All Questions

Filter by
Sorted by
Tagged with
0 votes
0 answers
8 views

TF accuracy metric wants a single value - but it should want a list of probabilities

I am performing a simple seq-to-seq transformer task. I have tried various loss and metrics but none are working. Currently, in model.compile() I am using these: ...
Breck Emert's user avatar
1 vote
0 answers
14 views

Does f1 score evaluate only the model or does it also enable us to observe and evaluate the data?

I have a dataset. This dataset consists of the data that the actual picture that needs to be drawn, that is, the 100-point graded paper, and the similarity between 100 and 0 points graded pictures ...
doqukan's user avatar
  • 11
1 vote
1 answer
14 views

Average training instances sampled with bagging

The book Hands-On Machine Learning has a section on Out-of-Bag Evaluation related to Decision Trees, where it's stated that, By default a BaggingClassifier samples m training instances with ...
Sahil Gupta's user avatar
1 vote
0 answers
7 views

How to analyze time series data and create time series model in Python?

I am trying to understand time-series data and model. In youtube tutorial and others, mostly univariate examples are shown. And they are applicable or suitable for those conditions. What if our ...
Bad Coder's user avatar
0 votes
0 answers
9 views

Why does the TensorFlow docs use a different GAN generator loss?

As per the original paper that introduced GANs, the generator loss is given as: $$ L_{G} = L _{BCE}(\mathbf{\vec 0}, \mathbf{D}(\mathbf{G}(\mathbf{\vec z}))) = \log(1 - \mathbf{D}(\mathbf{G}(\mathbf{\...
Sagnik Taraphdar's user avatar
0 votes
1 answer
12 views

The latest approach for feature dimenesion reduction

I have a feature matrix with 1200 rows and 18930 columns. The matrix is sparse and the original paper has used a stacked denoising autoencoder for dimensionality reduction. Since I want to enhance the ...
Satarnejad's user avatar
1 vote
1 answer
19 views

Multivariate Time series forecast deep learning

My Dataset: I have data for vehicles - mainly engine sensor data but also gps location, weather etc. The data is high frequency - every second. I have aggregated to 1 minute. I roughly have somewhere ...
Joshua's user avatar
  • 11
1 vote
0 answers
8 views

How to chose the right activation function for CNN output depending on the output value ranges?

I'm working on training a CNN model that takes an eye image as input and outputs the 5 coordinates of the ellipse representing the pupil ...
Ersven's user avatar
  • 11
5 votes
1 answer
123 views

Changing output size from a model

So I am currently training some deep learning models for some basic classification problems, and I am trying to figure out if it is possible to change the output size of the model in case I want to ...
pdaranda661's user avatar
0 votes
0 answers
10 views

sns.heatmap(df.corr(),annot=True) [closed]

ValueError Traceback (most recent call last) Cell In[93], line 1 ----> 1 sns.heatmap(df.corr(),annot=True) File ~\anaconda3\Lib\site-packages\pandas\core\frame.py:...
kartik sharma's user avatar
0 votes
0 answers
6 views

What to include in fact and dimension table from election database

I am working with election dataset of India of year 2014 and data for 2019 I also have table for party names and descriptions and finally state name with code. I am not getting how do i create a ...
Sugam Sharma's user avatar
1 vote
0 answers
26 views

Mean Absolute Error from Scratch in NumPy

I recently tried implementing MAE from scratch in NumPy. The loss value and the slope seem to be equivalent to what Scikit-learn outputs, but for some reason the intercept value seems to converge to ...
vxnuaj's user avatar
  • 11
0 votes
0 answers
7 views

Callback handlers in Langchain

This might be an odd question, but why is there two codes for the class BaseCallbackHandler? https://api.python.langchain.com/en/latest/_modules/langchain_core/callbacks/base.html#BaseCallbackHandler ...
Justin Jonany's user avatar
0 votes
0 answers
5 views

How to view Ep Reward mean when using TensorBoard with stable Baselines 3

I am not seeing ep_rwd_mean when running tensorboard. I can only see ...
Mich's user avatar
  • 111
0 votes
0 answers
14 views

How to properly select features for time series ML models

I've been trying to get good references on how to solve a problem that's been bothering me regarding the modelling techniques I've used. I'm currently interested in making forecasts using ML for ...
loguimaraes's user avatar
0 votes
1 answer
18 views

How to explain missing dates to a model?

I have this dataset that I'm trying to train a neural network on. The problem is that since weekend dates are not available, I am not confident in whether the model is able to account for that. ...
Akshat Vats's user avatar
0 votes
0 answers
6 views

xgboost regressor online predictions

I had tried to get predictions from vertex AI endpoint for xgboost regression model trained on black friday sales dataset,but it is not working , anyone can help with this.
charan's user avatar
  • 1
0 votes
1 answer
10 views

Averaging model performance across n-fold cross validation: MSE or R^2?

