private void TestDenseNetwork(int inputs, int samples, int batchSize, int epochs)
{
var net = new NeuralNetwork("deep_dense_test", 7);
var model = new Sequential();
model.AddLayer(new Dense(inputs, 5, Activation.Linear));
model.AddLayer(new Dense(model.LastLayer, 4, Activation.Linear));
model.AddLayer(new Dense(model.LastLayer, inputs, Activation.Linear));
net.Model = model;
List <Data> tData = new List <Data>();
for (int i = 0; i < samples; ++i)
{
var input = new Tensor(model.Layer(0).InputShape);
input.FillWithRand(10 * i, -2, 2);
tData.Add(new Data(input, input.Mul(1.7f)));
}
net.Optimize(new SGD(0.02f), Loss.MeanSquareError);
net.Fit(tData, batchSize, epochs, null, 2, Track.TrainError);
for (int i = 0; i < tData.Count; ++i)
{
Assert.IsTrue(tData[i].Output.Equals(net.Predict(tData[i].Input)[0], 0.01f));
}
}
private Sequential CreateSequential(JToken model)
{
var seq = new Sequential(controller);
var layers = model.SelectToken("config").Children();
foreach (var layer in layers)
{
var layerType = layer.SelectToken("class_name");
switch (layerType.Value <String>())
{
case "Linear":
// weight float tensor
var weightData = layer.SelectToken("config.weights.data").ToObject <float[]>();
var weightShape = layer.SelectToken("config.weights.shape").ToObject <int[]>();
var weightTensor = controller.floatTensorFactory.Create(_data: weightData, _shape: weightShape, _autograd: true);
// bias float tensor
var biasData = layer.SelectToken("config.bias.data").ToObject <float[]>();
var biasShape = layer.SelectToken("config.bias.shape").ToObject <int[]>();
var biasTensor = controller.floatTensorFactory.Create(_data: biasData, _shape: biasShape, _autograd: true);
var input = layer.SelectToken("config.input").ToObject <int>();
var output = layer.SelectToken("config.output").ToObject <int>();
var linear = new Linear(controller, input: input, output: output, weights: weightTensor, bias: biasTensor);
seq.AddLayer(linear);
break;
case "ReLU":
seq.AddLayer(new ReLU(controller));
break;
case "Log":
seq.AddLayer(new OpenMined.Syft.Layer.Log(controller));
break;
case "Dropout":
var rate = layer.SelectToken("config.rate").ToObject <float>();
var dropout = new Dropout(controller, rate);
seq.AddLayer(dropout);
break;
case "Softmax":
var dim = layer.SelectToken("config.dim").ToObject <int>();
seq.AddLayer(new Softmax(controller, dim));
break;
}
}
return(seq);
}
public DQN(Shape inputShape, int numberOfActions, int[] hiddenLayersNeurons, float learningRate, float discountFactor, int batchSize, BaseExperienceReplay memory)
: this(inputShape, numberOfActions, learningRate, discountFactor, batchSize, memory)
{
Net = new NeuralNetwork("dqn");
var Model = new Sequential();
Model.AddLayer(new Flatten(inputShape));
for (int i = 0; i < hiddenLayersNeurons.Length; ++i)
{
Model.AddLayer(new Dense(Model.LastLayer, hiddenLayersNeurons[i], Activation.ReLU));
}
Model.AddLayer(new Dense(Model.LastLayer, numberOfActions, Activation.Linear));
Net.Model = Model;
Net.Optimize(new Adam(learningRate), new CustomHuberLoss(ImportanceSamplingWeights));
}
private void TestConvolutionLayer(Shape inputShape, int kernelSize, int kernelsNum, int stride, int samples, int batchSize, int epochs, TrainDataFunc convFunc)
{
var net = new NeuralNetwork("convolution_test", 7);
var model = new Sequential();
model.AddLayer(new Convolution(inputShape, kernelSize, kernelsNum, stride, Activation.Linear)
{
KernelInitializer = new Initializers.Constant(1)
});
net.Model = model;
var expectedKernels = new Tensor(new Shape(kernelSize, kernelSize, inputShape.Depth, kernelsNum));
expectedKernels.FillWithRand(17);
var tData = GenerateTrainingData(samples, model.LastLayer.InputShape, expectedKernels, convFunc);
