train with pretrain

.gitignore

@@ -6,3 +6,4 @@ __pycache__/
 Dataset/
 .vscode
 /*/__pycache__
+.mypy_cache

FilterEvaluator/Evaluator.py

@@ -39,63 +39,19 @@ model = utils.SetDevice(Model.Net3Grad335())
 
 
 
-# model = utils.LoadModel(model, CurrentPath+"/checkpoint.pkl")
+model = utils.LoadModel(model, CurrentPath+"/checkpoint.pkl")
 
 
 
 
 
-# a = model.features[0].weight.data
-
-
-
-
 # traindata, testdata = Loader.MNIST(batchsize)
 # traindata, testdata = Loader.RandomMnist(batchsize, style="Vertical")
 # traindata, testdata = Loader.RandomMnist(batchsize, style="Horizontal")
 # traindata, testdata = Loader.RandomMnist(batchsize, style="VerticalOneLine")
 # traindata, testdata = Loader.RandomMnist(batchsize, style="VerticalZebra")
 # traindata, testdata = Loader.Cifar10Mono(batchsize)
-traindata, testdata = Loader.Cifar10Mono(batchsize, num_workers=2, shuffle=True)
-
-
-# def GetSample(netmodel,layer,dataloader,iteration=-1):
-#     netmodel.eval()
-#     sample = []
-#     for batch_idx, (data, target) in enumerate(dataloader):
-#         data = utils.SetDevice(data)
-#         target = utils.SetDevice(target)
-#         layerout = []
-#         layerint = []
-#         def getnet(self, input, output):
-#             layerout.append(output)
-#             layerint.append(input)
-#         handle = netmodel.features[layer].register_forward_hook(getnet)
-#         netmodel.forwardLayer(data,layer=layer)
-#         output = layerout[0][:,:,:,:]
-
-#         handle.remove()
-#         data.detach()
-#         target.detach()
-        
-#         sample.append(output.cpu().detach().numpy())
-#         if iteration > 0 and batch_idx >= (iteration-1):
-#             break
-
-#     sample = np.array(sample)
-#     sample = np.swapaxes(sample,2,0)
-#     sample = np.reshape(sample,(sample.shape[0],-1))
-
-#     active = []
-#     for i in range(sample.shape[0]):
-#         data = sample[i]
-#         mean = np.mean(data)
-#         dat1 = np.mean(np.abs(data - mean))
-#         dat2 = (data - mean)/dat1
-#         dat2 = np.mean(dat2*dat2)
-#         active.append(dat2)
-
-#     return active
+traindata, testdata = Loader.Cifar10Mono(batchsize, num_workers=0, shuffle=True)
 
 
 def GetSample(netmodel,layer,dataloader,iteration=-1):
@@ -128,15 +84,18 @@ def GetSample(netmodel,layer,dataloader,iteration=-1):
     dat2 = torch.mean(dat2 * dat2,dim=1)
     return dat2.cpu().detach().numpy()
 
-def weightToImage(weight,filename):
-    a2 = model.features[layear].weight.data[channel]
-    a2 = a2.cpu().detach().numpy().reshape(( a2.shape[-2], a2.shape[-1]))
-
-    a2min = np.min(a2)
-    a2max = np.max(a2)
-    a2 = (a2 - a2min)*255.0/(a2max-a2min)
-    a2 = a2.astype(int)
-    cv2.imwrite(filename,a2)
+def ConvKernelToImage(model, layer, foldname):
+    if not os.path.exists(foldname):
+        os.mkdir(foldname)
+    a2 = model.features[layer].weight.data
+    a2 = a2.cpu().detach().numpy().reshape((-1, a2.shape[-2], a2.shape[-1]))
+    for i in range(a2.shape[0]):
+        d = a2[i]
+        dmin = np.min(d)
+        dmax = np.max(d)
+        d = (d - dmin)*255.0/(dmax-dmin)
+        d = d.astype(int)
+        cv2.imwrite(foldname+"/"+str(i)+".png", d)
 
 def GetRandomSocre(netmodel,layer,dataloader,iteration=-1):
     weightshape = netmodel.features[layer].weight.data.shape
@@ -148,6 +107,12 @@ def GetRandomSocre(netmodel,layer,dataloader,iteration=-1):
   
