| Name | Version | Summary | date |
| torchio |
0.20.21 |
Tools for medical image processing with PyTorch |
2025-08-09 21:32:08 |
| torchrl-nightly |
2025.8.9 |
A modular, primitive-first, python-first PyTorch library for Reinforcement Learning |
2025-08-09 15:23:46 |
| birder |
0.0.10a0 |
An open-source computer vision framework for wildlife image analysis, featuring state-of-the-art models for species classification and detection. |
2025-08-09 15:18:19 |
| diffsptk |
3.3.1 |
Speech signal processing modules for machine learning |
2025-08-09 14:42:57 |
| sae-lens |
6.5.2 |
Training and Analyzing Sparse Autoencoders (SAEs) |
2025-08-09 13:45:15 |
| netron |
8.4.9 |
Viewer for neural network, deep learning and machine learning models. |
2025-08-09 08:51:20 |
| pyg-nightly |
2.7.0.dev20250809 |
Graph Neural Network Library for PyTorch |
2025-08-09 06:08:10 |
| batchtensor |
0.1.0 |
Functions to manipulate batches of PyTorch tensors |
2025-08-09 04:38:52 |
| nvidia-tao-pytorch |
6.25.7.0.2 |
NVIDIA's package for DNN implementation on PyTorch for use with TAO Toolkit. |
2025-08-08 21:10:41 |
| spatialreasoners |
1.0.0 |
SpatialReasoners: A framework for training Spatial Reasoning Models in any domain |
2025-08-08 20:46:56 |
| litai |
0.0.9 |
Easiest way to access any AI model with a single subscription. |
2025-08-08 17:45:29 |
| muon-fsdp2 |
0.3.0 |
Muon FSDP2 is a implementation of Muon optimizer for FSDP2 |
2025-08-08 13:45:52 |
| coola |
0.9.0 |
Library to check equality between two complex/nested objects |
2025-08-08 06:52:08 |
| torchmetrics |
1.8.1 |
PyTorch native Metrics |
2025-08-07 20:44:44 |
| lightning-sdk |
2025.8.7 |
SDK to develop using Lightning AI Studios |
2025-08-07 15:39:38 |
| orientLoss |
0.0.7 |
orientLoss is a classification loss function @pytorch. It less prone to overfitting compared to crossEntropy. Compatible with random vector/embeddings with direction-indicating categoriesăprobabilisticăoneHot as target. |
2025-08-07 10:12:01 |
| onedl-mim |
0.4.0rc0 |
MIM Installs OpenMMLab packages |
2025-08-07 07:53:27 |
| gradient-cache |
1.0.0 |
GPU memory-efficient training with gradient compression for PyTorch |
2025-08-06 18:35:11 |
| sentence-transformers |
5.1.0 |
Embeddings, Retrieval, and Reranking |
2025-08-06 13:48:55 |
| glassInit |
0.0.6 |
glassInit is a way to initialize the parameters of a neural network layer @pytorch. It is suitable for shortcut connections where tensor sizes need to be adjusted. The flow of information between forward and backward propagation is maximized while adjusting the tensor size. |
2025-08-06 13:26:50 |