net.Optimize(new SGD(0.02f), Loss.MeanSquareError);
net.Fit(tData, batchSize, epochs, null, 0, Track.Nothing);
var paramsAndGrads = model.LastLayer.GetParametersAndGradients();
for (int i = 0; i < expectedKernels.Length; ++i)
{
Assert.AreEqual(paramsAndGrads[0].Parameters.GetFlat(i), expectedKernels.GetFlat(i), 1e-2);
}
}
static void Main(string[] args)
{
Tensor.SetOpMode(Tensor.OpMode.GPU);
var net = new NeuralNetwork("test");
var inputShape = new Shape(64, 64, 4);
var model = new Sequential();
model.AddLayer(new Convolution(inputShape, 8, 32, 2, Activation.ELU));
model.AddLayer(new Convolution(model.LastLayer, 4, 64, 2, Activation.ELU));
model.AddLayer(new Convolution(model.LastLayer, 4, 128, 2, Activation.ELU));
model.AddLayer(new Flatten(model.LastLayer));
model.AddLayer(new Dense(model.LastLayer, 512, Activation.ELU));
model.AddLayer(new Dense(model.LastLayer, 3, Activation.Softmax));
net.Model = model;
net.Optimize(new Adam(), Loss.Huber1);
var input = new Tensor(new Shape(64, 64, 4, 32)); input.FillWithRand();
var output = new Tensor(new Shape(1, 3, 1, 32));
for (int n = 0; n < output.BatchSize; ++n)
{
output[0, Tools.Rng.Next(output.Height), 0, n] = 1.0f;
}
var timer = new Stopwatch();
timer.Start();
net.FitBatched(input, output, 10, 1, Track.Nothing);
timer.Stop();
Trace.WriteLine($"{Math.Round(timer.ElapsedMilliseconds / 1000.0, 2)} seconds");
}
private NeuralNetwork CreateFitTestNet()
{
var net = new NeuralNetwork("fit_test", 7);
var model = new Sequential();
model.AddLayer(new Dense(3, 2, Activation.Linear)
{
KernelInitializer = new Initializers.Constant(1), UseBias = false
});
net.Model = model;
net.Optimize(new SGD(0.07f), Loss.MeanSquareError);
return(net);
}
public void SoftCopyParameters()
{
var net = new NeuralNetwork("test");
var model = new Sequential();
model.AddLayer(new Dense(2, 3, Activation.Linear));
model.AddLayer(new Dense(3, 3, Activation.Linear));
net.Model = model;
net.ForceInitLayers();
var net2 = net.Clone();
net.SoftCopyParametersTo(net2, 0.1f);
var netParams = net2.GetParametersAndGradients();
var net2Params = net2.GetParametersAndGradients();
for (int i = 0; i < netParams.Count; ++i)
{
Assert.IsTrue(netParams[i].Parameters.Equals(net2Params[i].Parameters));
}
}
public Sequential CreateSequential(JToken model)
{
var seq = new Sequential(controller);
var layers = model.SelectToken("config").Children();
foreach (var layer in layers)
{
var layerType = layer.SelectToken("class_name");
switch (layerType.Value <String>())
{
case "Linear":
// weight float tensor
var weightData = layer.SelectToken("config.weights.data").ToObject <float[]>();
var input = layer.SelectToken("config.input").ToObject <int>();
var output = layer.SelectToken("config.output").ToObject <int>();
float[] biasData = null;
if (layer.SelectToken("config.bias") == null)
{
biasData = layer.SelectToken("config.bias.data").ToObject <float[]>();
}
Linear linear = new Linear(controller, input: input, output: output, weights: weightData, bias: biasData);
seq.AddLayer(linear);
break;
case "ReLU":
seq.AddLayer(new ReLU(controller));
break;
case "Log":
seq.AddLayer(new OpenMined.Syft.Layer.Log(controller));
break;
case "Dropout":
var rate = layer.SelectToken("config.rate").ToObject <float>();
var dropout = new Dropout(controller, rate);
seq.AddLayer(dropout);
break;
case "Softmax":
var dim = layer.SelectToken("config.dim").ToObject <int>();
seq.AddLayer(new Softmax(controller, dim));
break;
case "Sigmoid":
seq.AddLayer(new Sigmoid(controller));
break;
}
}
return(seq);
}
private Sequential CreateSequential(List <String> model)
{
// TODO just assumes it is all in a seq model the seq model should probably
// be in the JSON????