 
 
+ConvKernelToImage(model, 0, CurrentPath+"image")
+
+
+
+
+
 layer = 0
 
 weightshape = list(model.features[layer].weight.data.shape)

FilterEvaluator/TrainNetwork.py

@@ -14,6 +14,7 @@ from torch.utils.data import Dataset, DataLoader
 from PIL import Image
 import random
 import cv2
+from visdom import Visdom
 
 
 CurrentPath = os.path.split(os.path.realpath(__file__))[0]+"/"
@@ -23,36 +24,73 @@ sys.path.append(CurrentPath+'../tools')
 sys.path.append(CurrentPath+'../')
 
 import Model
-from tools import utils, Train, Loader
+from tools import utils, Train, Loader, WebVisual
+
 
 batchsize = 128
 
 
+
+# traindata, testdata = Loader.MNIST(batchsize, num_workers=4)
+# 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")
+# traindata, testdata = Loader.RandomMnist(batchsize, num_workers=4, style="VerticalZebra")
+traindata, testdata = Loader.Cifar10Mono(batchsize, num_workers=4,shuffle=True,trainsize=500)
+
+
+
+
+
+
+
+
+WebVisual.InitVisdom()
+window = WebVisual.LineWin()
+lineNoPre = WebVisual.Line("NoPre")
+linePretrain = WebVisual.Line("Pretrain")
+
+
+
+
+
+
 # model = utils.SetDevice(Model.Net535())
 # model = utils.SetDevice(Model.Net5Grad35())
 # model = utils.SetDevice(Model.Net31535())
-# model = utils.SetDevice(Model.Net3335()) # Test set: Average loss: 1.5294, Accuracy: 4501/10000 (45%)
+# model = utils.SetDevice(Model.Net3335()) 
 model = utils.SetDevice(Model.Net3Grad335())
 
 
 
+# model = utils.LoadModel(model, CurrentPath+"/checkpoint.pkl")
+
+
+
+optimizer = optim.SGD(model.parameters(), lr=0.1)
+# optimizer = optim.Adam(model.parameters(), lr=0.01)
+
+
+
 
 model = utils.LoadModel(model, CurrentPath+"/checkpoint.pkl")
-
-optimizer = optim.SGD(model.parameters(), lr=0.01)
-
-
-# traindata, testdata = Loader.MNIST(batchsize, num_workers=8)
-# traindata, testdata = Loader.RandomMnist(batchsize, num_workers=8, style="Vertical")
-# traindata, testdata = Loader.RandomMnist(batchsize, num_workers=8, style="Horizontal")
-# traindata, testdata = Loader.RandomMnist(batchsize, num_workers=8, style="VerticalOneLine")
-# traindata, testdata = Loader.RandomMnist(batchsize, num_workers=8, style="VerticalZebra")
-traindata, testdata = Loader.Cifar10Mono(batchsize, num_workers=8)
-
-
-
-for i in range(300):
+for i in range(2000):
     Train.train(model,traindata,optimizer,epoch=i)
-    Train.test(model,testdata)
+    window.AppendData(linePretrain,Train.test(model,testdata))
 
-utils.SaveModel(model,CurrentPath+"/checkpoint.pkl")
+
+
+model = utils.SetDevice(Model.Net3335())
+optimizer = optim.SGD(model.parameters(), lr=0.1)
+for i in range(2000):
+    Train.train(model, traindata, optimizer, epoch=i)
+    window.AppendData(lineNoPre, Train.test(model, testdata))
+
+
+
+
+
+
+
+
+# utils.SaveModel(model,CurrentPath+"/checkpointSGDPreTrain.pkl")

PaintVgg19/PaintVgg19Weight.py

@@ -1,5 +1,5 @@
 from __future__ import print_function
-from vgg19Pytorch import Vgg19Module
+# from vgg19Pytorch import Vgg19Module
 import torch
 import torch.nn as nn
 import torch.nn.functional as F
@@ -83,94 +83,94 @@ for w, p in zip(words[top5], probs):
     print('{}\tprobability:{}'.format(w, p))
 #endregion
 
