Python base.NNBase类代码示例

OGeek|极客世界-中国程序员成长平台 › 门户 › 编程› Python›Python编程经验

原作者: [db:作者] 来自: [db:来源] 收藏邀请

本文整理汇总了Python中nn.base.NNBase类的典型用法代码示例。如果您正苦于以下问题：Python NNBase类的具体用法？Python NNBase怎么用？Python NNBase使用的例子？那么恭喜您, 这里精选的类代码示例或许可以为您提供帮助。

在下文中一共展示了NNBase类的20个代码示例，这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞，您的评价将有助于我们的系统推荐出更棒的Python代码示例。

示例1: init

    def __init__(self, L0, U0=None,
                 alpha=0.005, rseed=10, bptt=1):

        self.hdim = L0.shape[1] # word vector dimensions      |D|
        self.vdim = L0.shape[0] # vocab size                  |V|
        param_dims = dict(H = (self.hdim, self.hdim),
                          U = L0.shape)
        # note that only L gets sparse updates
        param_dims_sparse = dict(L = L0.shape)
        NNBase.__init__(self, param_dims, param_dims_sparse)

        #### YOUR CODE HERE ####


        # Initialize word vectors
        # either copy the passed L0 and U0 (and initialize in your notebook)
        # or initialize with gaussian noise here
        self.sparams.L = 0.1 * random.standard_normal(self.sparams.L.shape)
        # self.params.U
        self.params.U = 0.1 * random.standard_normal(self.params.U.shape)
        # Initialize H matrix, as with W and U in part 1
        # self.params.H = random_weight_matrix(*self.params.H.shape)
        self.params.H = random_weight_matrix(*self.params.H.shape)

        self.bptt = bptt
        self.alpha = alpha

开发者ID:icodingc，项目名称:CS224d，代码行数:26，代码来源:rnnlm.py

示例2: init

    def __init__(self, L0, U0=None,alpha=0.005, lreg = 0.00001, rseed=10, bptt=1):

        self.hdim = L0.shape[1] # word vector dimensions
        self.vdim = L0.shape[0] # vocab size
        param_dims = dict(H = (self.hdim, self.hdim), W = (self.hdim,self.hdim))
                          #,U = L0.shape)
        # note that only L gets sparse updates
        param_dims_sparse = dict(L = L0.shape)
        NNBase.__init__(self, param_dims, param_dims_sparse)

        self.alpha = alpha
        self.lreg = lreg
        #### YOUR CODE HERE ####
        
        # Initialize word vectors
        # either copy the passed L0 and U0 (and initialize in your notebook)
        # or initialize with gaussian noise here

        # Initialize H matrix, as with W and U in part 1
        self.bptt = bptt
        random.seed(rseed)
        self.params.H = random_weight_matrix(*self.params.H.shape)
        self.params.W = random_weight_matrix(*self.params.W.shape)
        #self.params.U = 0.1*np.random.randn(*L0.shape)
        self.sparams.L = L0.copy()

开发者ID:alphadl，项目名称:cs224d，代码行数:25，代码来源:rnnlmWithHierarchicalSoftmax.py

示例3: init

    def __init__(self, L0, Dy=N_ASPECTS*SENT_DIM, U0=None,
                 alpha=0.005, rseed=10, bptt=5):

        self.hdim = L0.shape[1] # word vector dimensions
        self.vdim = L0.shape[0] # vocab size
        self.ydim = Dy
        param_dims = dict(H = (self.hdim, self.hdim),
                          U = (self.ydim, self.hdim),
                          b1 = (self.hdim,),
                          b2 =(self.ydim,))
        # note that only L gets sparse updates
        param_dims_sparse = dict(L = L0.shape)
        NNBase.__init__(self, param_dims, param_dims_sparse)

        #### YOUR CODE HERE ####
        var = .1
        sigma = sqrt(var)
        from misc import random_weight_matrix
        random.seed(rseed)
        # Initialize word vectors
        self.bptt = bptt
        self.alpha = alpha
        self.params.H=random_weight_matrix(*self.params.H.shape)
        if U0 is not None:
            self.params.U= U0.copy()
        else:
            self.params.U= random_weight_matrix(*self.params.U.shape)
        self.sparams.L = L0.copy()
        self.params.b1 = zeros((self.hdim,))
        self.params.b2 = zeros((self.ydim,))

