ConvNetSharp

---

Convnetsharp

Mulai awalnya sebagai C# port ConvnetJs. Anda dapat menggunakan ConvnetSharp untuk melatih dan mengevaluasi Convolutional Neural Networks (CNN).

Terima kasih banyak kepada penulis asli Convnetjs (Andrej Karpathy) dan untuk semua kontributor!
Convnetsharp bergantung pada Perpustakaan ManagedCuda ke CUDA ACCES NVIDIA

3 cara untuk membuat jaringan saraf

Core.layers	Flow.layers	Grafik komputasi
Tidak ada grafik komputasi	Lapisan yang membuat grafik komputasi di belakang tempat kejadian	'Aliran murni'
Jaringan yang disusun oleh penumpukan lapisan	Jaringan yang disusun oleh penumpukan lapisan	'Ops' terhubung satu sama lain. Dapat menerapkan jaringan yang lebih kompleks
Misalnya mnistdemo	Misalnya mnistflowgpudemo atau versi aliran classify2ddemo	Mis. Contoh Contoh

Kode contoh

Berikut adalah contoh minimum dari mendefinisikan jaringan saraf 2-layer dan melatihnya pada titik data tunggal:

 using System ;
using ConvNetSharp . Core ;
using ConvNetSharp . Core . Layers . Double ;
using ConvNetSharp . Core . Training . Double ;
using ConvNetSharp . Volume ;
using ConvNetSharp . Volume . Double ;

namespace MinimalExample
{
    internal class Program
    {
        private static void Main ( )
        {
            // specifies a 2-layer neural network with one hidden layer of 20 neurons
            var net = new Net < double > ( ) ;

            // input layer declares size of input. here: 2-D data
            // ConvNetJS works on 3-Dimensional volumes (width, height, depth), but if you're not dealing with images
            // then the first two dimensions (width, height) will always be kept at size 1
            net . AddLayer ( new InputLayer ( 1 , 1 , 2 ) ) ;

            // declare 20 neurons
            net . AddLayer ( new FullyConnLayer ( 20 ) ) ;

            // declare a ReLU (rectified linear unit non-linearity)
            net . AddLayer ( new ReluLayer ( ) ) ;

            // declare a fully connected layer that will be used by the softmax layer
            net . AddLayer ( new FullyConnLayer ( 10 ) ) ;

            // declare the linear classifier on top of the previous hidden layer
            net . AddLayer ( new SoftmaxLayer ( 10 ) ) ;

            // forward a random data point through the network
            var x =  BuilderInstance . Volume . From ( new [ ] { 0.3 , - 0.5 } , new Shape ( 2 ) ) ;

            var prob = net . Forward ( x ) ;

            // prob is a Volume. Volumes have a property Weights that stores the raw data, and WeightGradients that stores gradients
            Console . WriteLine ( " probability that x is class 0: " + prob . Get ( 0 ) ) ; // prints e.g. 0.50101

            var trainer = new SgdTrainer ( net ) { LearningRate = 0.01 , L2Decay = 0.001 } ;
            trainer . Train ( x , BuilderInstance . Volume . From ( new [ ] { 1.0 , 0.0 , 0.0 , 0.0 , 0.0 , 0.0 , 0.0 , 0.0 , 0.0 , 0.0 } , new Shape ( 1 , 1 , 10 , 1 ) ) ) ; // train the network, specifying that x is class zero

            var prob2 = net . Forward ( x ) ;
            Console . WriteLine ( " probability that x is class 0: " + prob2 . Get ( 0 ) ) ;
            // now prints 0.50374, slightly higher than previous 0.50101: the networks
            // weights have been adjusted by the Trainer to give a higher probability to
            // the class we trained the network with (zero)
        }
    }
} 

FLUENT API (lihat FLUENTMNISTDEMO)

 var net = FluentNet < double > . Create ( 24 , 24 , 1 )
                   . Conv ( 5 , 5 , 8 ) . Stride ( 1 ) . Pad ( 2 )
                   . Relu ( )
                   . Pool ( 2 , 2 ) . Stride ( 2 )
                   . Conv ( 5 , 5 , 16 ) . Stride ( 1 ) . Pad ( 2 )
                   . Relu ( )
                   . Pool ( 3 , 3 ) . Stride ( 3 )
                   . FullyConn ( 10 )
                   . Softmax ( 10 )
                   . Build ( ) ; 

GPU

Untuk beralih ke mode GPU:

• Tambahkan ' GPU ' di namespace: using ConvNetSharp.Volume. GPU .Single; atau using ConvNetSharp.Volume. GPU .Double;
• Tambahkan BuilderInstance<float>.Volume = new ConvNetSharp.Volume.GPU.Single.VolumeBuilder(); atau BuilderInstance<double>.Volume = new ConvNetSharp.Volume.GPU.Double.VolumeBuilder(); di pengemis kode Anda

Anda harus memiliki CUDA versi 10.0 dan Cudnn v7.6.4 (27 September 2019), untuk CUDA 10.0 diinstal. Jalur bin cudnn harus dirujuk dalam variabel lingkungan jalur.

Mnist GPU Demo di sini

Simpan dan Muat Jaringan

Serialisasi di convnetsharp.core

 using ConvNetSharp . Core . Serialization ;

[ .. . ]

// Serialize to json 
var json = net . ToJson ( ) ;

// Deserialize from json
Net deserialized = SerializationExtensions . FromJson < double > ( json ) ;

Serialisasi di ConvnetSharp.flow

 using ConvNetSharp . Flow . Serialization ;

[ .. . ]

// Serialize to two files: MyNetwork.graphml (graph structure) / MyNetwork.json (volume data)
net . Save ( " MyNetwork " ) ;

// Deserialize from files
var deserialized = SerializationExtensions . Load < double > ( " MyNetwork " , false ) [ 0 ] ;  // first element is the network (second element is the cost if it was saved along)