-# region write image and weight
-image = readAndPreprocessImage(CurrentPath+"dog_resize.jpg")
-conv1_1_pad = F.pad(image, (1L, 1L, 1L, 1L))
-conv1_1 = vgg19.conv1_1(conv1_1_pad)
-relu1_1 = F.relu(conv1_1)
-conv1_2_pad = F.pad(relu1_1, (1L, 1L, 1L, 1L))
-conv1_2 = vgg19.conv1_2(conv1_2_pad)
-relu1_2 = F.relu(conv1_2)
-pool1 = F.max_pool2d(relu1_2, kernel_size=(2L, 2L), stride=(2L, 2L), padding=(0L,), ceil_mode=True)
-conv2_1_pad = F.pad(pool1, (1L, 1L, 1L, 1L))
-conv2_1 = vgg19.conv2_1(conv2_1_pad)
-relu2_1 = F.relu(conv2_1)
-conv2_2_pad = F.pad(relu2_1, (1L, 1L, 1L, 1L))
-conv2_2 = vgg19.conv2_2(conv2_2_pad)
-relu2_2 = F.relu(conv2_2)
-pool2 = F.max_pool2d(relu2_2, kernel_size=(2L, 2L), stride=(2L, 2L), padding=(0L,), ceil_mode=True)
-conv3_1_pad = F.pad(pool2, (1L, 1L, 1L, 1L))
-conv3_1 = vgg19.conv3_1(conv3_1_pad)
-relu3_1 = F.relu(conv3_1)
-conv3_2_pad = F.pad(relu3_1, (1L, 1L, 1L, 1L))
-conv3_2 = vgg19.conv3_2(conv3_2_pad)
-relu3_2 = F.relu(conv3_2)
-conv3_3_pad = F.pad(relu3_2, (1L, 1L, 1L, 1L))
-conv3_3 = vgg19.conv3_3(conv3_3_pad)
-relu3_3 = F.relu(conv3_3)
-conv3_4_pad = F.pad(relu3_3, (1L, 1L, 1L, 1L))
-conv3_4 = vgg19.conv3_4(conv3_4_pad)
-relu3_4 = F.relu(conv3_4)
-pool3 = F.max_pool2d(relu3_4, kernel_size=(2L, 2L), stride=(2L, 2L), padding=(0L,), ceil_mode=True)
-conv4_1_pad = F.pad(pool3, (1L, 1L, 1L, 1L))
-conv4_1 = vgg19.conv4_1(conv4_1_pad)
-relu4_1 = F.relu(conv4_1)
-conv4_2_pad = F.pad(relu4_1, (1L, 1L, 1L, 1L))
-conv4_2 = vgg19.conv4_2(conv4_2_pad)
-relu4_2 = F.relu(conv4_2)
-conv4_3_pad = F.pad(relu4_2, (1L, 1L, 1L, 1L))
-conv4_3 = vgg19.conv4_3(conv4_3_pad)
-relu4_3 = F.relu(conv4_3)
-conv4_4_pad = F.pad(relu4_3, (1L, 1L, 1L, 1L))
-conv4_4 = vgg19.conv4_4(conv4_4_pad)
-relu4_4 = F.relu(conv4_4)
-pool4 = F.max_pool2d(relu4_4, kernel_size=(2L, 2L), stride=(2L, 2L), padding=(0L,), ceil_mode=True)
-conv5_1_pad = F.pad(pool4, (1L, 1L, 1L, 1L))
-conv5_1 = vgg19.conv5_1(conv5_1_pad)
-relu5_1 = F.relu(conv5_1)
-conv5_2_pad = F.pad(relu5_1, (1L, 1L, 1L, 1L))
-conv5_2 = vgg19.conv5_2(conv5_2_pad)
-relu5_2 = F.relu(conv5_2)
-conv5_3_pad = F.pad(relu5_2, (1L, 1L, 1L, 1L))
-conv5_3 = vgg19.conv5_3(conv5_3_pad)
-relu5_3 = F.relu(conv5_3)
-conv5_4_pad = F.pad(relu5_3, (1L, 1L, 1L, 1L))
-conv5_4 = vgg19.conv5_4(conv5_4_pad)
-relu5_4 = F.relu(conv5_4)
-pool5 = F.max_pool2d(relu5_4, kernel_size=(2L, 2L), stride=(2L, 2L), padding=(0L,), ceil_mode=True)
-fc6_0 = pool5.view(pool5.size(0), -1)
+# # region write image and weight
+# image = readAndPreprocessImage(CurrentPath+"dog_resize.jpg")
+# conv1_1_pad = F.pad(image, (1L, 1L, 1L, 1L))
+# conv1_1 = vgg19.conv1_1(conv1_1_pad)
+# relu1_1 = F.relu(conv1_1)
+# conv1_2_pad = F.pad(relu1_1, (1L, 1L, 1L, 1L))
+# conv1_2 = vgg19.conv1_2(conv1_2_pad)
+# relu1_2 = F.relu(conv1_2)
+# pool1 = F.max_pool2d(relu1_2, kernel_size=(2L, 2L), stride=(2L, 2L), padding=(0L,), ceil_mode=True)
+# conv2_1_pad = F.pad(pool1, (1L, 1L, 1L, 1L))
+# conv2_1 = vgg19.conv2_1(conv2_1_pad)
+# relu2_1 = F.relu(conv2_1)
+# conv2_2_pad = F.pad(relu2_1, (1L, 1L, 1L, 1L))
+# conv2_2 = vgg19.conv2_2(conv2_2_pad)
+# relu2_2 = F.relu(conv2_2)
+# pool2 = F.max_pool2d(relu2_2, kernel_size=(2L, 2L), stride=(2L, 2L), padding=(0L,), ceil_mode=True)
+# conv3_1_pad = F.pad(pool2, (1L, 1L, 1L, 1L))
+# conv3_1 = vgg19.conv3_1(conv3_1_pad)
+# relu3_1 = F.relu(conv3_1)
+# conv3_2_pad = F.pad(relu3_1, (1L, 1L, 1L, 1L))
+# conv3_2 = vgg19.conv3_2(conv3_2_pad)
+# relu3_2 = F.relu(conv3_2)
+# conv3_3_pad = F.pad(relu3_2, (1L, 1L, 1L, 1L))
+# conv3_3 = vgg19.conv3_3(conv3_3_pad)
+# relu3_3 = F.relu(conv3_3)
+# conv3_4_pad = F.pad(relu3_3, (1L, 1L, 1L, 1L))
+# conv3_4 = vgg19.conv3_4(conv3_4_pad)
+# relu3_4 = F.relu(conv3_4)
+# pool3 = F.max_pool2d(relu3_4, kernel_size=(2L, 2L), stride=(2L, 2L), padding=(0L,), ceil_mode=True)
+# conv4_1_pad = F.pad(pool3, (1L, 1L, 1L, 1L))
+# conv4_1 = vgg19.conv4_1(conv4_1_pad)
+# relu4_1 = F.relu(conv4_1)
+# conv4_2_pad = F.pad(relu4_1, (1L, 1L, 1L, 1L))
+# conv4_2 = vgg19.conv4_2(conv4_2_pad)
+# relu4_2 = F.relu(conv4_2)
+# conv4_3_pad = F.pad(relu4_2, (1L, 1L, 1L, 1L))
+# conv4_3 = vgg19.conv4_3(conv4_3_pad)
+# relu4_3 = F.relu(conv4_3)
+# conv4_4_pad = F.pad(relu4_3, (1L, 1L, 1L, 1L))
+# conv4_4 = vgg19.conv4_4(conv4_4_pad)
+# relu4_4 = F.relu(conv4_4)
+# pool4 = F.max_pool2d(relu4_4, kernel_size=(2L, 2L), stride=(2L, 2L), padding=(0L,), ceil_mode=True)
+# conv5_1_pad = F.pad(pool4, (1L, 1L, 1L, 1L))
+# conv5_1 = vgg19.conv5_1(conv5_1_pad)
+# relu5_1 = F.relu(conv5_1)
+# conv5_2_pad = F.pad(relu5_1, (1L, 1L, 1L, 1L))
+# conv5_2 = vgg19.conv5_2(conv5_2_pad)
+# relu5_2 = F.relu(conv5_2)
+# conv5_3_pad = F.pad(relu5_2, (1L, 1L, 1L, 1L))
+# conv5_3 = vgg19.conv5_3(conv5_3_pad)
+# relu5_3 = F.relu(conv5_3)
+# conv5_4_pad = F.pad(relu5_3, (1L, 1L, 1L, 1L))
+# conv5_4 = vgg19.conv5_4(conv5_4_pad)
+# relu5_4 = F.relu(conv5_4)
+# pool5 = F.max_pool2d(relu5_4, kernel_size=(2L, 2L), stride=(2L, 2L), padding=(0L,), ceil_mode=True)
+# fc6_0 = pool5.view(pool5.size(0), -1)
 
