sugarme / Gotch
Licence: apache-2.0
Go binding for Pytorch C++ API (libtorch)
Stars: ✭ 88
Projects that are alternatives of or similar to Gotch
Homie Esp8266
💡 ESP8266 framework for Homie, a lightweight MQTT convention for the IoT
Stars: ✭ 1,241 (+1310.23%)
Mutual labels: framework
Wire
Reactive data processing framework for visual programming tools
Stars: ✭ 86 (-2.27%)
Mutual labels: framework
Casing
The UI Framework for Framer Classic. Manages data, components and views
Stars: ✭ 83 (-5.68%)
Mutual labels: framework
Python Lambdarest
Flask like web framework for AWS Lambda
Stars: ✭ 84 (-4.55%)
Mutual labels: framework
Infima
A UI framework that provides websites with the minimal CSS and JS needed to get started with building a modern responsive beautiful website
Stars: ✭ 82 (-6.82%)
Mutual labels: framework
Pastepwn
Python framework to scrape Pastebin pastes and analyze them
Stars: ✭ 87 (-1.14%)
Mutual labels: framework
Shellkit
Objective-C framework for running shell scripts.
Stars: ✭ 83 (-5.68%)
Mutual labels: framework
Jsonapiframework
JsonApiFramework is a fast, extensible, and portable .NET framework for the reading and writing of JSON API documents. Currently working on ApiFramework 1.0 which is a new framework that supports the many enhancements documented in the 2.0 milestone of this project while being media type agnostic but will support media types like {json:api} and GraphQL for serialization/deserialization purposes.
Stars: ✭ 85 (-3.41%)
Mutual labels: framework
Typetron
Modern Node.js framework for creating fully-featured apps
Stars: ✭ 82 (-6.82%)
Mutual labels: framework
Qiankun
📦 🚀 Blazing fast, simple and complete solution for micro frontends.
Stars: ✭ 11,497 (+12964.77%)
Mutual labels: framework
Spring Data Mongodb
Provide support to increase developer productivity in Java when using MongoDB. Uses familiar Spring concepts such as a template classes for core API usage and lightweight repository style data access.
Stars: ✭ 1,253 (+1323.86%)
Mutual labels: framework
Unity Experiment Framework
UXF - Framework for creating human behaviour experiments in Unity
Stars: ✭ 81 (-7.95%)
Mutual labels: framework
Enduro2d
Yet another 2d game engine of dreams (work in progress)
Stars: ✭ 82 (-6.82%)
Mutual labels: framework
Reazy
Reazy Framework - A simple services-based framework for React and React Native
Stars: ✭ 86 (-2.27%)
Mutual labels: framework
Gotch
Overview
Gotch creates a thin wrapper to Pytorch C++ APIs (Libtorch) to make use of its already optimized C++ tensor APIs (~ over 1400) and dynamic graph computation with CUDA support and provides idiomatic Go APIs for developing and implementing Deep Learning in Go.
Some features are
- [x] Comprehensive Pytorch tensor APIs (~ 1404)
- [x] Fully featured Pytorch dynamic graph computation
- [x] JIT interface to run model trained/saved using PyTorch Python API
- [x] Load pretrained Pytorch models and run inference
- [x] Pure Go APIs to build and train neural network models with both CPU and GPU support
- [x] Most recent image models
- [ ] NLP Language models - Transformer in separate package built with GoTch and pure Go Tokenizer.
Gotch is in active development mode and may have API breaking changes. Feel free to pull request, report issues or discuss any concerns. All contributions are welcome.
