Questions tagged [deep-learning]
Deep Learning is an area of machine learning whose goal is to learn complex functions using special neural network architectures that are "deep" (consist of many layers). This tag should be used for questions about implementation of deep learning architectures. General machine learning questions should be tagged "machine learning". Including a tag for the relevant software library (e.g., "keras", "tensorflow","pytorch","fast.ai" etc) is helpful.
deep-learning
27,892
questions
0
votes
0
answers
11
views
CGAN Training Issues: Discriminator Accuracy at 100% and Generator Loss at 0
I am trying to train a Conditional Generative Adversarial Network (CGAN) to generate synthetic leaf images. However, during training, my discriminator's accuracy quickly reaches 100%, and the ...
0
votes
0
answers
11
views
Detecting unknown defects in components using deep learning methods
The problem:
We need to determine from images of technical components whether the components are defective or not. We don't have images of defective components, and we can't know in advance what kinds ...
-1
votes
0
answers
7
views
Why does my Custom model made by training through Mediapipe Model Maker detect people as my object?
So i have a soft toy that i want to detect. I trained on around 100 images using Mediapipe Model Maker. The results are okish. The model is able to recognize my toy from the front view most of the ...
-2
votes
1
answer
17
views
Combine three trained binary classification models into single multiclassification model in keras
I have three trained binary classification models, they are trained with sigmoid activation at output layer.
First model returning probability scalar from 0 to 1 to check whether image is number ZERO ...
-3
votes
0
answers
16
views
Why we use concatenation in Unet? [closed]
why we use concatenation in unet and how did we get this grey lines. pls can someone elaborate this I'm new to this
I tried Unet architecture but I'm unable to understand how we get the grey lines i.e....
-1
votes
0
answers
32
views
Sign Language alphabet identification using Machine Learning giving wrong predictions [closed]
I tried to use both CSV files and images to train and test the model. When I run it, it gives 1.000 accuracy but it gives the wrong prediction when I test it using my camera. For example, it always ...
-1
votes
0
answers
16
views
How to Estimate GPU Memory for training and inference, Data Requirements, and Training Time for Large Language Models?
This is a very concrete and well-defined computer engineering question. I don't understand why someone would want to close it.
Today, I faced this question during an interview for an ML Engineer ...
-3
votes
0
answers
16
views
Binary classification: Accuracy always equal to 1 [closed]
training a CNN for a binary image classification task. However accuracy is always shown as 1 on validation and test scores. the loss curve does not show overfitting though.
tried to add class weights ...
-1
votes
0
answers
27
views
Accuracy improving gets so slow after some epoches in neural network training [closed]
I have something like 70 million sample to train a neural network model, the accuracy improving goes very well and fast until somewhere like 25-30 epoch, after 25-30 epoch it gets so slow.
e.g.
epoch ...
-4
votes
0
answers
29
views
Which machine learning technique should I use to solve my sequence problem? [closed]
I have a set of data like the below:
Column A
Column B
Column C
Column D
Tom
Monday
Blue
0,3,20,36,80,98,100
Dan
Friday
Red
0,15,45,100
Sarah
Sunday
Red
0,6,31,91,100
Dan
Monday
Yellow
0,21,86,...
-2
votes
0
answers
10
views
Compare hyperparameters influence on model performance
I want to assess which Hyperparams seem to influence the most my results, if there is any kind of "threshold" value for a given or several hyperparams after which the model does not improve ...
-1
votes
0
answers
20
views
Seeking Techniques to Automate Transformation of Irregular Excel Layouts to Structured Datasets
I am facing a challenge with automating the transformation of irregular Excel layouts into structured datasets. These Excel files often contain:
Merged cells
Hierarchical columns
Annotations and notes ...
-2
votes
0
answers
23
views
Choosing the Right Normalization Layer for Audio Classification Neural Network [closed]
I am building an audio classification neural network. I have learned that it is essential to normalize the data during network design.
However, I discovered that there are various types of ...
-1
votes
0
answers
14
views
Extracting text from an TMT (thread mill test) report [closed]
I have a task that involves extracting specific values from a TMT PNG image of a table. Depending on the required output, I need to extract either a specific value from a table cell or some text from ...
-2
votes
0
answers
11
views
How to annotate VQA dataset? [closed]
Can't find a useful annotation platform or software? How did everyone solve this problem. And how to organize the JSON of the dataset.
I used label me and label studio, but the results were not good, ...