Category "tensorflow"

Unable to run tensorflow lite on ESP32 and Arduino Due both are 32 bits microcontrollers

I got two microcontrollers, one ESP32 and one Arduino DUE R3, both has an architecture of 32 bits and should be able to run a tensorflow lite model, however I t

pip install gym package but import error given

I created my tensorflow env using conda (MacBook Pro), and installed manually all the tensorflow required packages following the apple developer website: https:

What is the from repeating same layers in AI architecture

I know that in ai models lstm is used to extract features from data and dropout is used to focus in the main ones, but i can't understand why people used to rep

Setting up keras-rl2 on my M1 Macbook Pro

I am working on a project on Reinforcement Learning - and completely new at this. I installed keras-rl as pip install keras-rl, however it caused an error as ma

strongly different accuracy-values from model.evaluate(test_set) and from the sklearn classification_report

i'm experimenting on colab in image-classification with images of 32x32 pixels; i have 248 pics for training and 62 for testing (much too less, i know, but for

ValueError: `logits` and `labels` must have the same shape, received ((None, 250, 1) vs (None,)). What is wrong?

I'm new to ML and im trying to make a simple MLP work using serialization. I'll be using 2 layer MLP and binary outcome. (yes/no) Could someone explain what i'm

How to create custom tensor value with shape (b,n,m)?

How to create custom tensor value with shape (b,n,m) I see the cppflow::fill method but it allows inserting 1 value which fills the whole same value in the shap

Thread tf_data_private_threadpool creation via pthread_create() failed. with Tensorflow

Tensorflow: 2.9.0rc2 When I am running code from https://www.tensorflow.org/hub/tutorials/wav2vec2_saved_model_finetuning I get the following error: 2022-05-14

Why do I get worse results in Java than in Python when using the same Tensorflow models?

Introduction: For education purpose I developed a Java class that enables students to load Tensorflow models in the Tensorflow SavedModel format and use them fo

VAE reconstruction loss (MSE) not decreasing, but KL Divergence is

I've been trying to create an LSTM VAE to reconstruct multivariate time-series data on Tensorflow. To start off I attempted to adapt (changed to Functional API,

Tensorflow - Edit image to print out location of bounding boxes?

I have an android application and I've integrated my own custom tensorflow lite model. I can print out the object category and probability score but I'm at a lo

Is it there something wrong with tensorflow?

Hello I have being using tensorflow and keras for a while. I use this packages to build neural networks. As I work on CPU I was used to recive a message like th

Issues with IPython magics [TerminalIPythonApp] WARNING unrecognised alias

I recently got my code to function and was so proud of myself for figuring out the challenges experienced then. However, I reviewed some stuff in connecting wit

Tensorflow migration problem regardless defining the operations tensorflow.python.framework.ops

I am running a model from github and I already encountered several errors with pathing etc. After fixing this, I think the main error for now is tensorflow. Thi

Convert a pth pytorch file to an onnx model

I'm trying to convert a PyTorch model(pth file containing weights) to an onnx file then to a TensorFlow model since I work on TensorFlow. to then fine-tune it.

Facing These Issues When Generating IOS Build

These are the Errors while generating The IOS build TFlite Error (2.7.0) This is the current package which I am using in my project The Tflite Issue has been

JSONDecodeError: Expecting value: line 1 column 1 (char 0) on Raspberry Pi's Imager (GNU/Linux)

I've made an image recognition neural network in windows. Tested it, and it works (hurray!). It uses tensorflow. Now I wanted to transfer it on Raspberry Pi's I

model.predict_classes is deprecated - What to use instead?

I have been trying to revisit my python code for prediction on neural network and i realized after running the code that model.predict_classes is deprecated sin

Inspite of my model being properly trained and dumped in an pickle file and getting an unwanted error while testing the file using cv2.VideoCapture

My model is already trained and is saved in model_trained.pkl file. And I'm trying to test the same using video captures. But getting error "FileNotFoundError:

Another approach to create and form Tfrecord for training and testing data

I am currently using this command to create a train.record file !py generate_tfrecord.py -x C:/Users/Desktop/dataset/Workspace/images/train -l C:/User/Desktop/d