move to py3

Author: redone17

iter_utils.py

@@ -45,10 +45,10 @@ def train(model, train_loader, criterion, optimizer, init_lr=0.001, decay_epoch=
                 if phase == 'train':
                     loss.backward()
                     optimizer.step()
-                running_loss += loss.data[0]
+                running_loss += loss.data
                 _, predicted = torch.max(outputs.data, 1)
-                running_corrects += torch.sum(predicted==targets.data)
-                loss_curve.append(loss.data[0])
+                running_corrects += torch.sum(predicted==targets.data).item()
+                loss_curve.append(loss.data)
 
             epoch_loss = running_loss / len(train_loader.dataset)
             epoch_accuracy = running_corrects / len(train_loader.dataset)
@@ -68,10 +68,10 @@ def test(model, test_loader):
     corrects = 0
     model = model.cpu()
     for batch_idx, (inputs, targets) in enumerate(test_loader):
-        inputs, targets = Variable(inputs, volatile=True), Variable(targets)
-        outputs = model(inputs)
-        _, predicted = torch.max(outputs.data, 1)
-        corrects += torch.sum(predicted==targets.data)
+        with torch.no_grad():
+            inputs, targets = Variable(inputs), Variable(targets)
+            outputs = model(inputs)
+            _, predicted = torch.max(outputs.data, 1)
+            corrects += torch.sum(predicted==targets.data).item()
     accuracy = corrects / len(test_loader.dataset)
     return accuracy
-

run.py

@@ -20,38 +20,45 @@
 import torch.utils.data as data_utils
 from models import *
 
-## load data
-data_arr_01 = data_loader.load_data('data/pgb/SF01/vib_data_1.txt')
-# data_arr_03 = data_loader.load_data('data/pgb/SF03/vib_data_1.txt')
-# data_arr_01 = data_loader.resample_arr(data_arr_01, num=240) # add for Ince's model
-# data_arr_03 = data_loader.resample_arr(data_arr_03, num=240) # add for Ince's model
-# data_arr_01, _ = data_loader.fft_arr(data_arr_01) # add for fft wdcnn
-# data_arr_03, _ = data_loader.fft_arr(data_arr_03) # add for fft wdcnn
-# data_arr_01 = data_loader.stft_arr(data_arr_01) # add for stft-LeNet
-# data_arr_03 = data_loader.stft_arr(data_arr_03)
-label_vec = data_loader.load_label('data/pgb/SF01/label_vec.txt')
-
-trainset_01, testset_01 = data_loader.split_set(data_arr_01, label_vec)
-# trainset_03, testset_03 = data_loader.split_set(data_arr_03, label_vec)
-train_loader = data_utils.DataLoader(dataset = trainset_01, batch_size =512 , shuffle = True, num_workers = 2)
-test_loader = data_utils.DataLoader(dataset = testset_01, batch_size = 512, shuffle = True, num_workers = 2)
-print('Number of training samples: {}'.format(len(train_loader.dataset)))
-print('Number of testing samples: {}'.format(len(test_loader.dataset)))
-print( )
-
-## make models
-model = dcnn.Net('DCNN08', 1, 5)
-
-## train
-criterion = nn.CrossEntropyLoss()
-optimizer = optim.Adam(model.parameters(), weight_decay=0.0001)
-best_model, loss_curve = iter_utils.train(model, train_loader, criterion, optimizer,
-    init_lr=0.0001, decay_epoch=5, n_epoch=10)
-
-# test
-test_accuracy = iter_utils.test(best_model, test_loader)
-print('Test accuracy: {:.4f}%'.format(100*test_accuracy))
-
-## visualization
-# TODO
+def main():
+    ## load data
+    # data_arr_01 = data_loader.load_data(r'toydata/data.txt')
+    # label_vec = data_loader.load_label(r'toydata/label.txt')
 
+    data_arr_01 = data_loader.load_data(r'data/uestc_pgb/SF01/vib_data_1.txt')
+    # data_arr_03 = data_loader.load_data('data/pgb/SF03/vib_data_1.txt')
+    # data_arr_01 = data_loader.resample_arr(data_arr_01, num=240) # add for Ince's model
+    # data_arr_03 = data_loader.resample_arr(data_arr_03, num=240) # add for Ince's model
+    # data_arr_01, _ = data_loader.fft_arr(data_arr_01) # add for fft wdcnn
+    # data_arr_03, _ = data_loader.fft_arr(data_arr_03) # add for fft wdcnn
+    # data_arr_01 = data_loader.stft_arr(data_arr_01) # add for stft-LeNet
+    # data_arr_03 = data_loader.stft_arr(data_arr_03)
+    label_vec = data_loader.load_label(r'data/uestc_pgb/SF01/label_vec.txt')
+
+    trainset_01, testset_01 = data_loader.split_set(data_arr_01, label_vec)
+    # trainset_03, testset_03 = data_loader.split_set(data_arr_03, label_vec)
+    train_loader = data_utils.DataLoader(dataset = trainset_01, batch_size =512 , shuffle = True, num_workers = 2)
+    test_loader = data_utils.DataLoader(dataset = testset_01, batch_size = 512, shuffle = True, num_workers = 2)
+    print('Number of training samples: {}'.format(len(train_loader.dataset)))
+    print('Number of testing samples: {}'.format(len(test_loader.dataset)))
+    print( )
+
+    ## make models
+    model = wdcnn.Net(1, 5)
+
+    ## train
+    criterion = nn.CrossEntropyLoss()
+    optimizer = optim.Adam(model.parameters(), weight_decay=0.0001)
+    best_model, loss_curve = iter_utils.train(model, train_loader, criterion, optimizer,
+        init_lr=0.0001, decay_epoch=5, n_epoch=10, use_cuda=False)
+
+    # test
+    test_accuracy = iter_utils.test(best_model, test_loader)
+    print('Test accuracy: {:.4f}%'.format(100*test_accuracy))
+
+
+    ## visualization
+    # TODO
+
+if __name__ == '__main__':
+    main()