Features • Installation • Tutorials • Community • Citing • License
Overview
fasterAI is a PyTorch-based library that makes neural networks smaller, faster, and more efficient through state-of-the-art compression techniques. The library provides simple but powerful implementations of pruning, knowledge distillation, quantization, and other network optimization methods that can be applied with just a few lines of code.
Why compress your models with fasterai?
- Reduce model size by up to 90% with minimal accuracy loss
- Speed up inference for deployment on edge devices
- Lower energy consumption for more sustainable AI
- Simplify architectures while maintaining performance
Features
1. Sparsification
Make your model sparse by replacing selected weights with zeros using Sparsifier or SparsifyCallback.
| Parameter | Description | Options |
|---|---|---|
sparsity |
Percentage of weights to zero out | 0-100% |
granularity |
Level at which to apply sparsity | 'weight', 'vector', 'kernel', 'filter' |
context |
Scope of sparsification | 'local' (per layer), 'global' (whole model) |
criteria |
Method to select weights | 'magnitude', 'movement', 'gradient', etc. |
schedule |
How sparsity evolves during training | 'one_shot', 'iterative', 'gradual', etc. |
2. Pruning
Remove zero-weight nodes from your network structure using Pruner or PruneCallback.
| Parameter | Description | Options |
|---|---|---|
pruning_ratio |
Percentage of weights to remove | 0-100% |
context |
Scope of sparsification | 'local' (per layer), 'global' (whole model) |
criteria |
Method to select weights | 'magnitude', 'movement', 'gradient', etc. |
schedule |
How sparsity evolves during training | 'one_shot', 'iterative', 'gradual', etc. |
3. Knowledge Distillation
Transfer knowledge from a large teacher to a smaller student using KnowledgeDistillationCallback.
| Parameter | Description | Options |
|---|---|---|
teacher |
Teacher model | Any PyTorch model |
loss |
Distillation loss function | 'SoftTarget', 'Logits', 'Attention', etc. |
activations_student |
Student layers to match | Layer names as strings |
activations_teacher |
Teacher layers to match | Layer names as strings |
weight |
Balancing weight for distillation | 0.0-1.0 |
4. Regularization
Push weights toward zero during training using RegularizeCallback.
| Parameter | Description | Options |
|---|---|---|
criteria |
Regularization criteria | Same as sparsification criteria |
granularity |
Level of regularization | Same as sparsification granularity |
weight |
Regularization strength | Floating point value |
schedule |
How sparsity evolves during training | 'one_shot', 'iterative', 'gradual', etc. |
layer_types |
Layer types to regularize | 'nn.Conv2d', 'nn.Linear', etc. |
5. Quantization
Reduce the precision of weights and activations using Quantizer or QuantizeCallback.
| Parameter | Description | Options |
|---|---|---|
backend |
Target backend | 'x86', 'qnnpack' |
method |
Quantization method | 'static', 'dynamic', 'qat' |
use_per_tensor |
Force per-tensor quantization | True/False |
Quick Start
This is how easy it is to induce Sparsification in your PyTorch model:
from fasterai.sparse.all import *
learn = vision_learner(dls, model)
learn.fit_one_cycle(n_epochs, cbs=SparsifyCallback(sparsity, granularity, context, criteria, schedule))
Installation
pip install git+https://github.com/FasterAI-Labs/fasterai.git
or
pip install fasterai
Tutorials
- Get Started with FasterAI
- Create your own pruning schedule
- Find winning tickets using the Lottery Ticket Hypothesis
- Use Knowledge Distillation to help a student model to reach higher performance
- Sparsify Transformers
- Many more !
Join the community
Join our discord server to meet other FasterAI users and share your projects!
Citing
@software{Hubens,
author = {Nathan Hubens},
title = {fasterai},
year = 2022,
publisher = {Zenodo},
version = {v0.3.0},
doi = {10.5281/zenodo.6469868},
url = {https://doi.org/10.5281/zenodo.6469868}
}
License
Apache-2.0 License.
1 maintainer
Metadata
1 maintainer
Release files for fasterai 0.4.1
For a detailed explanation of source distributions (sdists) and built distributions (wheels), please see the package formats documentation.
Source distribution (sdist)
| File | Size | Uploaded | |
|---|---|---|---|
| fasterai-0.4.1.tar.gz | 87.9 kB | Details |
Built distribution (wheel)
| File | Interpreter | ABI | Platform | Reset |
|---|---|---|---|---|
| fasterai-0.4.1-py3-none-any.whl | Python 3 | none | any | Details |
Total release size: 184.9 kB
Release files / fasterai-0.4.1.tar.gz
| Download URL | fasterai-0.4.1.tar.gz |
|---|---|
| Size | 87.9 kB |
| Tags | Source |
|
SHA-256 checksum How to use checksums |
bb08ccd89f99d9d9080115dce32d14ed32c09cb05d27ea76451e0f9f209d97fb
|
|
BLAKE2b-256 checksum How to use checksums |
9c23c78829d09c519b02cd8dd8a1684795c3b48be75dfd5930c9498b12819373
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.12.11
|
Release files / fasterai-0.4.1-py3-none-any.whl
| Download URL | fasterai-0.4.1-py3-none-any.whl |
|---|---|
| Size | 97.1 kB |
| Tags | Python 3 |
|
SHA-256 checksum How to use checksums |
a41cde10056a0cfd46e9d2ed5ffe3b7d60cfd1fff21d2b8f59461902878d7d36
|
|
BLAKE2b-256 checksum How to use checksums |
40a4f4661bb9242b75a0ecf5a4f228a8e7d995e4570da5f35c78e8ffc3d26188
|
| Upload date | |
|
Uploaded using Trusted Publishing? What is trusted publishing? |
No |
| Uploaded via |
twine/7.0.0 CPython/3.12.11
|
