Questions tagged [tensorflow]
For questions related to Google's open-source library for machine learning and machine intelligence. However, note that programming questions are off-topic here.
348 questions
0
votes
0
answers
4
views
When Using Bidirectional Encoders Should The Onedirectional Decoder Have Twice The Dimension (Autoencoders)?
Just so we can avoid misunderstandings in the root: In general an Autoencoder tries to capture the complexity of an input in a latent space that is unable to hold all that input. It then tries to ...
- 101
0
votes
0
answers
63
views
Use TensorFlow's model in OpenCV (C++)
I've trained a model to recognize some captchas and the model is doing great. I've trained it using this tutorial (actually I just stole the code, tweaked it and run :) ). Now, I'd like to export it ...
- 1
0
votes
1
answer
41
views
CNN Fixed Predictions
I’m building a Keras model based on MobileNetV2 for frame-level prediction of 6 human competencies. Each output head represents a competency and is a softmax over 100 classes (scores 0–99). The model ...
0
votes
0
answers
20
views
Trained ML model is slowing down python code execution
I’m running a real-time inference loop in Python 3.12.3 with a pre-trained variational autoencoder (VAE) implemented in Tensorflow. Although I load the model once outside my main loop, each call to ...
- 1
1
vote
1
answer
53
views
How can STFT layer be trainable in Keras 3?
A traditional STFT parameter is window size, where greater window size means higher frequency domain resolution but in trade off the time domain resolution. It makes sense that if window size became ...
0
votes
0
answers
52
views
Kaggle notebook from keras 2 to keras 3 problems
as the title suggests, I'm trying to convert a notebook in keras 3, but idk why it's not working properly.
This is the original notebook (tell me if it's better to put here the code), I'm trying to do ...
- 1
0
votes
0
answers
28
views
ANN poor NMSE issue: complex valued input and output discrete-time voltage data from third order static non-linear system
I'm currently working on training a neural network in Python to model a nonlinear system using complex-valued voltage data. My dataset comprises 3400 training samples, each consisting of 128 discrete ...
0
votes
0
answers
58
views
Why am I getting the same accuracy on validation data? - Python - Computer Vision - Deep Learning
I'm getting the same accuracy on validation data, and the accuracy on the training data varies little in every epoch.
The training data consists of 19670 images (14445: class 0, 5225: class 1). The ...
- 1
0
votes
1
answer
56
views
custom seuential layer which can iterate over each value in the input
I would like to make a custom layer which takes an image (2D) and does some math to each pixel and then passes this to the next layer.
I have below some psudo code which tries to implement this. How ...
- 19
0
votes
0
answers
92
views
Keras Model: Input Shape Mismatch Issue After Debugging Dimensions
I have a multi-input Keras model combining a text input and a numeric input. Both inputs are passed through Dense layers followed by Embedding layers, then concatenated and pooled using ...
0
votes
1
answer
87
views
How to Resolve Matrix Size Mismatch in TensorFlow Model Builder for Combined Text and Numeric Inputs?
I'm working on a Keras model using the Functional API that processes two inputs:
Text Input: A padded integer array with a shape of (32, 1149) (batch size 32, sequence length 1149). Example: [5, 10, 3,...
0
votes
1
answer
79
views
How to print intermediate shapes in a Keras Functional API model_builder during graph construction?
I am trying to debug my model_builder function in Keras Functional API by printing the shapes of intermediate tensors. However, none of the methods I have tried so far seem to work as expected.
Here's ...
1
vote
2
answers
260
views
Why are PyTorch and TensorFlow the most widely used frameworks?
Even through there are several others, what's special about these two that make them so popular?
user88306
1
vote
1
answer
101
views
Regression model is doing exceptionally very well on time series
I have the following task to do: I have time series data. Training by the consecutive 3 days to predict the each 4th day. Each day data represents one CSV file which has dimension 24x25. Every ...
- 123
1
vote
0
answers
31
views
What Policy/Agent and Observation Spec To Use For TensorFlow Agents For Video Game Platformer?
I'm trying to create a model to beat a video game platformer I made a few months ago. In the game, the platforms scroll down from the sky and the player has to keep jumping to them to avoid touching ...
- 11