fix as 4 kernels in first layer.

FilterEvaluator/EvaluatorUnsuper.py

@@ -232,7 +232,7 @@ def UnsuperLearnSearchBestWeight(netmodel, layer, dataloader, databatchs=128, st
             if hasdata > 0:
                 entropys = []
                 for i in range(len(indexs)):
-                    histced = bitted[:,i].histc(256,0,255).type(torch.float32)
+                    histced = bitted[:,i].histc(15,0,15).type(torch.float32)
                     histced = histced[histced>0]
                     histced = histced/histced.sum()
                     entropy = (histced.log2()*histced).sum()

FilterEvaluator/TrainNetwork.py

@@ -40,7 +40,7 @@ batchsize = 128
 
 
 # traindata, testdata = Loader.MNIST(batchsize, num_workers=4, trainsize=5000)
-traindata, testdata = Loader.MNIST(batchsize, resize=7, trainsize=50000)
+traindata, testdata = Loader.MNIST(batchsize, resize=7, trainsize=500)
 # traindata, testdata = Loader.RandomMnist(batchsize, num_workers=4, style="Vertical")
 # traindata, testdata = Loader.RandomMnist(batchsize, num_workers=4, style="Horizontal")
 # traindata, testdata = Loader.RandomMnist(batchsize, num_workers=4, style="VerticalOneLine")
@@ -97,7 +97,7 @@ Train.TrainEpochs(model,traindata,optimizer,testdata,3000,10,lineNoPre)
 # optimizer = optim.SGD(model.parameters(), lr=0.1)
 # Train.TrainEpochs(model,traindata,optimizer,testdata,3000,10,linePretrainSearch)
 
-model = utils.SetDevice(Model.Net3Grad33())
+model = utils.SetDevice(Model.Net333())
 model = utils.LoadModel(model, CurrentPath+"/checkpointEntropySearch.pkl")
 optimizer = optim.SGD(model.parameters(), lr=0.1)
 Train.TrainEpochs(model,traindata,optimizer,testdata,3000,10,linePreAllGrad)