-imageVisual(conv1_1, "conv1_1", 8)
-imageVisual(conv1_2, 'conv1_2', 8)
-imageVisual(conv2_1, "conv2_1", 16)
-imageVisual(conv2_2, "conv2_2", 16)
-imageVisual(conv3_1, "conv3_1", 16)
-imageVisual(conv3_2, "conv3_2", 16)
-imageVisual(conv3_3, "conv3_3", 16)
-imageVisual(conv3_4, "conv3_4", 16)
-imageVisual(conv4_1, "conv4_1", 32)
-imageVisual(conv4_2, "conv4_2", 32)
-imageVisual(conv4_3, "conv4_3", 32)
-imageVisual(conv4_4, "conv4_4", 32)
-imageVisual(conv5_1, "conv5_1", 32)
-imageVisual(conv5_2, "conv5_2", 32)
-imageVisual(conv5_3, "conv5_3", 32)
-imageVisual(conv5_4, "conv5_4", 32)
+# imageVisual(conv1_1, "conv1_1", 8)
+# imageVisual(conv1_2, 'conv1_2', 8)
+# imageVisual(conv2_1, "conv2_1", 16)
+# imageVisual(conv2_2, "conv2_2", 16)
+# imageVisual(conv3_1, "conv3_1", 16)
+# imageVisual(conv3_2, "conv3_2", 16)
+# imageVisual(conv3_3, "conv3_3", 16)
+# imageVisual(conv3_4, "conv3_4", 16)
+# imageVisual(conv4_1, "conv4_1", 32)
+# imageVisual(conv4_2, "conv4_2", 32)
+# imageVisual(conv4_3, "conv4_3", 32)
+# imageVisual(conv4_4, "conv4_4", 32)
+# imageVisual(conv5_1, "conv5_1", 32)
+# imageVisual(conv5_2, "conv5_2", 32)
+# imageVisual(conv5_3, "conv5_3", 32)
+# imageVisual(conv5_4, "conv5_4", 32)
 
