Questions tagged [tensorflow]
TensorFlow is an open source library for machine learning and machine intelligence. It is developed by Google and became open source in November 2015.
45
questions
3
votes
1
answer
124
views
Keras Tuner Subclass for Time Series Cross-Validation
Custom Keras Tuner with Time Series Cross-Validation
I have written my own subclass of the default Keras tuner Tune class.
Objective: I needed a way to incorporate ...
1
vote
1
answer
105
views
Custom neural network implementation in TensorFlow to compare normalisation vs. no normalisation on data
I am performing a sports prediction multi-class classification problem, and wanted to compare the differences in model performance between normalised and non-normalised data. You can see the 2 ...
3
votes
1
answer
100
views
Constraining monotonicity in the loss function during training
I have a neural network that I am training on a loss function composed of two terms (i.e. loss = loss1 + loss2). Ideally, I would like for both ...
1
vote
0
answers
104
views
Train a Keras model to recognize and predict speech in real-time using microphone as audio source
Please help me optimize this script. I'm running it in Google Colab GPU runtime. I've implemented many optimizations but they worsened it. I need serious help. I have to submit my project in 3 days!. ...
1
vote
0
answers
785
views
Object detection YOLO v1 loss function implementation with Python 3 and TensorFlow 2.x
About the code
Object detection YOLO v1 loss function implementation with Python + TensorFlow 2.x. It based on the Pytorch implementations below and re-implemented with TensorFlow based on my ...
1
vote
0
answers
55
views
prediction student performance using conventional neural network CNN
I have to do an experiment to predict student performance using Deep Learning. We can try applying these models and compare the accuracy, precision, recall, and F1 score. (Also, we can try only fully ...
1
vote
0
answers
32
views
RESNET machine learning code with TensorFlow
I am a PhD student working on a machine learning project with binary classification and RESNET architecture in TensorFlow. I believe I have done everything correctly but I am looking for some ...
8
votes
2
answers
1k
views
Face tracking with recognition and age/gender detection
This program loads a video, detects and tracks faces in the video and detects the estimated age and gender of each person. The objective is to collect data on the number of unique people in a video ...
2
votes
0
answers
66
views
xagents - implementations of reinforcement learning algorithms
Description
It is valid to say, this work started and evolved from a standalone DQN implementation, which I included in an old question, to a mini-library xagents, housing 7 re-usable tensorflow-based ...
1
vote
0
answers
42
views
The best tensorflow neural net I got so far for iris dataset
Compared to my another post Logistic Regression for non linearly separable data which uses one-layer net, i.e. Logistic Regression to classify the iris data set, this post is to discuss the tensorflow ...
2
votes
0
answers
497
views
How to avoid retracing in tensorflow when predicting scores for inputs with different sizes
I use the following code in order to assess the quality of an audio, which is based on this original-project: MOSNet. I call compute_mosnet_score() in a loop with a ...
3
votes
0
answers
68
views
Toy neural network give poor results [closed]
I'm a beginner both in Python and Tensorflow.
I made a toy neural network to learn both.
The objective of the NN is to identify the module c, or separation between lines defined by random points, and ...
2
votes
0
answers
814
views
Assigning parallel workers to predict from keras model using concurrent.futures
I am working on a Reinforcement learning project, where I have to gather a lot of data using a TensorFlow model. During the data gathering, the weights of the model do not change. So, I am using ...
1
vote
0
answers
34
views
Industrial Practices for Time-Series Forecasting
Hi I have wrote a code here for predicting temperature across months. This is the dataset that I was using: https://www.kaggle.com/sumanthvrao/daily-climate-time-series-data
I have used a SARIMA model ...
2
votes
0
answers
24
views
Transfer learning CNNs for image classification in TensorFlow
This code works, and I'm pretty sure it's mathematically/algorithmically correct:
...
2
votes
0
answers
1k
views
Playing pong (atari game) using a DQN agent
I trained a DQN agent using tensorflow and OpenAI gym Atari environment called PongNoFrameskip-v4, but this code should be compatible with any ...
10
votes
2
answers
354
views
Convert an English sentence to German using Bahdanau Attention
Context
I am following this tutorial .
My mission is to convert an English sentence to a German sentence using Bahdanau Attention.
Summary of the Code
I first took the whole English and German ...
2
votes
0
answers
110
views
Cosine Similarity Matrix Loss Function
I am currently implementing this paper on generalised end to end loss: https://arxiv.org/pdf/1710.10467.pdf
A batch of N speakers and M utterances are fed to the model which outputs an embedding ...
2
votes
1
answer
2k
views
Keras stacked LSTM model for multiclass classification
I am working on a multiple classification problem and after dabbling with multiple neural network architectures, I settled for a stacked LSTM structure as it yields the best accuracy for my use-case. ...
2
votes
0
answers
47
views
Converting tensorflow v1 to v2 without compatability.v1
I am in the process of converting this code predictor.py located here to tensorflow v2 with Python 3.7. I want to do this conversion part by part. So from the ...
3
votes
0
answers
196
views
Doing image compression with Neural Network AutoEncoders
I wanted to create an image compressor using Machine Learning and started work on an "AutoEncoder". This is a type of Neural Network which takes in the image and creates a compressed vector form.
It ...
1
vote
1
answer
44
views
Tensorflow Python ML to Detect Emotion [closed]
I've created an application to predict emotions. But I think the application is being over fitted. And I cannot figure out how to solve the overfitting. I'm using a small data set of 107 images spread ...
