a = torch.Tensor(3, 3).bernoulli_()

tensor([[1., 1., 1.],         [0., 1., 0.],         [0., 1., 0.]])

a = torch.Tensor(3, 3).normal_(0,1)

tensor([[ 0.7777,  0.9153, -0.1495],         [-0.0533,  1.6500, -1.2531],         [-0.5321,  0.1954, -1.3835]])

b = torch.tensor(a,requires_grad=True)

E:\anaconda2\envs\python36\lib\site-packages\ipykernel_launcher.py:1: UserWarning: To copy construct from a tensor, it is recommended to use sourceTensor.clone().detach() or sourceTensor.clone().detach().requires_grad_(True), rather than torch.tensor(sourceTensor).   """Entry point for launching an IPython kernel. Out[7]: tensor([[ 0.7777,  0.9153, -0.1495],         [-0.0533,  1.6500, -1.2531],         [-0.5321,  0.1954, -1.3835]], requires_grad=True)

c = a.clone().detach().requires_grad_(True)

tensor([[ 0.7777,  0.9153, -0.1495],         [-0.0533,  1.6500, -1.2531],         [-0.5321,  0.1954, -1.3835]], requires_grad=True)

class Net(nn.Module):     def __init__(self,input,hidden,classes):         super(Net, self).__init__()         self.input = input         self.hidden = hidden         self.classes = classes                  self.w0 = nn.Parameter(torch.Tensor(self.input,self.hidden))         self.b0 = nn.Parameter(torch.Tensor(self.hidden))         self.w1 = nn.Parameter(torch.Tensor(self.hidden,self.classes))         self.b1 = nn.Parameter(torch.Tensor(self.classes))         self.reset_parameters()              def reset_parameters(self):         nn.init.normal_(self.w0)         nn.init.constant_(self.b0,0)         nn.init.normal_(self.w1)         nn.init.constant_(self.b1,0)                       def forward(self,x):         out = torch.matmul(x,self.w0)+self.b0         out = F.relu(out)         out = torch.matmul(out,self.w1)+self.b1         return out

w = torch.empty(2, 3)  # 1. 均匀分布 - u(a,b) # torch.nn.init.uniform_(tensor, a=0, b=1) nn.init.uniform_(w) # tensor([[ 0.0578,  0.3402,  0.5034], #         [ 0.7865,  0.7280,  0.6269]])  # 2. 正态分布 - N(mean, std) # torch.nn.init.normal_(tensor, mean=0, std=1) nn.init.normal_(w) # tensor([[ 0.3326,  0.0171, -0.6745], #        [ 0.1669,  0.1747,  0.0472]])  # 3. 常数 - 固定值 val # torch.nn.init.constant_(tensor, val) nn.init.constant_(w, 0.3) # tensor([[ 0.3000,  0.3000,  0.3000], #         [ 0.3000,  0.3000,  0.3000]])  # 4. 对角线为 1，其它为 0 # torch.nn.init.eye_(tensor) nn.init.eye_(w) # tensor([[ 1.,  0.,  0.], #         [ 0.,  1.,  0.]])  # 5. Dirac delta 函数初始化，仅适用于 {3, 4, 5}-维的 torch.Tensor # torch.nn.init.dirac_(tensor) w1 = torch.empty(3, 16, 5, 5) nn.init.dirac_(w1)  # 6. xavier_uniform 初始化 # torch.nn.init.xavier_uniform_(tensor, gain=1) # From - Understanding the difficulty of training deep feedforward neural networks - Bengio 2010 nn.init.xavier_uniform_(w, gain=nn.init.calculate_gain('relu')) # tensor([[ 1.3374,  0.7932, -0.0891], #         [-1.3363, -0.0206, -0.9346]])  # 7. xavier_normal 初始化 # torch.nn.init.xavier_normal_(tensor, gain=1) nn.init.xavier_normal_(w) # tensor([[-0.1777,  0.6740,  0.1139], #         [ 0.3018, -0.2443,  0.6824]])  # 8. kaiming_uniform 初始化 # From - Delving deep into rectifiers: Surpassing human-level performance on ImageNet classification - HeKaiming 2015 # torch.nn.init.kaiming_uniform_(tensor, a=0, mode='fan_in', nonlinearity='leaky_relu') nn.init.kaiming_uniform_(w, mode='fan_in', nonlinearity='relu') # tensor([[ 0.6426, -0.9582, -1.1783], #         [-0.0515, -0.4975,  1.3237]])  # 9. kaiming_normal 初始化 # torch.nn.init.kaiming_normal_(tensor, a=0, mode='fan_in', nonlinearity='leaky_relu') nn.init.kaiming_normal_(w, mode='fan_out', nonlinearity='relu') # tensor([[ 0.2530, -0.4382,  1.5995], #         [ 0.0544,  1.6392, -2.0752]])  # 10. 正交矩阵 - (semi)orthogonal matrix # From - Exact solutions to the nonlinear dynamics of learning in deep linear neural networks - Saxe 2013 # torch.nn.init.orthogonal_(tensor, gain=1) nn.init.orthogonal_(w) # tensor([[ 0.5786, -0.5642, -0.5890], #         [-0.7517, -0.0886, -0.6536]])  # 11. 稀疏矩阵 - sparse matrix  # 非零元素采用正态分布 N(0, 0.01) 初始化. # From - Deep learning via Hessian-free optimization - Martens 2010 # torch.nn.init.sparse_(tensor, sparsity, std=0.01) nn.init.sparse_(w, sparsity=0.1) # tensor(1.00000e-03 * #        [[-0.3382,  1.9501, -1.7761], #         [ 0.0000,  0.0000,  0.0000]])