-weightVisual(vgg19.conv1_1, "conv1_1")
-weightVisual(vgg19.conv1_2, 'conv1_2')
-weightVisual(vgg19.conv2_1, "conv2_1")
-weightVisual(vgg19.conv2_2, "conv2_2")
-weightVisual(vgg19.conv3_1, "conv3_1")
-weightVisual(vgg19.conv3_2, "conv3_2")
-weightVisual(vgg19.conv3_3, "conv3_3")
-weightVisual(vgg19.conv3_4, "conv3_4")
-weightVisual(vgg19.conv4_1, "conv4_1")
-weightVisual(vgg19.conv4_2, "conv4_2")
-weightVisual(vgg19.conv4_3, "conv4_3")
-weightVisual(vgg19.conv4_4, "conv4_4")
-weightVisual(vgg19.conv5_1, "conv5_1")
-weightVisual(vgg19.conv5_2, "conv5_2")
-weightVisual(vgg19.conv5_3, "conv5_3")
-weightVisual(vgg19.conv5_4, "conv5_4")
-# endregion
+# weightVisual(vgg19.conv1_1, "conv1_1")
+# weightVisual(vgg19.conv1_2, 'conv1_2')
+# weightVisual(vgg19.conv2_1, "conv2_1")
+# weightVisual(vgg19.conv2_2, "conv2_2")
+# weightVisual(vgg19.conv3_1, "conv3_1")
+# weightVisual(vgg19.conv3_2, "conv3_2")
+# weightVisual(vgg19.conv3_3, "conv3_3")
+# weightVisual(vgg19.conv3_4, "conv3_4")
+# weightVisual(vgg19.conv4_1, "conv4_1")
+# weightVisual(vgg19.conv4_2, "conv4_2")
+# weightVisual(vgg19.conv4_3, "conv4_3")
+# weightVisual(vgg19.conv4_4, "conv4_4")
+# weightVisual(vgg19.conv5_1, "conv5_1")
+# weightVisual(vgg19.conv5_2, "conv5_2")
+# weightVisual(vgg19.conv5_3, "conv5_3")
+# weightVisual(vgg19.conv5_4, "conv5_4")
+# # endregion