var seq = new Sequential(controller);
foreach (var l in model)
{
var config = JObject.Parse(l);
Layer layer = null;
switch ((string)config["name"])
{
case "linear":
layer = new Linear(controller, (int)config["input"], (int)config["output"]);
break;
case "softmax":
layer = new Softmax(controller, (int)config["dim"]);
break;
case "relu":
layer = new ReLU(controller);
break;
case "log":
layer = new Log(controller);
break;
case "dropout":
layer = new Dropout(controller, (float)config["rate"]);
break;
}
seq.AddLayer(layer);
}
return(seq);
}
private void TestDenseLayer(int inputs, int outputs, int samples, int batchSize, int epochs)
{
var net = new NeuralNetwork("dense_test", 7);
var model = new Sequential();
model.AddLayer(new Dense(inputs, outputs, Activation.Linear)
{
KernelInitializer = new Initializers.Constant(1), UseBias = false
});
net.Model = model;
var expectedWeights = new Tensor(new[] { 1.1f, 0.1f, -1.3f, 0.2f, -0.9f, 0.7f }, new Shape(3, 2));
var tData = GenerateTrainingData(samples, model.LastLayer.InputShape, expectedWeights, MatMult);
net.Optimize(new SGD(0.07f), Loss.MeanSquareError);
net.Fit(tData, batchSize, epochs, null, 2, Track.TrainError);
var paramsAndGrads = model.LastLayer.GetParametersAndGradients();
for (int i = 0; i < expectedWeights.Length; ++i)
{
Assert.AreEqual(paramsAndGrads[0].Parameters.GetFlat(i), expectedWeights.GetFlat(i), 1e-2);
}
}
public DQNConv(int[] inputSize, int numberOfActions, float learningRate, float discountFactor, int batchSize, BaseExperienceReplay memory)
: base(null, numberOfActions, learningRate, discountFactor, batchSize, memory)
{
Tensor.SetOpMode(Tensor.OpMode.GPU);
InputSize = inputSize;
Shape inputShape = new Shape(inputSize[0], inputSize[1], TemporalDataSize);
Net = new NeuralNetwork("DQNConv");
var Model = new Sequential();
Model.AddLayer(new Convolution(inputShape, 8, 32, 2, Activation.ELU));
Model.AddLayer(new Convolution(Model.LastLayer, 4, 64, 2, Activation.ELU));
Model.AddLayer(new Convolution(Model.LastLayer, 4, 128, 2, Activation.ELU));
Model.AddLayer(new Flatten(Model.LastLayer));
Model.AddLayer(new Dense(Model.LastLayer, 512, Activation.ELU));
Model.AddLayer(new Dense(Model.LastLayer, numberOfActions, Activation.Softmax));
Net.Model = Model;
Net.Optimize(new Adam(learningRate), new CustomHuberLoss(ImportanceSamplingWeights));
}
public void ProcessMessage(string json_message, MonoBehaviour owner, Action <string> response)
{
Command msgObj = JsonUtility.FromJson <Command> (json_message);
try
{
switch (msgObj.objectType)
{
case "Optimizer":
{
if (msgObj.functionCall == "create")
{
string optimizer_type = msgObj.tensorIndexParams[0];
// Extract parameters
List <int> p = new List <int>();
for (int i = 1; i < msgObj.tensorIndexParams.Length; i++)
{
p.Add(int.Parse(msgObj.tensorIndexParams[i]));
}
List <float> hp = new List <float>();
for (int i = 0; i < msgObj.hyperParams.Length; i++)
{
hp.Add(float.Parse(msgObj.hyperParams[i]));
}
Optimizer optim = null;
if (optimizer_type == "sgd")
{
optim = new SGD(this, p, hp[0], hp[1], hp[2]);
}
else if (optimizer_type == "rmsprop")
{
optim = new RMSProp(this, p, hp[0], hp[1], hp[2], hp[3]);
}
else if (optimizer_type == "adam")
{
optim = new Adam(this, p, hp[0], hp[1], hp[2], hp[3], hp[4]);
}
response(optim.Id.ToString());
return;
}
else
{
Optimizer optim = this.GetOptimizer(msgObj.objectIndex);
response(optim.ProcessMessage(msgObj, this));
