public void CancelSelection()
{
switch (curChar)
{
case SelectableCharacters.Leslie:
CD.GetComponent <Collider2D>().isTrigger = true;
Leslie.GetComponent <Image>().sprite = HoverImages[0];
break;
case SelectableCharacters.Jona:
ND.GetComponent <Collider2D>().isTrigger = true;
Jona.GetComponent <Image>().sprite = HoverImages[1];
break;
case SelectableCharacters.Ashita:
NED.GetComponent <Collider2D>().isTrigger = true;
Ashita.GetComponent <Image>().sprite = HoverImages[2];
break;
case SelectableCharacters.Catarine:
ED.GetComponent <Collider2D>().isTrigger = true;
Catarine.GetComponent <Image>().sprite = HoverImages[3];
break;
case SelectableCharacters.Ramsey:
SED.GetComponent <Collider2D>().isTrigger = true;
Ramsey.GetComponent <Image>().sprite = HoverImages[4];
break;
case SelectableCharacters.Drogas:
SD.GetComponent <Collider2D>().isTrigger = true;
Drogas.GetComponent <Image>().sprite = HoverImages[5];
break;
case SelectableCharacters.Sylvia:
SWD.GetComponent <Collider2D>().isTrigger = true;
Sylvia.GetComponent <Image>().sprite = HoverImages[6];
break;
case SelectableCharacters.Bjin:
WD.GetComponent <Collider2D>().isTrigger = true;
Bjin.GetComponent <Image>().sprite = HoverImages[7];
break;
case SelectableCharacters.Xavier:
NWD.GetComponent <Collider2D>().isTrigger = true;
Xavier.GetComponent <Image>().sprite = HoverImages[8];
break;
case SelectableCharacters.None:
break;
default:
break;
}
weaponSelect.SetActive(false);
weaponSelectActive = false;
characterChosen = false;
}
internal WeightInitialisationProvider(ILinearAlgebraProvider lap)
{
Ones = new Constant(lap, 0f, 1f);
Zeroes = new Constant(lap, 0f, 0f);
Gaussian = new Gaussian(lap);
Xavier = new Xavier(lap);
Identity = new Identity(lap, 1f);
Identity01 = new Identity(lap, 0.1f);
}
public void makeAllDissapear()
{
Leslie.SetActive(false);
Jona.SetActive(false);
Ashita.SetActive(false);
Catarine.SetActive(false);
Ramsey.SetActive(false);
Drogas.SetActive(false);
Sylvia.SetActive(false);
Bjin.SetActive(false);
Xavier.SetActive(false);
}
public FeatureExpander(string network, string[] outputs, int[] num_filters, bool use_1x1_transition = true,
bool use_bn = true, float reduce_ratio = 1, int min_depth = 128, bool global_pool = false,
bool pretrained = false, Context ctx = null, string[] inputs = null, ParameterDict @params = null) : base(null, null, @params)
{
var(p_i, p_o, p_p) = __internal__.ParseNetwork(network, outputs, inputs, pretrained, ctx);
// append more layers
var y = p_o.Last();
var weight_init = new Xavier(rnd_type: "gaussian", factor_type: "out", magnitude: 2);
foreach (var _tup_2 in num_filters.Select((_p_1, _p_2) => Tuple.Create(_p_2, _p_1)))
{
var i = _tup_2.Item1;
var f = _tup_2.Item2;
if (use_1x1_transition)
{
var num_trans = Math.Max(min_depth, Convert.ToInt32(Math.Round(f * reduce_ratio)));
y = sym.Convolution(y, weight_init.InitWeight("weight"), null, num_filter: num_trans, kernel: new Shape(1, 1), no_bias: use_bn, symbol_name: $"expand_trans_conv{i}");
if (use_bn)
{
y = sym.BatchNorm(y, null, null, null, null, symbol_name: $"expand_trans_bn{i}");
}
y = sym.Activation(y, act_type: ActivationType.Relu, symbol_name: $"expand_trans_relu{i}");
}