for m in model.modules():     if isinstance(m, (nn.Conv2d, nn.Linear)):         nn.init.xavier_uniform_(m.weight)

for m in self.modules():     if isinstance(m, nn.Conv2d):         nn.init.kaiming_normal_(m.weight, mode='fan_out', nonlinearity='relu')     elif isinstance(m, (nn.BatchNorm2d, nn.GroupNorm)):         nn.init.constant_(m.weight, 1)         nn.init.constant_(m.bias, 0)

a = tf.zeros([2,3], dtype = tf.float32)

b = tf.ones([3,4])

c = tf.constant(2, dtype=tf.int32, shape=[1,10])

d = tf.random_normal([1,10],mean = 20, stddev = 3)

bias = tf.Variable(tf.zeros([1,2]) + 0.01)

import tensorflow as tf   value = [0, 1, 2, 3, 4, 5, 6, 7] init = tf.constant_initializer(value)   with tf.Session() as sess:     x = tf.get_variable('x', shape=[8], initializer=init)   x.initializer.run()   print(x.eval（))   #output: #[ 0.  1.  2.  3.  4.  5.  6.  7.]

import tensorflow as tf   init_zeros=tf.zeros_initializer() init_ones = tf.ones_initializer     with tf.Session() as sess:     x = tf.get_variable('x', shape=[8], initializer=init_zeros)   y = tf.get_variable('y', shape=[8], initializer=init_ones)   x.initializer.run()   y.initializer.run()   print(x.eval（))   print(y.eval（))   #output: # [ 0.  0.  0.  0.  0.  0.  0.  0.] # [ 1.  1.  1.  1.  1.  1.  1.  1.]

import tensorflow as tf   init_random = tf.random_normal_initializer(mean=0.0, stddev=1.0, seed=None, dtype=tf.float32) init_truncated = tf.truncated_normal_initializer(mean=0.0, stddev=1.0, seed=None, dtype=tf.float32)     with tf.Session() as sess:     x = tf.get_variable('x', shape=[10], initializer=init_random)   y = tf.get_variable('y', shape=[10], initializer=init_truncated)   x.initializer.run()   y.initializer.run()     print(x.eval（))   print(y.eval（))     #output: # [-0.40236568 -0.35864913 -0.94253045 -0.40153521  0.1552504   1.16989613 #   0.43091929 -0.31410623  0.70080078 -0.9620409 ] # [ 0.18356581 -0.06860946 -0.55245203  1.08850253 -1.13627422 -0.1006074 #   0.65564936  0.03948414  0.86558545 -0.4964745 ]

import tensorflow as tf   init_uniform = tf.random_uniform_initializer(minval=0, maxval=10, seed=None, dtype=tf.float32)     with tf.Session() as sess:     x = tf.get_variable('x', shape=[10], initializer=init_uniform)   x.initializer.run()     print(x.eval（))   # output: # [ 6.93343639  9.41196823  5.54009819  1.38017178  1.78720832  5.38881063 #   3.39674473  8.12443542  0.62157512  8.36026382]

with tf.Session() as sess:     init_op = tf.global_variables_initializer()     sess.run(init_op)