return;
}
}
case "FloatTensor":
{
if (msgObj.objectIndex == 0 && msgObj.functionCall == "create")
{
FloatTensor tensor = floatTensorFactory.Create(_shape: msgObj.shape, _data: msgObj.data, _shader: this.Shader);
response(tensor.Id.ToString());
return;
}
else
{
FloatTensor tensor = floatTensorFactory.Get(msgObj.objectIndex);
// Process message's function
response(tensor.ProcessMessage(msgObj, this));
return;
}
}
case "IntTensor":
{
if (msgObj.objectIndex == 0 && msgObj.functionCall == "create")
{
int[] data = new int[msgObj.data.Length];
for (int i = 0; i < msgObj.data.Length; i++)
{
data[i] = (int)msgObj.data[i];
}
IntTensor tensor = intTensorFactory.Create(_shape: msgObj.shape, _data: data);
response(tensor.Id.ToString());
return;
}
else
{
IntTensor tensor = intTensorFactory.Get(msgObj.objectIndex);
// Process message's function
response(tensor.ProcessMessage(msgObj, this));
return;
}
}
case "agent":
{
if (msgObj.functionCall == "create")
{
Layer model = (Layer)GetModel(int.Parse(msgObj.tensorIndexParams[0]));
Optimizer optimizer = optimizers[int.Parse(msgObj.tensorIndexParams[1])];
response(new Syft.NN.RL.Agent(this, model, optimizer).Id.ToString());
return;
}
//Debug.Log("Getting Model:" + msgObj.objectIndex);
Syft.NN.RL.Agent agent = this.GetAgent(msgObj.objectIndex);
response(agent.ProcessMessageLocal(msgObj, this));
return;
}
case "model":
{
if (msgObj.functionCall == "create")
{
string model_type = msgObj.tensorIndexParams[0];
Debug.LogFormat("<color=magenta>createModel:</color> {0}", model_type);
if (model_type == "linear")
{
response(this.BuildLinear(msgObj.tensorIndexParams).Id.ToString());
return;
}
else if (model_type == "relu")
{
response(this.BuildReLU().Id.ToString());
return;
}
else if (model_type == "log")
{
response(this.BuildLog().Id.ToString());
return;
}
else if (model_type == "dropout")
{
response(this.BuildDropout(msgObj.tensorIndexParams).Id.ToString());
return;
}
else if (model_type == "sigmoid")
{
response(this.BuildSigmoid().Id.ToString());
return;
}
else if (model_type == "sequential")
{
response(this.BuildSequential().Id.ToString());
return;
}
else if (model_type == "softmax")
{
response(this.BuildSoftmax(msgObj.tensorIndexParams).Id.ToString());
return;
}
else if (model_type == "logsoftmax")
{
response(this.BuildLogSoftmax(msgObj.tensorIndexParams).Id.ToString());
return;
}
else if (model_type == "tanh")
{
response(new Tanh(this).Id.ToString());
return;
}
else if (model_type == "crossentropyloss")
{
response(new CrossEntropyLoss(this, int.Parse(msgObj.tensorIndexParams[1])).Id.ToString());
return;
}
else if (model_type == "categorical_crossentropy")
{
response(new CategoricalCrossEntropyLoss(this).Id.ToString());
return;
}
else if (model_type == "nllloss")
{
response(new NLLLoss(this).Id.ToString());
return;
}
else if (model_type == "mseloss")
{
response(new MSELoss(this).Id.ToString());
return;
}
else if (model_type == "embedding")
{
response(new Embedding(this, int.Parse(msgObj.tensorIndexParams[1]), int.Parse(msgObj.tensorIndexParams[2])).Id.ToString());
return;
}
else
{
Debug.LogFormat("<color=red>Model Type Not Found:</color> {0}", model_type);
}
}
else
{
//Debug.Log("Getting Model:" + msgObj.objectIndex);
Model model = this.GetModel(msgObj.objectIndex);
response(model.ProcessMessage(msgObj, this));
return;
}
response("Unity Error: SyftController.processMessage: Command not found:" + msgObj.objectType + ":" + msgObj.functionCall);