开发者ID:laisun，项目名称:EntitySentiment，代码行数:30，代码来源:rnn_simple.py

示例4: init

    def __init__(self, L0, U0=None,
                 alpha=0.005, rseed=10, bptt=1):

        self.hdim = L0.shape[1] # word vector dimensions
        self.vdim = L0.shape[0] # vocab size
        param_dims = dict(H = (self.hdim, self.hdim),
                          U = L0.shape)
        # note that only L gets sparse updates
        param_dims_sparse = dict(L = L0.shape)
        NNBase.__init__(self, param_dims, param_dims_sparse)

        #### YOUR CODE HERE ####


        # Initialize word vectors
        # either copy the passed L0 and U0 (and initialize in your notebook)
        # or initialize with gaussian noise here
        # Initialize H matrix, as with W and U in part 1
        self.sparams.L = L0.copy()
        if U0 is None:
            self.params.U = random.normal(0, 0.1, param_dims['U'])
        else:
            self.params.U = U0.copy()
        self.params.H = random_weight_matrix(*param_dims['H'])
        self.alpha = alpha
#        self.rseed = rseed
        self.bptt = bptt

开发者ID:ZhengXuxiao，项目名称:DLforNLP，代码行数:27，代码来源:rnnlm.py

示例5: init

    def __init__(self, L0, U0=None,
                 alpha=0.005, rseed=10, bptt=1):
        random.seed(rseed)
        self.hdim = L0.shape[1] # word vector dimensions
        self.vdim = L0.shape[0] # vocab size
        param_dims = dict(H = (self.hdim, self.hdim),
                          U = L0.shape)
        # note that only L gets sparse updates
        param_dims_sparse = dict(L = L0.shape)
        NNBase.__init__(self, param_dims, param_dims_sparse)

        #### YOUR CODE HERE ####
        self.sparams.L = L0.copy()
        self.params.H = random_weight_matrix(self.hdim, self.hdim)
        self.alpha = alpha
        self.bptt = bptt


        # Initialize word vectors
        # either copy the passed L0 and U0 (and initialize in your notebook)
        # or initialize with gaussian noise here
        if U0 is not None:
            self.params.U = U0.copy()
        else:
            sigma = 0.1
            mu = 0
            #self.params.U = random.normal(mu, sigma, (self.vdim, self.hdim))
            self.params.U = sigma*random.randn(self.vdim, self.hdim) + mu

开发者ID:janenie，项目名称:rnn_research，代码行数:28，代码来源:rnnlm.py

示例6: init

    def __init__(self, L0, D0, U0=None,
                 alpha=0.005, rseed=10, bptt=1):

        self.hdim = L0.shape[1] # word vector dimensions
        self.vdim = L0.shape[0] # vocab size
        self.ddim = D0.shape[0] # doc size
        param_dims = dict(H = (self.hdim, self.hdim),
                          U = L0.shape, G = L0.shape)
        # note that only L gets sparse updates
        param_dims_sparse = dict(L = L0.shape, D = D0.shape)
        NNBase.__init__(self, param_dims, param_dims_sparse)

        #### YOUR CODE HERE ####

        self.bptt = bptt
        self.alpha = alpha

        # Initialize word vectors
        self.sparams.L = L0.copy()
        self.sparams.D = D0.copy()

        self.params.U = random.randn(self.vdim, self.hdim)*0.1

        # Initialize H matrix, as with W and U in part 1
        self.params.H = random_weight_matrix(self.hdim, self.hdim)
        self.params.G = random_weight_matrix(self.vdim, self.hdim)

开发者ID:afgiel，项目名称:docvec，代码行数:26，代码来源:drnnlm.py

示例7: init

    def __init__(self, wv, dims=[100, 5],
                 reg=0.1, alpha=0.001,
                 rseed=10):
        """
        Set up classifier: parameters, hyperparameters
        """
        ##
        # Store hyperparameters
        self.lreg = reg # regularization
        self.alpha = alpha # default learning rate
        self.nclass = dims[1] # number of output classes

        ##
        # NNBase stores parameters in a special format
        # for efficiency reasons, and to allow the code
        # to automatically implement gradient checks
        # and training algorithms, independent of the
        # specific model architecture
        # To initialize, give shapes as if to np.array((m,n))
        param_dims = dict(W = (dims[1], dims[0]), # 5x100 matrix
                          b = (dims[1])) # column vector
        # These parameters have sparse gradients,
        # which is *much* more efficient if only a row
        # at a time gets updated (e.g. word representations)
        param_dims_sparse = dict(L=wv.shape)
        NNBase.__init__(self, param_dims, param_dims_sparse)