y = sym.Convolution(y, weight_init.InitWeight("weight"), null, num_filter: f, kernel: new Shape(3, 3), pad: new Shape(1, 1), stride: new Shape(2, 2), no_bias: use_bn, symbol_name: $"expand_conv{i}");
if (use_bn)
{
y = sym.BatchNorm(y, null, null, null, null, symbol_name: $"expand_bn{i}");
}
y = sym.Activation(y, act_type: ActivationType.Relu, symbol_name: $"expand_reu{i}");
p_o.Add(y);
}
if (global_pool)
{
p_o.Add(sym.Pooling(y, pool_type: PoolingType.Avg, global_pool: true, kernel: new Shape(1, 1)));
}
base.Construct(p_o, p_i, p_p);
}
private static void Main()
{
/*basic config*/
const int batchSize = 256;
const int maxEpo = 100;
const float learningRate = 1e-4f;
const float weightDecay = 1e-4f;
/*context and net symbol*/
var ctx = Context.Gpu();
var net = AlexnetSymbol(2);
/*args_map and aux_map is used for parameters' saving*/
var argsMap = new Dictionary <string, NDArray>();
var auxMap = new Dictionary <string, NDArray>();
/*we should tell mxnet the shape of data and label*/
argsMap["data"] = new NDArray(new Shape(batchSize, 3, 256, 256), ctx);
argsMap["label"] = new NDArray(new Shape(batchSize), ctx);
/*with data and label, executor can be generated varmatically*/
using (var exec = net.SimpleBind(ctx, argsMap))
{
var argNames = net.ListArguments();
var auxiliaryDictionary = exec.AuxiliaryDictionary();
var argmentDictionary = exec.ArgmentDictionary();
/*if fine tune from some pre-trained model, we should load the parameters*/
// NDArray.Load("./model/alex_params_3", nullptr, &args_map);
/*else, we should use initializer Xavier to init the params*/
var xavier = new Xavier(RandType.Gaussian, FactorType.In, 2.34f);
foreach (var arg in argmentDictionary)
{
/*be careful here, the arg's name must has some specific ends or starts for
* initializer to call*/
xavier.Operator(arg.Key, arg.Value);
}
/*print out to check the shape of the net*/
foreach (var s in net.ListArguments())
{
Logging.LG(s);
var sb = new StringBuilder();
var k = argmentDictionary[s].GetShape();
foreach (var i in k)
{
sb.Append($"{i} ");
}
Logging.LG(sb.ToString());
}
/*these binary files should be generated using im2rc tools, which can be found
* in mxnet/bin*/
var trainIter = new MXDataIter("ImageRecordIter")
.SetParam("path_imglist", "./data/train.lst")
.SetParam("path_imgrec", "./data/train.rec")
.SetParam("data_shape", new Shape(3, 256, 256))
.SetParam("batch_size", batchSize)
.SetParam("shuffle", 1)
.CreateDataIter();
var valIter = new MXDataIter("ImageRecordIter")
.SetParam("path_imglist", "./data/val.lst")
.SetParam("path_imgrec", "./data/val.rec")
.SetParam("data_shape", new Shape(3, 256, 256))
.SetParam("batch_size", batchSize)
.CreateDataIter();
var opt = OptimizerRegistry.Find("ccsgd");
opt.SetParam("momentum", 0.9)
.SetParam("rescale_grad", 1.0 / batchSize)
.SetParam("clip_gradient", 10)
.SetParam("lr", learningRate)
.SetParam("wd", weightDecay);
var accuracyTrain = new Accuracy();
var accuracyVal = new Accuracy();
var loglossVal = new LogLoss();
for (var iter = 0; iter < maxEpo; ++iter)
{
Logging.LG($"Train Epoch: {iter}");
/*reset the metric every epoch*/
accuracyTrain.Reset();
/*reset the data iter every epoch*/
trainIter.Reset();