return;
}
case "controller":
{
if (msgObj.functionCall == "num_tensors")
{
response(floatTensorFactory.Count() + "");
return;
}
else if (msgObj.functionCall == "num_models")
{
response(models.Count + "");
return;
}
else if (msgObj.functionCall == "new_tensors_allowed")
{
Debug.LogFormat("New Tensors Allowed:{0}", msgObj.tensorIndexParams[0]);
if (msgObj.tensorIndexParams[0] == "True")
{
allow_new_tensors = true;
}
else if (msgObj.tensorIndexParams[0] == "False")
{
allow_new_tensors = false;
}
else
{
throw new Exception("Invalid parameter for new_tensors_allowed. Did you mean true or false?");
}
response(allow_new_tensors + "");
return;
}
else if (msgObj.functionCall == "load_floattensor")
{
FloatTensor tensor = floatTensorFactory.Create(filepath: msgObj.tensorIndexParams[0], _shader: this.Shader);
response(tensor.Id.ToString());
return;
}
else if (msgObj.functionCall == "set_seed")
{
Random.InitState(int.Parse(msgObj.tensorIndexParams[0]));
response("Random seed set!");
return;
}
else if (msgObj.functionCall == "concatenate")
{
List <int> tensor_ids = new List <int>();
for (int i = 1; i < msgObj.tensorIndexParams.Length; i++)
{
tensor_ids.Add(int.Parse(msgObj.tensorIndexParams[i]));
}
FloatTensor result = Functional.Concatenate(floatTensorFactory, tensor_ids, int.Parse(msgObj.tensorIndexParams[0]));
response(result.Id.ToString());
return;
}
else if (msgObj.functionCall == "ones")
{
int[] dims = new int[msgObj.tensorIndexParams.Length];
for (int i = 0; i < msgObj.tensorIndexParams.Length; i++)
{
dims[i] = int.Parse(msgObj.tensorIndexParams[i]);
}
FloatTensor result = Functional.Ones(floatTensorFactory, dims);
response(result.Id.ToString());
return;
}
else if (msgObj.functionCall == "randn")
{
int[] dims = new int[msgObj.tensorIndexParams.Length];
for (int i = 0; i < msgObj.tensorIndexParams.Length; i++)
{
dims[i] = int.Parse(msgObj.tensorIndexParams[i]);
}
FloatTensor result = Functional.Randn(floatTensorFactory, dims);
response(result.Id.ToString());
return;
}
else if (msgObj.functionCall == "random")
{
int[] dims = new int[msgObj.tensorIndexParams.Length];
for (int i = 0; i < msgObj.tensorIndexParams.Length; i++)
{
dims[i] = int.Parse(msgObj.tensorIndexParams[i]);
}
FloatTensor result = Functional.Random(floatTensorFactory, dims);
response(result.Id.ToString());
return;
}
else if (msgObj.functionCall == "zeros")
{
int[] dims = new int[msgObj.tensorIndexParams.Length];
for (int i = 0; i < msgObj.tensorIndexParams.Length; i++)
{
dims[i] = int.Parse(msgObj.tensorIndexParams[i]);
}
FloatTensor result = Functional.Zeros(floatTensorFactory, dims);
response(result.Id.ToString());
return;
}
else if (msgObj.functionCall == "model_from_json")
{
Debug.Log("Loading Model from JSON:");
var json_str = msgObj.tensorIndexParams[0];
var config = JObject.Parse(json_str);
Sequential model;
if ((string)config["class_name"] == "Sequential")
{
model = this.BuildSequential();
}
else
{
response("Unity Error: SyftController.processMessage: while Loading model, Class :" + config["class_name"] + " is not implemented");
return;
}
for (int i = 0; i < config["config"].ToList().Count; i++)
{
var layer_desc = config["config"][i];
var layer_config_desc = layer_desc["config"];
if ((string)layer_desc["class_name"] == "Linear")
{
int previous_output_dim;
if (i == 0)
{