        ##
        # Now we can access the parameters using
        # self.params.<name> for normal parameters
        # self.sparams.<name> for params with sparse gradients
        # and get access to normal NumPy arrays
        self.sparams.L = wv.copy() # store own representations
        self.params.W = random_weight_matrix(*self.params.W.shape)

开发者ID:kornev，项目名称:cs224d-hw2，代码行数:34，代码来源:softmax_example.py

示例8: init

    def __init__(self, L0, U0=None,
                 alpha=0.005, rseed=10, bptt=1):

        self.hdim = L0.shape[1] # word vector dimensions
        self.vdim = L0.shape[0] # vocab size
        param_dims = dict(H = (self.hdim, self.hdim),
                          U = (L0.shape if U0 is None else U0.shape))
        # note that only L gets sparse updates
        param_dims_sparse = dict(L = L0.shape)
        NNBase.__init__(self, param_dims, param_dims_sparse)

        #### YOUR CODE HERE ####
        self.alpha = alpha

        self.bptt = bptt

        # Initialize word vectors
        # either copy the passed L0 and U0 (and initialize in your notebook)
        # or initialize with gaussian noise here
        random.seed(rseed)
        
        sigma = sqrt(0.1)
        self.sparams.L = random.normal(0, sigma, L0.shape)
        self.params.U = random.normal(0, sigma, param_dims['U'])
        
        # Initialize H matrix, as with W and U in part 1
        self.params.H = random_weight_matrix(*param_dims['H'])

        self.lamb = .0001 # regularization

开发者ID:arthur-tsang，项目名称:EqnMaster，代码行数:29，代码来源:rnnlm.py

示例9: init

    def __init__(self, L0, U0=None,
                 alpha=0.005, rseed=10):

        self.hdim = L0.shape[1] # word vector dimensions
        self.vdim = L0.shape[0] # vocab size
        param_dims = dict(LH = (self.hdim, self.hdim),
                          RH = (self.hdim, self.hdim),
                          U = (self.vdim, self.hdim * 2))
        # note that only L gets sparse updates
        param_dims_sparse = dict(LL = L0.shape, RL = L0.shape)
        NNBase.__init__(self, param_dims, param_dims_sparse)

        #### YOUR CODE HERE ####
        np.random.seed(rseed) # be sure to seed this for repeatability!
        self.alpha = alpha

        # Initialize word vectors
        # either copy the passed L0 and U0 (and initialize in your notebook)
        # or initialize with gaussian noise here
        #self.sparams.LL = np.random.randn(*L0.shape) * np.sqrt(0.1)
        #self.sparams.RL = np.random.randn(*L0.shape) * np.sqrt(0.1)
        self.sparams.LL = L0
        self.sparams.RL = L0
        self.params.U = np.random.randn(self.vdim, self.hdim*2) * np.sqrt(0.1)

        # Initialize H matrix, as with W and U in part 1
        self.params.LH = random_weight_matrix(self.hdim, self.hdim)
        self.params.RH = random_weight_matrix(self.hdim, self.hdim)

开发者ID:nishithbsk，项目名称:SentenceGeneration，代码行数:28，代码来源:brnnlm.py

示例10: init

    def __init__(self, L0, U0=None,
                 alpha=0.005, rseed=10, bptt=1):

        self.hdim = L0.shape[1] # word vector dimensions
        self.vdim = L0.shape[0] # vocab size
        param_dims = dict(H = (self.hdim, self.hdim),
                          U = L0.shape)
        # note that only L gets sparse updates
        param_dims_sparse = dict(L = L0.shape)
        NNBase.__init__(self, param_dims, param_dims_sparse)

开发者ID:YunshengWei，项目名称:Deep-Learning-for-Natural-Language-Processing，代码行数:10，代码来源:rnnlm.py

示例11: grad_check

    def grad_check(self, x, y, outfd=sys.stderr, **kwargs):
        """
        Wrapper for gradient check on RNNs;
        ensures that backprop-through-time is run to completion,
        computing the full gradient for the loss as summed over
        the input sequence and predictions.

        Do not modify this function!
        """
        NNBase.grad_check(self, x, y, outfd=outfd, **kwargs)

开发者ID:nishithbsk，项目名称:SentenceGeneration，代码行数:10，代码来源:brnnlm.py

示例12: init

    def __init__(self, wv, windowsize=3,
                 dims=[None, 100, 5],
                 reg=0.001, alpha=0.01, rseed=10):
        """
        Initialize classifier model.

