Training a cnn in Keras at the moment. Now I want to log the history of the training process for later visualizations, which I do with: history_callback =

Jupyter Kernel Dies Importing Keras

I am running an Apple Macbook with 16 GB of RAM and the M1 chip. I am trying to import Keras through the command: from tensorflow.keras.models import Sequential

tflite: get_tensor on non-output tensors gives random values

I'm trying to debug my tflite model, that uses custom ops. I've found the correspondence between op names (in *.pb) and op ids (in *.tflite), and I'm doing a la

ValueError: cannot reshape array of size 921600 into shape (224,224,3)

I trained a model using Transfer Learning(InceptionV3) and when I tried to predict the results it shows: ValueError: cannot reshape array of size 921600 into sh

ValueError: Input 0 of layer is incompatible with the layer: expected shape=(None, 224, 224, 3), found shape=(224, 224, 3)

"after converting the dataset to the tfrecord file format, I tried to train the model I created with it, but I couldn't convert it to the input format suitable

How to user a tensorflow server saved model with string tensor input to predict in the local machine?

I'm trying to run saved serving models in my local machine. However, it takes string tensor as input, and I'm having trouble converting the images to the correc

Unable to install 'Tensorflow Federated' on Apple Silicon M1

I have TensorFlow (2.8.0) installed and running on my Apple Silicon M1 MacBook. But facing dependency error on trying to install tensorflow-federated with the b

Ordering of batch normalization and dropout?

The original question was in regard to TensorFlow implementations specifically. However, the answers are for implementations in general. This general answer is

ValueError: Unknown metric function: cosine

i have been getting valueError issue. Currently using python3.9.11., keras2.8. if loss_init=="r2": parallel_model.compile(loss=custom_r2_loss, o

Can you mix keras.layers output with tensorflow operations?

I know that output of keras layers (like keras.layers.Dense()) produce so-called 'keras tensors'. Also, there are 'tensorflow tensors' that are produced by tens

training = False in Keras Sequential API

We can pass the training = False argument while calling the pre-trained model when using Keras Functional API as shown in this tutorial. How to implement the sa

Can't I simply copy and paste a program from a Jupyter notebook to a file.py?

It's weird, I wrote a functioning program on a Jupyter notebook and I wanted to have it in a normal python file with VSCode aswell. However, while copying and p

Object detection shows incorrect results on mask rcnn demo code

I have cloned https://github.com/akTwelve/Mask_RCNN and run the demo code. Everything works fine and runs correctly but the image processing part has incorrect

Keras model - high accuracy on natively executed code, fails to learn in colab

I am doing classification of citrus leaves dataset. I came up with a very basic model and ran it in Jupyter notebook on my machine, using anaconda. Exact same m

list indices must be integers or slices, not ListWrapper

I'm having some trouble with a pretty basic model. Am unable to create a pre-processing layer that simply normalizes all features. It is likely that my concept

Bazel build on cycle in dependency graph error

I am doing a bazel build for my project,i created a java_library rule and used at different places. but I am having this cycle in dependency graph: ERROR:

Validation accuracy not changing while loss is decreasing in keras image classification? [closed]

Image classification Problem I have two classes of images. Fake Real Dataset splitting detail is below. Total Training FAKE Images 3457 Total

Tensorflow my GPU is not recognized and There are many dll errors

I'm too new with tensorflow and keras, actually I'm trying first to install it correctly. I used Anaconda to make it easier. My question is probabily related to

Cant properly load saved model and call predict method

I am having trouble loading large model after saving. have tried all below saveing methods: tf.saved_model.save(model, model_save_path) model.save(model_save_pa

Tensorflow error TF error: module compiled against API version 0xe but this version of numpy is 0xd

RuntimeError: module compiled against API version 0xe but this version of numpy is 0xd Traceback (most recent call last): File "Tensorflow/scripts/generate_tfre