remove random seed

tutorial-contents/301_regression.py

@@ -11,7 +11,7 @@ from torch.autograd import Variable
 import torch.nn.functional as F
 import matplotlib.pyplot as plt
 
-torch.manual_seed(1)    # reproducible
+# torch.manual_seed(1)    # reproducible
 
 x = torch.unsqueeze(torch.linspace(-1, 1, 100), dim=1)  # x data (tensor), shape=(100, 1)
 y = x.pow(2) + 0.2*torch.rand(x.size())                 # noisy y data (tensor), shape=(100, 1)

tutorial-contents/302_classification.py

@@ -11,7 +11,7 @@ from torch.autograd import Variable
 import torch.nn.functional as F
 import matplotlib.pyplot as plt
 
-torch.manual_seed(1)    # reproducible
+# torch.manual_seed(1)    # reproducible
 
 # make fake data
 n_data = torch.ones(100, 2)

tutorial-contents/304_save_reload.py

@@ -10,7 +10,7 @@ import torch
 from torch.autograd import Variable
 import matplotlib.pyplot as plt
 
-torch.manual_seed(1)    # reproducible
+# torch.manual_seed(1)    # reproducible
 
 # fake data
 x = torch.unsqueeze(torch.linspace(-1, 1, 100), dim=1)  # x data (tensor), shape=(100, 1)

tutorial-contents/306_optimizer.py

@@ -12,7 +12,7 @@ import torch.nn.functional as F
 from torch.autograd import Variable
 import matplotlib.pyplot as plt
 
-torch.manual_seed(1)    # reproducible
+# torch.manual_seed(1)    # reproducible
 
 LR = 0.01
 BATCH_SIZE = 32

tutorial-contents/401_CNN.py

@@ -19,7 +19,7 @@ import torch.utils.data as Data
 import torchvision
 import matplotlib.pyplot as plt
 
-torch.manual_seed(1)    # reproducible
+# torch.manual_seed(1)    # reproducible
 
 # Hyper Parameters
 EPOCH = 1               # train the training data n times, to save time, we just train 1 epoch

tutorial-contents/402_RNN_classifier.py

@@ -15,7 +15,7 @@ import torchvision.transforms as transforms
 import matplotlib.pyplot as plt
 
 
-torch.manual_seed(1)    # reproducible
+# torch.manual_seed(1)    # reproducible
 
 # Hyper Parameters
 EPOCH = 1               # train the training data n times, to save time, we just train 1 epoch

tutorial-contents/403_RNN_regressor.py

@@ -13,7 +13,7 @@ from torch.autograd import Variable
 import numpy as np
 import matplotlib.pyplot as plt
 
-torch.manual_seed(1)    # reproducible
+# torch.manual_seed(1)    # reproducible
 
 # Hyper Parameters
 TIME_STEP = 10      # rnn time step

tutorial-contents/404_autoencoder.py

@@ -18,7 +18,7 @@ from matplotlib import cm
 import numpy as np
 
 
-torch.manual_seed(1)    # reproducible
+# torch.manual_seed(1)    # reproducible
 
 # Hyper Parameters
 EPOCH = 10

tutorial-contents/406_GAN.py

@@ -13,8 +13,8 @@ from torch.autograd import Variable
 import numpy as np
 import matplotlib.pyplot as plt
 
-torch.manual_seed(1)    # reproducible
-np.random.seed(1)
+# torch.manual_seed(1)    # reproducible
+# np.random.seed(1)
 
 # Hyper Parameters
 BATCH_SIZE = 64

tutorial-contents/406_conditional_GAN.py

@@ -13,8 +13,8 @@ from torch.autograd import Variable
 import numpy as np
 import matplotlib.pyplot as plt
 
-torch.manual_seed(1)    # reproducible
-np.random.seed(1)
+# torch.manual_seed(1)    # reproducible
+# np.random.seed(1)
 
 # Hyper Parameters
 BATCH_SIZE = 64

tutorial-contents/501_why_torch_dynamic_graph.py

@@ -13,7 +13,7 @@ from torch.autograd import Variable
 import numpy as np
 import matplotlib.pyplot as plt
 
-torch.manual_seed(1)    # reproducible
+# torch.manual_seed(1)    # reproducible
 
 # Hyper Parameters
 INPUT_SIZE = 1          # rnn input size / image width

tutorial-contents/502_GPU.py

@@ -12,7 +12,7 @@ from torch.autograd import Variable
 import torch.utils.data as Data
 import torchvision
 
-torch.manual_seed(1)
+# torch.manual_seed(1)
 
 EPOCH = 1
 BATCH_SIZE = 50

tutorial-contents/503_dropout.py

@@ -10,7 +10,7 @@ import torch
 from torch.autograd import Variable
 import matplotlib.pyplot as plt
 
-torch.manual_seed(1)    # reproducible
+# torch.manual_seed(1)    # reproducible
 
 N_SAMPLES = 20
 N_HIDDEN = 300

tutorial-contents/504_batch_normalization.py

@@ -16,8 +16,8 @@ import torch.nn.functional as F
 import matplotlib.pyplot as plt
 import numpy as np
 
-torch.manual_seed(1)    # reproducible
-np.random.seed(1)
+# torch.manual_seed(1)    # reproducible
+# np.random.seed(1)
 
 # Hyper parameters
 N_SAMPLES = 2000