TorchSim
TorchSim is a pure Pytorch-based MR simulator, including analytical and EPG model.
Features
TorchSim contains tools to implement parallelized and differentiable MR simulators. Specifically, we provide
- Automatic vectorization of across multiple atoms (e.g., voxels).
- Automatic generation of forward and jacobian methods (based on forward-mode autodiff) to be used in parameter fitting or model-based reconstructions.
- Support for custom manual defined jacobian methods to override auto-generated jacobian.
- Support for advanced signal models, including diffusion, flow, magnetization transfer and chemical exchange.
- GPU support.
Installation
TorchSim can be installed via pip as:
pip install torchsim
Basic Usage
Using TorchSim, we can quickly implement and run MR simulations. We also provide pre-defined simulators for several applications:
import numpy as np
import torchsim
# generate a flip angle pattern
flip = np.concatenate((np.linspace(5, 60.0, 300), np.linspace(60.0, 2.0, 300), np.ones(280)*2.0))
sig, jac = torchsim.mrf_sim(flip=flip, TR=10.0, T1=1000.0, T2=100.0, diff=("T1","T2"))
This way we obtained the forward pass signal (sig) as well as the jacobian
calculated with respect to T1 and T2.
Development
If you are interested in improving this project, install TorchSim in editable mode:
git clone git@github.com:FiRMLAB-Pisa/torchsim
cd torchsim
pip install -e ".[dev]"
pre-commit install
The install compiles the two C++ kernels, so it needs a C++17 compiler; CMake
and Ninja arrive as build-time wheels. pre-commit runs the formatter and the
linter -- both ruff -- on every commit, which is exactly what CI checks.
Related projects
This package is inspired by the following excellent projects:
- epyg <https://github.com/brennerd11/EpyG>
- sycomore <https://github.com/lamyj/sycomore/>
- mri-sim-py <https://somnathrakshit.github.io/projects/project-mri-sim-py-epg/>
- ssfp <https://github.com/mckib2/ssfp>
- erwin <https://github.com/lamyj/erwin>
1 maintainer
Metadata
1 maintainer
Release files for torchsim 0.0.8
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| torchsim-0.0.8.tar.gz | 20.6 MB | Details |
Built distributions (wheels)
| File | Reset | |||
|---|---|---|---|---|
| torchsim-0.0.8-cp310-abi3-win_amd64.whl | CPython 3.10 | abi3 | Windows x86-64 | Details |
| torchsim-0.0.8-cp310-abi3-musllinux_1_2_x86_64.whl | CPython 3.10 | abi3 | Linux musl 1.2+ x86-64 | Details |
| torchsim-0.0.8-cp310-abi3-musllinux_1_2_aarch64.whl | CPython 3.10 | abi3 | Linux musl 1.2+ ARM64 | Details |
| torchsim-0.0.8-cp310-abi3-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl | CPython 3.10 | abi3 | Linux glibc 2.28+ x86-64, Linux glibc 2.27+ x86-64 | Details |
| torchsim-0.0.8-cp310-abi3-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl | CPython 3.10 | abi3 | Linux glibc 2.28+ ARM64, Linux glibc 2.27+ ARM64 | Details |
| torchsim-0.0.8-cp310-abi3-macosx_11_0_arm64.whl | CPython 3.10 | abi3 | macOS 11.0+ ARM64 | Details |
| torchsim-0.0.8-cp310-abi3-macosx_10_9_x86_64.whl | CPython 3.10 | abi3 | macOS 10.9+ x86-64 | Details |
Total release size: 33.1 MB
Release files / torchsim-0.0.8.tar.gz
| Download URL | torchsim-0.0.8.tar.gz |
|---|---|
| Size | 20.6 MB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
6626025983aa0fe3c9d385d861f7b210a9a6d111ec58d439cfe150021d036baf
|
|
BLAKE2b-256 checksum How to use checksums |
0f236ee7d5f39ff2182a2a6e00632ba3bfc707ea4151adc6e3c88e5f0291490e
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 1, 2026.
Transparency logRelease files / torchsim-0.0.8-cp310-abi3-win_amd64.whl
| Download URL | torchsim-0.0.8-cp310-abi3-win_amd64.whl |
|---|---|
| Size | 1.0 MB |
| Tags | CPython 3.10 Windows x86-64 abi3 |
|
SHA-256 checksum How to use checksums |
1ee8a9673e4d4d31f9b0a7f95b99dd3e7e7cc1c6b6acf586abd217b73e8664a3
|
|
BLAKE2b-256 checksum How to use checksums |
4aada2ff53f7fd2896019a083a852afe9c1109f69a2e43af923a3b19fadcd64a
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 1, 2026.