I'm comparing the performance of several models on the same data using cross-validation (holding out 1/n of the data as a test set, fitting the model on the remaining data, testing on the test set). I ...
Leo Selker's user avatar
1 vote
0 answers
13 views

Does it make sense that the performance of XG Boost varies dramatically from two machines holding all hyperparameters fixed?

I am hyperparameter tuning an xgboost model and I am finding that depending if I train the model locally on my machine vs on AWS sagemaker, I get quite different results. Running cross-validation ...
Luca Guarro's user avatar
0 votes
1 answer
27 views

How an I improve my prediction of my model much more than that?

Here is my interpretation of my model so far, I am investigating the relationship between rating and followers on video games but there is a problem. The more you get high ratings the more you get ...
Hugo Guay's user avatar
-1 votes
0 answers
18 views

convolution neural network

how can i use CNN to know the percent of each compenet in a food and how can I get this Quality and Quantity of Training Data i found that i start with a range of labels representing different ...
sekhra salma's user avatar
0 votes
0 answers
32 views

Strange behaviour on Random Forest Classifier

I've build two identical rf_classifier and trained with two identical datasets but with 2 different target variable (the sell or not sell of two different specific products, one for each algorithm). ...
Federicofkt's user avatar
0 votes
0 answers
13 views

Feature Engineering a Recency feature

I have a customer scoring problem I'm working on specifically on predicting conversion and coming up with a probability score on conversion (using xgboost classifier atm). There's a feature I want to ...
MetalicSt33l's user avatar
0 votes
0 answers
10 views

Segment a spectrogram into a series of images by beats per minute to train a Deep Neural Network

I have a .csv file with information about a soundtrack and it is divided into beats (per minute), which are ordered by row. As in: the index corresponds to each beat, and the columns have info about ...
Johnathan Smitherton's user avatar
0 votes
0 answers
25 views

Are there any general theoretical results about the behavior of data in the neighborhood of a single data point?

I know from calculus that any relatively well-behaved function $y=f(x)$ can be approximated by a linear function $y=ax+b$ within a sufficiently small neighborhood around each point of an independent ...
Vladislav Gladkikh's user avatar
1 vote
1 answer
18 views

Improving GPU Utilization in LLM Inference System

I´m trying to build a distributed LLM inference platform with Huggingface support. The implementation involves utilizing Python for model processing and Java for interfacing with external systems. ...
Cardstdani's user avatar
0 votes
0 answers
11 views

Can equation from paper "Item-based Collaborative Filtering Recommendation Algorithms" be used for implicit feedback?

Article Item-based Collaborative Filtering Recommendation Algorithms by Badrul Sarwar, George Karypis, Joseph Konstan, and John Riedl gives this equation: $$P_{u,i} = \frac{\sum_{j}^S s_{i,j} * R_{u,j}...
Catnip's user avatar
  • 11
1 vote
0 answers
26 views

How does implicit library calculates scores for items?

What method does implicit(python library) use to calculate scores when recommending items to users using the CosineRecommender model? I understood that it happens in the NearestNeighboursScorer class. ...
Catnip's user avatar
  • 11
0 votes
0 answers
21 views

Fuzzy Name Matching with Machine Learning. Input data encoding

I have a huge amount of data in my dataset: Last name, first name, date of birth of Indian residents and I need to match them for similarity. The matching is fuzzy, the data looks like this (names are ...
ккк ккк's user avatar
0 votes
0 answers
18 views

Input 0 of layer "sequential_2" is incompatible with the layer: expected shape=(None, 3, 3), found shape=(1, 3, 11)

I am trying to predict stock closing price using news sentiment analysis with the help LSTM neural network but after I do model.fit(). I am encountered with the error message: ValueError: Input 0 of ...
pankaj yadav's user avatar
0 votes
0 answers
11 views

In Swin-Transformer, Is each token (to-embedding) value an integer?

Swin-Transformer transform the image to tokens to input to transformer. Is each token (before-embedding) value an integer? In practice, where is this done? https://github.com/microsoft/Swin-...
CoderOnly's user avatar
  • 701
0 votes
1 answer
19 views

Data generation methods for NLP tasks

I am doing a Natural language processing related project. It is a sentiment analysis task. I need to generate a dataset for the uniqueness of the work. Is there any recommendation on how can I ...
Encipher's user avatar
  • 361
0 votes
0 answers
16 views

What is the shape of the hidden/cell state of convLSTM2D?

I am new to convLSTM2D and I understand how it works, however, I am confused about the shape of the hidden states at different epochs ...
user43280's user avatar
  • 101
0 votes
1 answer
30 views

Why does forecasting with an LSTM yield better results with shuffling?