previous_output_dim = (int)layer_config_desc["batch_input_shape"][layer_config_desc["batch_input_shape"].ToList().Count - 1];
}
else
{
previous_output_dim = (int)layer_config_desc["units"];
}
string[] parameters = { "linear", previous_output_dim.ToString(), layer_config_desc["units"].ToString(), "Xavier" };
Layer layer = this.BuildLinear(parameters);
model.AddLayer(layer);
string activation_name = layer_config_desc["activation"].ToString();
if (activation_name != "linear")
{
Layer activation;
if (activation_name == "softmax")
{
parameters = new string[] { activation_name, "1" };
activation = this.BuildSoftmax(parameters);
}
else if (activation_name == "relu")
{
activation = this.BuildReLU();
}
else
{
response("Unity Error: SyftController.processMessage: while Loading activations, Activation :" + activation_name + " is not implemented");
return;
}
model.AddLayer(activation);
}
}
else
{
response("Unity Error: SyftController.processMessage: while Loading layers, Layer :" + layer_desc["class_name"] + " is not implemented");
return;
}
}
response(model.Id.ToString());
return;
}
else if (msgObj.functionCall == "from_proto")
{
Debug.Log("Loading Model from ONNX:");
var filename = msgObj.tensorIndexParams[0];
var input = File.OpenRead(filename);
ModelProto modelProto = ModelProto.Parser.ParseFrom(input);
Sequential model = this.BuildSequential();
foreach (NodeProto node in modelProto.Graph.Node)
{
Layer layer;
GraphProto g = ONNXTools.GetSubGraphFromNodeAndMainGraph(node, modelProto.Graph);
if (node.OpType == "Gemm")
{
layer = new Linear(this, g);
}
else if (node.OpType == "Dropout")
{
layer = new Dropout(this, g);
}
else if (node.OpType == "Relu")
{
layer = new ReLU(this, g);
}
else if (node.OpType == "Softmax")
{
layer = new Softmax(this, g);
}
else
{
response("Unity Error: SyftController.processMessage: Layer not yet implemented for deserialization:");
return;
}
model.AddLayer(layer);
}
response(model.Id.ToString());
return;
}
else if (msgObj.functionCall == "to_proto")
{
ModelProto model = this.ToProto(msgObj.tensorIndexParams);
string filename = msgObj.tensorIndexParams[2];
string type = msgObj.tensorIndexParams[3];
if (type == "json")
{
response(model.ToString());
}
else
{
using (var output = File.Create(filename))
{
model.WriteTo(output);
}
response(new FileInfo(filename).FullName);
}
return;
}
response("Unity Error: SyftController.processMessage: Command not found:" + msgObj.objectType + ":" + msgObj.functionCall);
return;
}
case "Grid":
if (msgObj.functionCall == "learn")
{
var inputId = int.Parse(msgObj.tensorIndexParams[0]);
var targetId = int.Parse(msgObj.tensorIndexParams[1]);
response(this.grid.Run(inputId, targetId, msgObj.configurations, owner));
return;
}
if (msgObj.functionCall == "getResults")
{
this.grid.GetResults(msgObj.experimentId, response);
return;
}
// like getResults but doesn't pause to wait for results
// this function will return right away telling you if
// it knows whether or not it is done
if (msgObj.functionCall == "checkStatus")
{
this.grid.CheckStatus(msgObj.experimentId, response);
return;
}
break;
default:
break;
}
}
catch (Exception e)
{
Debug.LogFormat("<color=red>{0}</color>", e.ToString());
response("Unity Error: " + e.ToString());
return;
}
// If not executing createTensor or tensor function, return default error.
response("Unity Error: SyftController.processMessage: Command not found:" + msgObj.objectType + ":" + msgObj.functionCall);
return;
}