while (trainIter.Next())
{
var batch = trainIter.GetDataBatch();
Logging.LG($"{trainIter.GetDataBatch().Index.Length}");
/*use copyto to feed new data and label to the executor*/
batch.Data.CopyTo(argmentDictionary["data"]);
batch.Label.CopyTo(argmentDictionary["label"]);
exec.Forward(true);
exec.Backward();
for (var i = 0; i < argNames.Count; ++i)
{
if (argNames[i] == "data" || argNames[i] == "label")
{
continue;
}
opt.Update(i, exec.ArgmentArrays[i], exec.GradientArrays[i]);
}
NDArray.WaitAll();
accuracyTrain.Update(batch.Label, exec.Outputs[0]);
}
Logging.LG($"ITER: {iter} Train Accuracy: {accuracyTrain.Get()}");
Logging.LG($"Val Epoch: {iter}");
accuracyVal.Reset();
valIter.Reset();
loglossVal.Reset();
while (valIter.Next())
{
var batch = valIter.GetDataBatch();
Logging.LG($"{valIter.GetDataBatch().Index.Length}");
batch.Data.CopyTo(argmentDictionary["data"]);
batch.Label.CopyTo(argmentDictionary["label"]);
exec.Forward(false);
NDArray.WaitAll();
accuracyVal.Update(batch.Label, exec.Outputs[0]);
loglossVal.Update(batch.Label, exec.Outputs[0]);
}
Logging.LG($"ITER: {iter} Val Accuracy: {accuracyVal.Get()}");
Logging.LG($"ITER: {iter} Val LogLoss: {loglossVal.Get()}");
/*save the parameters*/
var savePathParam = $"./model/alex_param_{iter}";
var saveArgs = argmentDictionary;
/*we do not want to save the data and label*/
if (saveArgs.ContainsKey("data"))
{
saveArgs.Remove("data");
}
if (saveArgs.ContainsKey("label"))
{
saveArgs.Remove("label");
}
/*the alexnet does not get any aux array, so we do not need to save
* aux_map*/
Logging.LG($"ITER: {iter} Saving to...{savePathParam}");
NDArray.Save(savePathParam, saveArgs);
}
/*don't foget to release the executor*/
}
MXNet.MXNotifyShutdown();
}
private void Construct(SymbolList outputs, SymbolList inputs, ParameterDict @params, int[] num_filters, bool use_1x1 = true, bool use_upsample = true,
bool use_elewadd = true, bool use_p6 = false, bool p6_conv = true, bool no_bias = true,
bool pretrained = false, string norm_layer = null, FuncArgs norm_kwargs = null, Context ctx = null)
{
Symbol y_p6 = null;
// e.g. For ResNet50, the feature is :
// outputs = ['stage1_activation2', 'stage2_activation3',
// 'stage3_activation5', 'stage4_activation2']
// with regard to [conv2, conv3, conv4, conv5] -> [C2, C3, C4, C5]
// append more layers with reversed order : [P5, P4, P3, P2]
var y = outputs.Last();
var base_features = outputs.Take(outputs.Length - 1).ToArray();
var num_stages = num_filters.Length + 1;
var weight_init = new Xavier(rnd_type: "uniform", factor_type: "in", magnitude: 1);
var tmp_outputs = new List <Symbol>();
// num_filter is 256 in ori paper
for (int i = 0; i < base_features.Length; i++)
{
var bf = base_features[i];
var f = num_filters[i];
if (i == 0)
{
if (use_1x1)
{
y = sym.Convolution(y, weight_init.InitWeight("weight"), null, num_filter: f, kernel: new Shape(1, 1), pad: new Shape(0, 0), stride: new Shape(1, 1), no_bias: no_bias, symbol_name: $"P{num_stages - i}_conv_lat");
if (norm_layer != null)
{
if (norm_layer == "SyncBatchNorm")
{
norm_kwargs["key"] = $"P{num_stages - i}_lat_bn";
norm_kwargs["name"] = $"P{num_stages - i}_lat_bn";
}
var bn = LayerUtils.NormLayer(norm_layer, norm_kwargs);
