logWMSE, an audio quality metric & loss function with support for digital silence target. Useful for training and evaluating audio source separation systems.
-
Updated
Jun 19, 2024 - Python
logWMSE, an audio quality metric & loss function with support for digital silence target. Useful for training and evaluating audio source separation systems.
Github repo for ML Specialization course on Coursera. Contains notes and practice python notebooks.
All codes of my master thesis conducted under computational learning theory
TensorFlow implementations of losses for sequence to sequence machine learning models
Repository for the paper "Advancing Time Series Forecasting: Variance-Aware Loss Functions in Transformers"
CAMRI Loss: Improving Recall of a Specific Class without Sacrificing Accuracy
optimizer & lr scheduler & loss function collections in PyTorch
Efficient implementation of object condensation losses for use in various projects
A discriminative few-shot learning approach for face recognition and verification using a Siamese network architecture. Employing a triplet loss function, the model optimizes the embedding space to cluster faces of the same individual and separate those of different individuals, enhancing accuracy and efficiency with limited training data.
Collection of audio-focused loss functions in PyTorch
AI | ML | DL Fully Covered for Basic
Use different models to predict car prices using web scraping
This repository is the implementation of the paper, "Score-balanced Loss for Multi-aspect Pronunciation Assessment" (Interspeech 2023).
learning python day 11
Soft-DTW loss function for Keras/TensorFlow
Code for the Lovász-Softmax loss (CVPR 2018)
I am currently working on developing this repository. This repository includes folders including codes for separate deep learning frameworks/API.
Custom implementations of L1/L2/BCE/CE loss and ReLU/Sigmoid/Tanh/Softmax activation functions.
Julia package of loss functions for machine learning.
Add a description, image, and links to the loss-functions topic page so that developers can more easily learn about it.
To associate your repository with the loss-functions topic, visit your repo's landing page and select "manage topics."