I first partition the timeseries data into train, validation, and test splits, without performing any shuffling. Each row is a window of ordered samples, so my training data might be shaped ...
MuhammedYunus's user avatar
0 votes
0 answers
12 views

i am facing problem in combining the forecasts generated by multiple stacked GRU models

first i have used CEEMDAN, to decompose multi-variate data into different IMFs, after that for each IMF stacked GRU model is trained, which gives results for each IMFs, for the final predictions i ...
Poonam Dhaka's user avatar
0 votes
1 answer
60 views

Test Error is extremely higher than Training error after gridsearch and crossvalidation

I'm currently working on a machine learning project. It's a supervised learning problem. My goal is to predict for given data of an animal(keeping,size,weight,...) ingredients(energy,vitamine etc..). ...
Marco Cotrotzo's user avatar
1 vote
1 answer
35 views

How to measure different models' feature importance using a generic and common standard?

I want to measure the feature importance of a series of models after training them. Most models have some built-in APIs that allow me to access their feature importance, but as far as I know, these ...
Yuuya's user avatar
  • 11
0 votes
0 answers
6 views

diffusion model: can't overfit on single batch

I am training the diffusion model from diffusion policy, specifically their vision notebook, on a custom dataset. As always, I try to make a sanity check of the pipeline, by overfitting on a single ...
Felix Hegg's user avatar
-1 votes
0 answers
29 views

What two different formulas in SVC minimization problem means?

Im studying a Support Vectors Machine and for soft margin I found minimization problem in form like this: $$\min_{w,b} \frac{1}{2} \|w\|^2 + C \sum_{i=1}^l \xi_i$$ And this this formula seems pretty ...
Almer's user avatar
  • 1
2 votes
1 answer
33 views

Techniques for solving the problem with an unbalanced data set

I am trying to solve a problem with an unbalanced data set. I have two classes, one is for patients with risk (1), the other for patients without risk (0). I have a larger number of patients without ...
Naty's user avatar
  • 21
0 votes
0 answers
14 views

The possible integrations of physics and deep learning?

I have developed a model in my thesis which can compute the energy of a special physical system and some other useful physical quantities. Now I want to use it in deep learning somehow. Do you have ...
Wisdom's user avatar
  • 101
0 votes
1 answer
33 views

Can anyone help me understand this problem in my data?

I tried making a model using the autoTS library but the thing is in the result it gives me the following results. I checked everything there is no missing data but the original data had a missing ...
theunknown's user avatar
0 votes
0 answers
12 views

Cross label two dataframes using arbitrary comparison of two columns using pandas

I have two dataframes each with geometric data (shapely shape files). Call them df1 and df2. The geometry in df1 is a polygon (an area) and the geometry in df2 are points. All polygons are unique and ...
Chad Sexington's user avatar
0 votes
0 answers
8 views

Why is resnet regression model (on a skewed data with small interval) not converging?

Using resnet50 (torchvision.models pretrained=False) with an input of [15, 224,224] which includes 14 heatmaps and a level set ...
topcat's user avatar
  • 1
1 vote
0 answers
27 views

recognition of names, surnames and patronymics

is there an example of neural networks on Github or Kaggle that perform the task of recognizing identical surnames, first names and patronymics? I'm just learning neural networks so it's interesting ...
nanana's user avatar
  • 11
0 votes
0 answers
5 views

Does Factorization Machines accept continuous variables?

Most of the implementations I have seen of FM rely on an Embedding lookup matrix, restricting the variables that can be used to some categorical variable. Is there a way to use FM with both ...
Daniel Ávila Vera's user avatar
0 votes
0 answers
20 views

Diffusion Models: Conditioning on Time vs. Noise Level

I am new to SE-Data Science, therefore I hope this is the right place to ask this rather theoretical question. In diffusion models we usually have a time variable which determines the noise schedule (...
Lockhart 's user avatar
0 votes
0 answers
23 views

The origin of NaN in the dataset

I train on a dataset with Kaggle from Netflix, where information about the series is provided. I am interested in a question about NaN in the column with the name Director. I want to try to understand ...
Egor Fomenko's user avatar
0 votes
1 answer
18 views

Accuracy and test_accuracy gives a result =1

I've developed a code for classifying hyperspectral images using three different convolutional neural network (CNN) architectures: 1D, 2D, and 3D. The code has two main parts: Preprocessing and data ...
user162895's user avatar
1 vote
0 answers
50 views

Using SMOTE Train Model and Optimal Cutoff on Unbalanced Test Data

My original dataset has a binary dependent variable with 3% of the values being one. First, I split the original dataset into training and testing sets using an 80-20 split. Since it includes both ...
CraigS's user avatar
  • 11

15 30 50 per page
1
2 3 4 5
739