y = bn.Call(y);
}
}
if (use_p6 && p6_conv)
{
// method 2 : use conv (Deformable use this)
y_p6 = sym.Convolution(y, weight_init.InitWeight("weight"), null, num_filter: f, kernel: new Shape(3, 3), pad: new Shape(1, 1), stride: new Shape(2, 2), no_bias: no_bias, symbol_name: $"P{num_stages + 1}_conv1");
if (norm_layer != null)
{
if (norm_layer == "SyncBatchNorm")
{
norm_kwargs["key"] = $"P{num_stages - i}_pre_bn";
norm_kwargs["name"] = $"P{num_stages - i}_pre_bn";
}
var bn = LayerUtils.NormLayer(norm_layer, norm_kwargs);
y_p6 = bn.Call(y_p6);
}
}
}
else
{
if (use_1x1)
{
bf = sym.Convolution(bf, weight_init.InitWeight("weight"), null, num_filter: f, kernel: new Shape(1, 1), pad: new Shape(0, 0), stride: new Shape(1, 1), no_bias: no_bias, symbol_name: $"P{num_stages - i}_conv_lat");
if (norm_layer != null)
{
if (norm_layer == "SyncBatchNorm")
{
norm_kwargs["key"] = $"P{num_stages - i}_conv1_bn";
norm_kwargs["name"] = $"P{num_stages - i}_conv1_bn";
}
var bn = LayerUtils.NormLayer(norm_layer, norm_kwargs);
bf = bn.Call(bf);
}
}
if (use_upsample)
{
y = sym.UpSampling(y, scale: 2, num_args: 1, sample_type: UpsamplingSampleType.Nearest, symbol_name: $"P{num_stages - i}_upsp");
}
if (use_elewadd)
{
// make two symbol alignment
// method 1 : mx.sym.Crop
// y = mx.sym.Crop(*[y, bf], name="P{}_clip".format(num_stages-i))
// method 2 : mx.sym.slice_like
y = sym.SliceLike(y, bf, axes: new Shape(2, 3), symbol_name: $"P{num_stages - i}_clip");
y = sym.ElemwiseAdd(bf, y, symbol_name: $"P{num_stages - i}_sum");
}
}
// Reduce the aliasing effect of upsampling described in ori paper
var @out = sym.Convolution(y, weight_init.InitWeight("weight"), null, num_filter: f, kernel: new Shape(3, 3), pad: new Shape(1, 1), stride: new Shape(1, 1), no_bias: no_bias, symbol_name: $"P{num_stages - i}_conv1");
if (i == 0 && use_p6 && !p6_conv)
{
// method 2 : use max pool (Detectron use this)
y_p6 = sym.Pooling(@out, pool_type: PoolingType.Max, kernel: new Shape(1, 1), pad: new Shape(0, 0), stride: new Shape(2, 2), symbol_name: $"P{num_stages + 1}_pre");
}
if (norm_layer != null)
{
if (norm_layer == "SyncBatchNorm")
{
norm_kwargs["key"] = $"P{num_stages - i}_bn";
norm_kwargs["name"] = $"P{num_stages - i}_bn";
}
var bn = LayerUtils.NormLayer(norm_layer, norm_kwargs);
@out = bn.Call(@out);
}
tmp_outputs.Add(@out);
}
if (use_p6)
{
outputs = tmp_outputs.Take(tmp_outputs.Count - 1).ToList();
outputs.Add(y_p6);
}
else
{
outputs = tmp_outputs.Take(tmp_outputs.Count - 1).ToList();
}
base.Construct(outputs, inputs, @params);
}
public void switchChar(Collider2D collin)
{
switch (collin.name)
{
case "CenterDiamond":
//if (!CD.GetComponent<Collider2D>().isTrigger)
//{
// CD.GetComponent<Collider2D>().isTrigger = true;
//}
makeAllDissapear();
Leslie.SetActive(true);
TextObject.GetComponentInChildren <Text>().text = "Leslie";
curChar = SelectableCharacters.Leslie;
break;
case "NorthDiamond":
makeAllDissapear();
Jona.SetActive(true);
TextObject.GetComponentInChildren <Text>().text = "Jona";
curChar = SelectableCharacters.Jona;
break;
case "NorthEastDiamond":
makeAllDissapear();
Ashita.SetActive(true);
TextObject.GetComponentInChildren <Text>().text = "Ashita";
