55,696 questions
- Bountied 0
- Unanswered
- Frequent
- Score
- Trending
- Week
- Month
- Unanswered (my tags)
0
votes
1
answer
27
views
Why is batching inference is not equal to simple inference in runtime [closed]
I'm only considering the total inference time.
I'm using a PyTorch model with CUDA for a computer vision task, and I’ve observed two different scenarios:
Multiple models in parallel:
In this setup, n ...
-1
votes
0
answers
27
views
How to interpret an unstable learning curve on a model tuned with Hyberband Tuning? [closed]
I have used Hyperband automatic tuning for an ANN model to predict price. After running the model with the automatic tuning, I am obtaining an R2 score of 1.00 that suggest overfitting, however, I am ...
1
vote
0
answers
46
views
Validating MSD Brain Tumor Segmentation Pipeline
I am creating a 3D medical image segmentation pipeline and working on the Brain Tumor Segmentation task in the MSD dataset (available here)
).
According to their official paper titled "The Medical ...
-1
votes
1
answer
43
views
How to make the ImageJ cell counter process semi-automatic for leaf counting? [closed]
I am counting duckweed floating on the surface of water in a jar. To count this duckweed I use the Cell Counter plugin of imageJ. I classify these duckweed in three categories: alive, dead, or turion. ...
-1
votes
0
answers
26
views
Is there a simple ML regression option to estimate frequency features(like central frequency, bandwidth) from a noisy time series short signal? [closed]
Just curious, I am wondering if there is a very simple ML architecture that can be trained to estimate frequency informations in a noisy time series data. Time domain information are easy to ...
3
votes
1
answer
89
views
add a condition on time in scipy odeint
I am having some troubles finding a simple solution to what seems to be a simple problem.
I want to compute the integration a simple function. And I want to modify this function if it reaches a ...
-4
votes
1
answer
34
views
Does the weights file stay the same for a different model organism [closed]
I am making a new ML model for genomics based off an existing model. Key difference: model organism. The old model uses bigger, human fastq files, whereas mine will be made for yeast data. Should I ...
0
votes
0
answers
115
views
transformation logic for real-time inference service
I have developed an XGBoost model, the data transformations where done using Pandas for training the model. For real-time inference the data comes from the HTTP request single object/record that ...
-1
votes
0
answers
111
views
Dependency Hell in Google Colab
I was trying to train a NN in Google Colab with Pytorch and then convert it to TFlite. It seems that everything works only with Python 3.11. I was able to find a "switch" that returns Colab ...
1
vote
0
answers
113
views
Temporal Fusion Transformer training oscillating [closed]
I'm practicing using the Temporal Fusion Transformer on a self-made parking lot dataset. I have 23 fields of data features, and for testing, I set the model parameters identically to those used in the ...
2
votes
1
answer
101
views
ERROR: No matching distribution found for tensorflow==2.12
I use macOS. I have to use LibRecommender in my code.
Python Version: 3.8.13
According to this link, the 2.10 is a suitable tensorflow version.
This is what's in my requirements.txt file I install ...
-1
votes
0
answers
101
views
How to achieve instant multi-layer virtual try-on (VTO) using preprocessed human and outfit segmentation masks? [closed]
I’m building a virtual try-on (VTO) app where users can upload their avatar (photo) once, and then try on multiple outfits (like T-shirts, jackets, hoodies, etc.) instantly — including multi-layering (...
-1
votes
0
answers
28
views
Why Should Bias (Pred − True) Be Evaluated Alongside RMSE and MAE in Model Performance Assessment? [closed]
In the evaluation of regression or predictive models, RMSE and MAE are widely used to measure the magnitude of prediction errors.
However, both metrics disregard the direction of these errors — ...
0
votes
2
answers
90
views
Why is there a duplicate index when using sort_index() in pandas?
I am doing target mean mapping based on an external statistical table, where org_ is the external data and merged_data is the set of training data and test data. After processing, the features of ...
0
votes
1
answer
59
views
Cannot calculate confusion matrix utilizing supervision from roboflow for Yolov8 model
I am trying to calculate the confusion matrix for my yolov8 (or yolov11) model utilizing supervision from roboflow. I found some instructions but they do not seem to be crystal clear. For example ...