Questions tagged [machine-learning]
Implementation questions about machine learning algorithms. General questions about machine learning (concepts, theory, methodology, terminology, etc.) should be posted to their specific communities.
machine-learning
56,040
questions
0
votes
0
answers
6
views
Why we use concatenation in U net
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 U net architecture but I'm unable to understand how we get the grey lines i....
1
vote
0
answers
8
views
Logic Behind the Categorical Variables Hot Encoding For Machine Learning Models
I am not getting one thing that in machine learning for categorical variables, like the categorical variable 'Is_available' (having 2 unique values, Yes and No), we simply replace Yes with 1 and No ...
0
votes
0
answers
22
views
Sign Language alphabet identification using Machine Learning giving wrong predictions
I'm just a beginner on machine learning and I've watched tutorial videos on YouTube in order to come up with my code. Our professor has only given us less than a week to learn and complete this ...
-2
votes
0
answers
12
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 ...
0
votes
0
answers
15
views
Neural network codes in R
I am running my neural network codes in R for my survival data. I could run these codes but I need to calculate metrics (precision, accuracy, sensitivity, specificity) for the neural network model and ...
-1
votes
0
answers
26
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
28
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,...
-1
votes
0
answers
11
views
Very high MAE and MSE on my RandomForestRegressor
I got a flight predictions dataset that i wanted to try my machine learning skills.
I cleaned the data and fixed some new features and removed others
i also got out some valuable data. But when i ...
-1
votes
0
answers
34
views
How to solve Process finished with exit code -1073741819 (0xC0000005) in Python? [closed]
I am using Python 3.8 in Pycharm. I have Windows 10 and wanted to reproduce this publicly available code:
#!/usr/bin/env python
# -*- encoding: utf-8 -*-
import sys
sys.setrecursionlimit(4000)
import ...
-2
votes
1
answer
18
views
Which loss function should be used if sum(y_true)=1?
My yTrue are basically like [.2,.8] but never [1,0] or [0,1]
sum(yTrue)=1 always
I tried CategoricalCrossentropy But a TypeError occured-
TypeError: Expected float32, but got <keras.src.losses....
-1
votes
0
answers
10
views
ValueError: Unrecognized keyword arguments: ['batch_shape'] [closed]
Trying to load a model that I trained on kaggle After saving and downloading the model I am getting this issue I am not able to load the model on my local system but when I try to do it on kaggle it ...
0
votes
0
answers
14
views
Loading Joblib model in Airflow dag
I'm trying to use joblib inside an airflow dag, when loading a model file I run joblib.load(model_name) but I get an error
File "/usr/local/lib/python3.9/pickle.py", line 331, in ...
-4
votes
0
answers
26
views
Ways for python code to interact with websites and gather data? [closed]
I need to gather data to then feed into NLT filters and the project requires me to gather data (URL and text) from articles. Is there a way to implement this in python, or in any programming language?
...
0
votes
0
answers
17
views
LSTM vs. XGBoost for one step ahead predictions: Why does LSTM in this code perform so worse?
I am working on generating recursive one-step-ahead predictions for a time series y using a minimal set of regressors. I have found that linear models all perform similarly and fail to outperform ...
0
votes
0
answers
21
views
XGBoost Classifier, Grid search
I am trying to apply an XGBoost Classifier model in Python via XGBClassifier (see documentation here). The idea is to train the model on a city-year (e.g. zurich-2000) couple and test it on data for ...