2
votes
0
answers
112
views
ML text generating code with Python and Tensorflow
I wanted a simple code review for improvement to increase the efficiency of my text generating model. This model is taken from the official TensorFlow site but is being trained on different datasets. ...
3
votes
1
answer
36
views
Creating generator object with image augmentation to train Convolutional Neural Networks with Keras
I am currently self-studying on Python generator object and use it to generate training data and do augmentation on-the-fly, then feed it into Convolutional Neural Networks.
Could anyone please help ...
3
votes
0
answers
477
views
PPE object detection with tensorflow and opencv with rtsp streams
I am working on an object detection API implemented in Tensorflow 1.14 and OpenCV 4.1, where my task is to recognize personal protection equipment (PPE) worn by workers at various construction site ...
4
votes
0
answers
70
views
Evaluating a previously calculated gradient function
I am trying to perform optimization using a surrogate model instead of the real function and for that, I need the gradient of my LSTM model with respect to the input. In this case, I have 3 features ...
16
votes
2
answers
423
views
MNIST Deep Neural Network in TensorFlow
I have been working on this code for a while and it gave me a lot of headaches before I got it to work. It basically tries to use the MNIST dataset to classify handwritten digits. I am not using the ...
5
votes
0
answers
61
views
Tensorflow loop to analyze gradients derived from MRI and PET images
The code shown below takes the partial derivative of each pixel of the output fused image of a neural network with respect to input image of the neural network using tensorflow's ...
4
votes
1
answer
185
views
U-Net: A TensorFlow model
What I want to know
I am writing a ML model called U-Net with Python (and TensorFlow). My question is not about the machine learning or Tensorflow, I want to know the best structure of the code.
I ...
3
votes
0
answers
64
views
TensorFlow regressor to predict probability of winning, given a current score
This is a TensorFlow regressor that tells me that if you get x score, you will have x% to win a game in x game(game is not important).
Doing this as a project to learn tensorflow.
...
2
votes
0
answers
1k
views
Simple Self-Organizing Map (SOM) in Tensorflow
I've implemented a self-organising map in Tensorflow's low-level API. After testing with sklearn's Iris data, the results seem correct. I did implement the algorithm also using NumPy before converting ...
3
votes
0
answers
1k
views
A simple toy ResNet model and its implementation
I want to understand how resnet works also called us residual networks and I understand it better when I code one myself. I tried to find a simple implementation of resnet in the web but most I found ...
1
vote
0
answers
823
views
Tensorflow model for predicting dice game decisions
For my first ML project I have modeled a dice game called Ten Thousand, or Farkle, depending on who you ask, as a vastly over-engineered solution to a computer player. You can find the complete game, ...
2
votes
0
answers
578
views
Principal Component Analysis in Tensorflow
To learn the low-level API of Tensorflow I am trying to implement some traditional machine learning algorithms. The following Python script implements Principal Component Analysis using gradient ...
3
votes
1
answer
416
views
BipedalWalker-v2 one-step actor-critic agent trains slow
I'm trying to solve the OpenAI BipedalWalker-v2 by using a one-step actor-critic agent. I'm implementing the solution using python and tensorflow. My question is whether the code is slow because of ...
3
votes
0
answers
4k
views
Code for Training a Handwriting Recognition Model
I just made my machine learning code work a few days ago and I would like to know if there's a way to improve my code.
Before I get to the implementation of the tasks at hand, I would like to ...
4
votes
0
answers
205
views
Distributed TensorFlow | VGG 16
I am trying to develop a VGG 16 model distributed over a single server.
I have one available GPU server with 1 CPU and two GPU cards. I have the code to treat them as different servers and implement ...
8
votes
1
answer
2k
views
Speech Recognition Part 3: Training the Neural Network
The last part of my speech recognition series: finally training my network. Here's the dataset I did it with (self-generated, small I know), and the code I used.
After running this code (takes ...
4
votes
0
answers
278
views
Linear Regression in Tensorflow
I am a machine learning newbie and recently I implemented (or at least tried to implement) a linear regression model in tensorflow. I would love to know how I can improve my code:
...
5
votes
0
answers
159
views
Deep learning CNN for image recognition using tensor flow
This algorithm is a convolutional deep neural network used for image recognition.
I used the MNIST data set, which is a bunch of images from 0 to 9. As of right now, I have trained this image with ...
2
votes
0
answers
790
views
Optimize GPU usage for real-time object detection from camera with TensorFlow GPU and OpenCV
Trying to recognize objects real time using TensorFlow Object Detection API OpenCV using ssd_mobilenet_v1_coco_11_06_2017 model in GPU.
...
5
votes
0
answers
785
views
Low accuracy of LSTM model tensorflow [closed]
I am trying to learn LSTM model for sentiment analysis using Tensorflow, I have gone through the LSTM model.
Following code (create_sentiment_featuresets.py) generates the lexicon from 5000 positive ...
4
votes
2
answers
829
views
Python Script: Converts .tsv to TFRecord
The python code below converts a tab spaced values file (.tsv) into a TFRecord in hopes that this approach expedites future time spent loading the data. Is the performance of this task correct and ...
2
votes
0
answers
894
views
Implementing Adagrad in Python
I'm trying to implement Adagrad in Python. For learning purposes, I am using matrix factorisation as an example. I'd be using Autograd for computing the gradients.
My main question is if the ...
3
votes
0
answers
77
views
Tensorflow implementation of the Thomson model
I've implemented the Thomson model in Tensorflow and it seems to work very well. I'm repeating some computation by computing the other half of the symmetric distance matrix. I think, for a GPU based ...