curChar = SelectableCharacters.Ashita;
break;
case "EastDiamond":
makeAllDissapear();
Catarine.SetActive(true);
TextObject.GetComponentInChildren <Text>().text = "Catarine";
curChar = SelectableCharacters.Catarine;
break;
case "SouthEastDiamond":
makeAllDissapear();
Ramsey.SetActive(true);
TextObject.GetComponentInChildren <Text>().text = "Ramsey";
curChar = SelectableCharacters.Ramsey;
break;
case "SouthDiamond":
makeAllDissapear();
Drogas.SetActive(true);
TextObject.GetComponentInChildren <Text>().text = "Drogas";
curChar = SelectableCharacters.Drogas;
break;
case "SouthWestDiamond":
makeAllDissapear();
Sylvia.SetActive(true);
TextObject.GetComponentInChildren <Text>().text = "Sylvia";
curChar = SelectableCharacters.Sylvia;
break;
case "WestDiamond":
makeAllDissapear();
Bjin.SetActive(true);
TextObject.GetComponentInChildren <Text>().text = "Bjin";
curChar = SelectableCharacters.Bjin;
break;
case "NorthWestDiamond":
makeAllDissapear();
Xavier.SetActive(true);
TextObject.GetComponentInChildren <Text>().text = "Xavier";
curChar = SelectableCharacters.Xavier;
break;
default:
break;
}
}
public void selectChar()
{
switch (curChar)
{
case SelectableCharacters.Leslie:
TextObject.GetComponentInChildren <Text>().text = "Leslie Selected";
Leslie.GetComponent <Image>().sprite = SelectedImages[0];
CD.GetComponent <Collider2D>().isTrigger = false;
break;
case SelectableCharacters.Jona:
TextObject.GetComponentInChildren <Text>().text = "Jona Selected";
Jona.GetComponent <Image>().sprite = SelectedImages[1];
ND.GetComponent <Collider2D>().isTrigger = false;
break;
case SelectableCharacters.Ashita:
TextObject.GetComponentInChildren <Text>().text = "Ashita Selected";
Ashita.GetComponent <Image>().sprite = SelectedImages[2];
NED.GetComponent <Collider2D>().isTrigger = false;
break;
case SelectableCharacters.Catarine:
TextObject.GetComponentInChildren <Text>().text = "Catarine Selected";
Catarine.GetComponent <Image>().sprite = SelectedImages[3];
ED.GetComponent <Collider2D>().isTrigger = false;
break;
case SelectableCharacters.Ramsey:
TextObject.GetComponentInChildren <Text>().text = "Ramsey Selected";
Ramsey.GetComponent <Image>().sprite = SelectedImages[4];
SED.GetComponent <Collider2D>().isTrigger = false;
break;
case SelectableCharacters.Drogas:
TextObject.GetComponentInChildren <Text>().text = "Drogas Selected";
Drogas.GetComponent <Image>().sprite = SelectedImages[5];
SD.GetComponent <Collider2D>().isTrigger = false;
break;
case SelectableCharacters.Sylvia:
TextObject.GetComponentInChildren <Text>().text = "Sylvia Selected";
Sylvia.GetComponent <Image>().sprite = SelectedImages[6];
SWD.GetComponent <Collider2D>().isTrigger = false;
break;
case SelectableCharacters.Bjin:
TextObject.GetComponentInChildren <Text>().text = "Bjin Selected";
Bjin.GetComponent <Image>().sprite = SelectedImages[7];
WD.GetComponent <Collider2D>().isTrigger = false;
break;
case SelectableCharacters.Xavier:
TextObject.GetComponentInChildren <Text>().text = "Xavier Selected";
Xavier.GetComponent <Image>().sprite = SelectedImages[8];
NWD.GetComponent <Collider2D>().isTrigger = false;
break;
default:
break;
}
characterChosen = true;
weaponMenu();
}