tools/Loader.py

@@ -1,17 +1,13 @@
-# from __future__ import print_function
 import os
 import torch
 import torchvision
 from torchvision import datasets, transforms
 import torchvision.models as models
 import numpy as np
-from torch.utils.data import Dataset, DataLoader
+from torch.utils.data import Dataset, DataLoader, Subset
 import random
 
 
-
-
-
 def MNIST(batchsize=8, num_workers=0, shuffle=False):
   CurrentPath = os.path.split(os.path.realpath(__file__))[0]+"/"
   train_loader = torch.utils.data.DataLoader(
@@ -46,23 +42,24 @@ def Cifar10(batchsize=8, num_workers=0, shuffle=False):
 
     return train_loader, test_loader
 
-def Cifar10Mono(batchsize=8, num_workers=0, shuffle=False):
+def Cifar10Mono(batchsize=8, num_workers=0, shuffle=False, trainsize=0):
     CurrentPath = os.path.split(os.path.realpath(__file__))[0]+"/"
-    
+    dataset = datasets.CIFAR10(root=CurrentPath+'../Dataset/', train=True, download=True,
+                               transform=transforms.Compose([
+                                   transforms.Grayscale(),
+                                   transforms.ToTensor(),
+                                   transforms.Normalize((0.1307,), (0.3081,))
+                               ]))
+    if trainsize == 0:
+        trainsize = dataset.data.shape[0]
     train_loader = torch.utils.data.DataLoader(
-    datasets.CIFAR10(root=CurrentPath+'../Dataset/', train=True, download=True,
-                    transform=transforms.Compose([
-                        transforms.Grayscale(),
-                        transforms.ToTensor(),
-                        transforms.Normalize((0.1307,), (0.3081,))
-                    ])), batch_size=batchsize, shuffle=shuffle, num_workers=num_workers, drop_last=True)
+        Subset(dataset, range(0, trainsize)), batch_size=batchsize, shuffle=shuffle, num_workers=num_workers, drop_last=True)
     test_loader = torch.utils.data.DataLoader(
         datasets.CIFAR10(root=CurrentPath+'../Dataset/', train=False, transform=transforms.Compose([
             transforms.Grayscale(),
             transforms.ToTensor(),
             transforms.Normalize((0.1307,), (0.3081,))
         ])), batch_size=batchsize, shuffle=shuffle, num_workers=num_workers, drop_last=True)
-
     return train_loader, test_loader
 
 def RandomMnist(batchsize=8, num_workers=0, shuffle=False, style=""):
@@ -124,6 +121,7 @@ def RandomMnist(batchsize=8, num_workers=0, shuffle=False, style=""):
         transforms.RandomRotation(30),
         transforms.RandomResizedCrop(28),
         transforms.ToTensor(), transforms.Normalize((0.1307,), (0.3081,))]))
+
     train_loader = torch.utils.data.DataLoader(train_data,
                                                batch_size=batchsize,
                                                shuffle=shuffle,