Dependencies
- Libtorch C++ v1.7.0 library of Pytorch
Installation
- Default CUDA version is
10.1
if CUDA is available otherwise using CPU version. - Default Pytorch C++ API version is
1.7.0
wget https://raw.githubusercontent.com/sugarme/gotch/v0.3.8/setup.sh
chmod +x setup.sh
# Default
bash setup.sh
# Specify CUDA version
export CUDA_VER=YOUR_PC_CUDA_VERSION && bash setup.sh
# CPU
export CUDA_VER=cpu && bash setup.sh
Examples
Basic tensor operations
import (
"fmt"
"github.com/sugarme/gotch"
ts "github.com/sugarme/gotch/tensor"
)
func basicOps() {
xs := ts.MustRand([]int64{3, 5, 6}, gotch.Float, gotch.CPU)
fmt.Printf("%8.3f\n", xs)
fmt.Printf("%i", xs)
/*
(1,.,.) =
0.391 0.055 0.638 0.514 0.757 0.446
0.817 0.075 0.437 0.452 0.077 0.492
0.504 0.945 0.863 0.243 0.254 0.640
0.850 0.132 0.763 0.572 0.216 0.116
0.410 0.660 0.156 0.336 0.885 0.391
(2,.,.) =
0.952 0.731 0.380 0.390 0.374 0.001
0.455 0.142 0.088 0.039 0.862 0.939
0.621 0.198 0.728 0.914 0.168 0.057
0.655 0.231 0.680 0.069 0.803 0.243
0.853 0.729 0.983 0.534 0.749 0.624
(3,.,.) =
0.734 0.447 0.914 0.956 0.269 0.000
0.427 0.034 0.477 0.535 0.440 0.972
0.407 0.945 0.099 0.184 0.778 0.058
0.482 0.996 0.085 0.605 0.282 0.671
0.887 0.029 0.005 0.216 0.354 0.262
TENSOR INFO:
Shape: [3 5 6]
DType: float32
Device: {CPU 1}
Defined: true
*/
// Basic tensor operations
ts1 := ts.MustArange(ts.IntScalar(6), gotch.Int64, gotch.CPU).MustView([]int64{2, 3}, true)
defer ts1.MustDrop()
ts2 := ts.MustOnes([]int64{3, 4}, gotch.Int64, gotch.CPU)
defer ts2.MustDrop()
mul := ts1.MustMatmul(ts2, false)
defer mul.MustDrop()
fmt.Printf("ts1:\n%2d", ts1)
fmt.Printf("ts2:\n%2d", ts2)
fmt.Printf("mul tensor (ts1 x ts2):\n%2d", mul)
/*
ts1:
0 1 2
3 4 5
ts2:
1 1 1 1
1 1 1 1
1 1 1 1
mul tensor (ts1 x ts2):
3 3 3 3
12 12 12 12
*/
// In-place operation
ts3 := ts.MustOnes([]int64{2, 3}, gotch.Float, gotch.CPU)
fmt.Printf("Before:\n%v", ts3)
ts3.MustAdd1_(ts.FloatScalar(2.0))
fmt.Printf("After (ts3 + 2.0):\n%v", ts3)
/*
Before:
1 1 1
1 1 1
After (ts3 + 2.0):
3 3 3
3 3 3
*/
}
Simplified Convolutional neural network
import (
"fmt"
"github.com/sugarme/gotch"
"github.com/sugarme/gotch/nn"
ts "github.com/sugarme/gotch/tensor"
)
type Net struct {
conv1 *nn.Conv2D
conv2 *nn.Conv2D
fc *nn.Linear
}
func newNet(vs *nn.Path) *Net {
conv1 := nn.NewConv2D(vs, 1, 16, 2, nn.DefaultConv2DConfig())
conv2 := nn.NewConv2D(vs, 16, 10, 2, nn.DefaultConv2DConfig())
fc := nn.NewLinear(vs, 10, 10, nn.DefaultLinearConfig())
return &Net{
conv1,
conv2,
fc,
}
}
func (n Net) ForwardT(xs *ts.Tensor, train bool) *ts.Tensor {
xs = xs.MustView([]int64{-1, 1, 8, 8}, false)
outC1 := xs.Apply(n.conv1)
outMP1 := outC1.MaxPool2DDefault(2, true)
defer outMP1.MustDrop()
outC2 := outMP1.Apply(n.conv2)
outMP2 := outC2.MaxPool2DDefault(2, true)
outView2 := outMP2.MustView([]int64{-1, 10}, true)
defer outView2.MustDrop()
outFC := outView2.Apply(n.fc)
return outFC.MustRelu(true)
}
func main() {
vs := nn.NewVarStore(gotch.CPU)
net := newNet(vs.Root())
xs := ts.MustOnes([]int64{8, 8}, gotch.Float, gotch.CPU)
logits := net.ForwardT(xs, false)
fmt.Printf("Logits: %0.3f", logits)
}
//Logits: 0.000 0.000 0.000 0.225 0.321 0.147 0.000 0.207 0.000 0.000
gotch
on Google Colab or locally
Play with - Tensor Initiation
- Tensor Indexing
- MNIST
- YOLO v3 model infering
- RNN model training
- CIFAR model training
- JIT ResNet18 Torch Script model load and inference
- Neural style transfer
- Image pretrained models - inference
- Translation
More coming soon...
Getting Started
- See pkg.go.dev for APIs detail.
License
Gotch is Apache 2.0 licensed.
Acknowledgement
- This project has been inspired and used many concepts from tch-rs Libtorch Rust binding.
Note that the project description data, including the texts, logos, images, and/or trademarks,
for each open source project belongs to its rightful owner.
If you wish to add or remove any projects, please contact us at [email protected].