Transparency logRelease files / torchsim-0.0.8-cp310-abi3-musllinux_1_2_x86_64.whl
| Download URL | torchsim-0.0.8-cp310-abi3-musllinux_1_2_x86_64.whl |
|---|---|
| Size | 2.8 MB |
| Tags | CPython 3.10 Linux musl 1.2+ x86-64 abi3 |
|
SHA-256 checksum How to use checksums |
3cec4abb46304b26d92401261d9425fabb7995c4976d04b88b005a826f4620b1
|
|
BLAKE2b-256 checksum How to use checksums |
646935f1cd9b3c3b0f49521758c3735aa0a9bf6a5ad700d2ff058302da7c3a81
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 1, 2026.
Transparency logRelease files / torchsim-0.0.8-cp310-abi3-musllinux_1_2_aarch64.whl
| Download URL | torchsim-0.0.8-cp310-abi3-musllinux_1_2_aarch64.whl |
|---|---|
| Size | 2.6 MB |
| Tags | CPython 3.10 Linux musl 1.2+ ARM64 abi3 |
|
SHA-256 checksum How to use checksums |
150fa08eb52bfdcfae5cb56f2d0cc00a523307867a0c414e2898a6146a3ea849
|
|
BLAKE2b-256 checksum How to use checksums |
bae25916ba30a0e89cac77791c36c2f28895be3c0e2bc51807045350b6fad157
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 1, 2026.
Transparency logRelease files / torchsim-0.0.8-cp310-abi3-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl
| Download URL | torchsim-0.0.8-cp310-abi3-manylinux_2_27_x86_64.manylinux_2_28_x86_64.whl |
|---|---|
| Size | 2.0 MB |
| Tags | CPython 3.10 Linux glibc 2.27+ x86-64 Linux glibc 2.28+ x86-64 abi3 |
|
SHA-256 checksum How to use checksums |
5b2e06db2266216183cc2c3850f10d62b1c639e373b184677d99fc72992331d3
|
|
BLAKE2b-256 checksum How to use checksums |
0e90e1b8f983a3bb076c49f1dbedb5d1c02a94378c26fa2f141d45caf6b4e0fe
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 1, 2026.
Transparency logRelease files / torchsim-0.0.8-cp310-abi3-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl
| Download URL | torchsim-0.0.8-cp310-abi3-manylinux_2_27_aarch64.manylinux_2_28_aarch64.whl |
|---|---|
| Size | 1.6 MB |
| Tags | CPython 3.10 Linux glibc 2.27+ ARM64 Linux glibc 2.28+ ARM64 abi3 |
|
SHA-256 checksum How to use checksums |
57183f84fcda93c4889f939d12c6f2bec01988884162d0f8ac10cb9bb105130c
|
|
BLAKE2b-256 checksum How to use checksums |
b490f4290163012a354eea368a749e7fc1bbef55f519d0c5d8f6139f1e550126
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 1, 2026.
Transparency logRelease files / torchsim-0.0.8-cp310-abi3-macosx_11_0_arm64.whl
| Download URL | torchsim-0.0.8-cp310-abi3-macosx_11_0_arm64.whl |
|---|---|
| Size | 1.2 MB |
| Tags | CPython 3.10 abi3 macOS 11.0+ ARM64 |
|
SHA-256 checksum How to use checksums |
5089d1f2bd8091decd9b735e2ab32cf11122a9e234d9e6f3e53d282991d25791
|
|
BLAKE2b-256 checksum How to use checksums |
0eae4baccaf966f54401489b9392bca2d49807cc3d0a41732522bde6a9298e05
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 1, 2026.
Transparency logRelease files / torchsim-0.0.8-cp310-abi3-macosx_10_9_x86_64.whl
| Download URL | torchsim-0.0.8-cp310-abi3-macosx_10_9_x86_64.whl |
|---|---|
| Size | 1.3 MB |
| Tags | CPython 3.10 abi3 macOS 10.9+ x86-64 |
|
SHA-256 checksum How to use checksums |
6729bc488c38fa58c3a2474217b7f5f4d8ccf3424e9d07ddd1d0b147f316e3ea
|
|
BLAKE2b-256 checksum How to use checksums |
3b2a2c70a2da3f9f82e3d44e33eab2d1fd6a5fab03c6f6219829df8e1b6d26e7
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
Yes |
| Uploaded via |
twine/7.0.0 CPython/3.13.14
|
Provenance
Provenance describes where a file came from. On PyPI, provenance is shared via attestations, which provide a verifiable record of the build or publishing details. View details, limitations and caveats.
PyPI Publish Attestation
PyPI verified that this artifact, at this checksum, originated from the publisher listed below.
Signed by GitHub Actions, verified by PyPI on Oct 1, 2026.
Transparency log