tools/Train.py

@@ -11,11 +11,13 @@ import os
 import utils as utils
 
 
-def train(model, train_loader, optimizer, epoch=0, deviceid=[0]):
+def train(model, train_loader, optimizer, epoch=0):
     model.train()
+    batchsize = int(train_loader.sampler.num_samples /
+                    train_loader.batch_size / 5)+1
     for batch_idx, (data, target) in enumerate(train_loader):
-        data = utils.SetDevice(data, deviceid)
-        target = utils.SetDevice(target, deviceid)
+        data = utils.SetDevice(data)
+        target = utils.SetDevice(target)
         optimizer.zero_grad()
 
         output = model(data)
@@ -23,7 +25,7 @@ def train(model, train_loader, optimizer, epoch=0, deviceid=[0]):
         loss.backward()
         optimizer.step()
 
-        if batch_idx % 100 == 0 and batch_idx > 0:
+        if batch_idx % batchsize == 0 and batch_idx > 0:
             print('Train Epoch: {} [{}/{} ({:.0f}%)]\tLoss: {:.6f}'
                   .format(epoch, batch_idx * len(data),
                           len(train_loader.dataset),
@@ -32,14 +34,14 @@ def train(model, train_loader, optimizer, epoch=0, deviceid=[0]):
                           loss.item()))
 
 
-def test(model, test_loader, deviceid=[0]):
+def test(model, test_loader):
     with torch.no_grad():
         model.eval()
         test_loss = 0
         correct = 0
         for data, target in test_loader:
-            data = utils.SetDevice(data, deviceid)
-            target = utils.SetDevice(target, deviceid)
+            data = utils.SetDevice(data)
+            target = utils.SetDevice(target)
             output = model(data)
 
             # sum up batch loss
@@ -49,9 +51,7 @@ def test(model, test_loader, deviceid=[0]):
             correct += pred.eq(target.view_as(pred)).sum().item()
 
         test_loss /= len(test_loader.dataset)
+        accu = 100. * correct / len(test_loader.dataset)
         print('\nTest set: Average loss: {:.4f}, Accuracy: {}/{} ({:.0f}%)\n'
-              .format(test_loss, correct,
-                      len(
-                          test_loader.dataset),
-                      100. * correct / len(
-                          test_loader.dataset)))
+              .format(test_loss, correct, len(test_loader.dataset), accu))
+        return accu

tools/WebVisual.py

@@ -0,0 +1,64 @@
+from visdom import Visdom
+import random
+import numpy as np
+
+
+
+def InitVisdom():
+    viz = Visdom()
+    assert viz.check_connection()
+    viz.close()
+
+class Line():
+    def __init__(self,name,size):
+        super(Line, self).__init__()
+        self.name=name
+        self.size=size
+    def __init__(self):
+        super(Line, self).__init__()
+        self.name=str(random.random())
+        self.size=0
+    def __init__(self,name):
+        super(Line, self).__init__()
+        self.name=name
+        self.size=0
+
+class LineWin():
+    def __init__(self):
+        super(LineWin, self).__init__()
+        self.viz = Visdom()
+        self.name = str(random.random())
+        self.win = self.viz.line(
+            X=np.array([0]),
+            Y=np.array([0]),
+            name=self.name
+        )
+        self.data = np.array([])
+        
+    def AppendLine(self,y):
+        if not isinstance(y,list):
+            y = [y]
+        linename = str(random.random())
+        self.viz.line(
+            X=np.array(range(len(y))),
+            Y=np.array(y),
+            opts=dict(markercolor=np.array([50]),
+                    markersymbol='dot',),
+            win=self.win,
+            update="new",
+            name=linename,
+        )
+        return Line(linename,len(y))
+
+    def AppendData(self,line, y):
+        if not isinstance(y,list):
+            y = [y]
+        self.viz.line(
+            X=np.array(range(line.size, line.size+len(y))),
+            Y=np.array(y),
+            win=self.win,
+            update="append",
+            name=line.name
+        )
+        line.size = line.size + len(y)
+