Category "tensorflow"

How to speed up Tensorflow 2 keras model for inference?

So there's a big update nowadays, moving from TensorFlow 1.X to 2.X. In TF 1.X I got use to a pipeline which helped me to push my keras model to production. Th

TENSORFLOW: UNSUPPORTABLE CALLABLE

I am trying to build the following model but am getting this error when I am finally training the model and trying to get it's accuracy. It gets stuck when I am

TFlite model.process() sometimes needs input data TensorImage and sometimes TensorBuffer to process an image? Are there different image input data?

Some TFlite models model.process() seems to need TensorBuffer and other rather needs TensorImage . I don't know why? First, I took a regular TensorFlow / Keras

How to reset the state of an LSTM RNN after each epoch within Keras?

I have defined a stateful LSTM RNN, and I want to reset the state of the RNN after each epoch. I have found that one way to do this would be: n_epochs = 50 for

TypeError: 'AutoTrackable' object is not callable

I am trying to run inference on my trained model following this tutorial. I am using TF 2.1.0 and I have tried with tf-nightly 2.5.0.dev20201202. But I get Type

Tensorflow classification predictions

I'm dealing with a simple classification problem and I'm new to it. I want it to give results like 0 and 1, but it gives a percentage ending as below. how can i

TensorFlow : failed call to cuInit: CUDA_ERROR_NO_DEVICE

My test : import tensorflow as tf hello = tf.constant('Hello, TensorFlow!') sess = tf.Session()` Error : c:\l\work\tensorflow-1.1.0\tensorflow\stream_execut

How does one invert an encoded prediction in Keras for model serving?

I have a Keras model in which i have successfully added a StringLookUp pre-processing step as part of the model definition. This is generally a good practice be

Tensorflow - Value Error in model.fit - How to fix

I am trying to train a Deep Neural Network using MNIST data set. BATCH_SIZE = 100 train_data = train_data.batch(BATCH_SIZE) validation_data = validation_data.b

Using a 2d kernel on 1d input in a convolutional network

I am trying to create a TasNet model, which is an audio separation network from the original paper. In section 2.2.1 they discuss how the encoder is going to ha

I can't run tf_upgrade_v2 to migrate to tensorflow 2

I try to do the following steps to migrate from TensorFlow 1 to TensorFlow 2: https://www.tensorflow.org/guide/upgrade. I can do this in Google Colab but I can'

NotImplementedError: Cannot convert a symbolic Tensor (2nd_target:0) to a numpy array

I try to pass 2 loss functions to a model as Keras allows that. loss: String (name of objective function) or objective function or Loss instance. See losses. I

Does TensorFlow Lite for Microcontrollers support Google Edge TPU?

I already know that TensorFlow Lite (TFL) supports the Google Edge TPU, for instance through the Coral Dev Board (Linux required). However I'd like to know whet

How to insert dropout layers after activation layers in a pre-trained non-sequential model using functional keras API?

I am working on a modified resnet, and want to insert dropout after activation layers. I have tried the following but due to the model not being sequential, it

TypeError: Failed to convert elements of SparseTensor to Tensor

TypeError: Failed to convert elements of SparseTensor(indices=Tensor("DeserializeSparse:0", shape=(None, 2), dtype=int64), values=Tensor("DeserializeSparse:1",

Deep learning result graph is is limited to the average area

] You can check the Network Model and Result from the Photos. Result datas are stuck in the "average band" and can't forecasting the exact value. I used a 3ye

Is there a way to convert a list of dict back to tf.data.Dataset?

I used tfds.load to load Cityscapes dataset. The tf.data.Dataset object is enumerable and returns a dict for each enumeration. I added another value to each dic

TensorFlow static C API library - how to link with 10 sub-dependencies?

I am trying to link with static C API version of the TensorFlow library. I built the static library using the following commands: // get the sources git clone h

Tensorflow Op: how to include libtensorflow_framework.so?

I followed the instructions of this tutorial: https://www.tensorflow.org/extend/adding_an_op#implement_the_gradient_in_python. There is this comment provided: g

TypeError: <lambda>() got an unexpected keyword argument 'dtype' with keras

I am running ANFIS algorithm on iris dataset. While adding fuzzylayer to the model i am getting error like below: TypeError: <lambda>() got an unexpected