        Arguments:
        wv : initial word vectors (array |V| x n)
            note that this is the transpose of the n x |V| matrix L
            described in the handout; you'll want to keep it in
            this |V| x n form for efficiency reasons, since numpy
            stores matrix rows continguously.
        windowsize : int, size of context window
        dims : dimensions of [input, hidden, output]
            input dimension can be computed from wv.shape
        reg : regularization strength (lambda)
        alpha : default learning rate
        rseed : random initialization seed
        """

        # Set regularization
        self.lreg = float(reg)
        self.alpha = alpha # default training rate

        dims[0] = windowsize * wv.shape[1] # input dimension
        param_dims = dict(W=(dims[1], dims[0]),
                          b1=(dims[1],),
                          U=(dims[2], dims[1]),
                          b2=(dims[2],),
                          )
        param_dims_sparse = dict(L=wv.shape)

        # initialize parameters: don't change this line
        NNBase.__init__(self, param_dims, param_dims_sparse)

        random.seed(rseed) # be sure to seed this for repeatability!
        #### YOUR CODE HERE ####

        # any other initialization you need
        #self.sparams， self.grads, self.param, self.sgrads
        #where are they defined?
        #为什么可以直接可以使用？
        self.sparams.L = wv.copy()
        #self.sparam.L = wv.copy()
        self.params.U = random_weight_matrix(*param_dims["U"])
        #self.param.U = random_weight_matrix(param_dims["U"])
        self.params.W = random_weight_matrix(*param_dims["W"])
        #self.param.b1 = zeros(param_dims["b1"])
        #self.param.b2 = zeros(param_dims["b2"])
        self.windowSize = windowsize
        self.wordVecLen = wv.shape[1]
        self.wordVecNum = wv.shape[0]

开发者ID:NeighborhoodWang，项目名称:CS224D-problem-set2，代码行数:52，代码来源:nerwindow.py

示例13: init

    def __init__(self, wv, windowsize=3,
                 dims=[None, 100, 5],
                 reg=0.001, alpha=0.01, rseed=10):
        """
        Initialize classifier model.

        Arguments:
        wv : initial word vectors (array |V| x n)
            note that this is the transpose of the n x |V| matrix L
            described in the handout; you'll want to keep it in
            this |V| x n form for efficiency reasons, since numpy
            stores matrix rows continguously.
        windowsize : int, size of context window
        dims : dimensions of [input, hidden, output]
            input dimension can be computed from wv.shape
        reg : regularization strength (lambda)
        alpha : default learning rate
        rseed : random initialization seed
        """

        # Set regularization
        self.lreg = float(reg)
        self.alpha = alpha # default training rate

        dims[0] = windowsize * wv.shape[1]         # input dimension
        param_dims = dict(W1=(dims[1], dims[0]),   # 100 x 150
                          b2=(dims[1],),           # 100 x 1
                          W2=(dims[2], dims[1]),   # 5 X 100
                          b3=(dims[2],),           # 5 x 1
                          )

        param_dims_sparse = dict(L=wv.shape)       # |V| x 50

        # initialize parameters: don't change this line
        NNBase.__init__(self, param_dims, param_dims_sparse)

        random.seed(rseed) # be sure to seed this for repeatability!
        #### YOUR CODE HERE ####
        self.sparams.L = wv.copy();

        self.params.W1 = random_weight_matrix(param_dims['W1'][0], param_dims['W1'][1])

        self.params.b2 = append([], random_weight_matrix(param_dims['b2'][0], 1))
        self.params.b3 = append([], random_weight_matrix(param_dims['b3'][0], 1))
        self.params.W2 = random_weight_matrix(param_dims['W2'][0], param_dims['W2'][1])
        self.n = wv.shape[1]

        # informational
        self.windowsize = windowsize
        self.hidden_units = dims[1]

开发者ID:kireet，项目名称:cs224d，代码行数:50，代码来源:nerwindow.py

示例14: grad_check

 def grad_check(self, x, y, outfd=sys.stderr, **kwargs):
     """
     Wrapper for gradient check on RNNs;
     ensures that backprop-through-time is run to completion,
     computing the full gradient for the loss as summed over
     the input sequence and predictions.
     Do not modify this function!
     """
     bptt_old = self.bptt
     self.bptt = len(y)
     print >> outfd, "NOTE: temporarily setting self.bptt = len(y) = %d to compute true gradient." % self.bptt
     NNBase.grad_check(self, x, y, outfd=outfd, **kwargs)
     self.bptt = bptt_old
     print >> outfd, "Reset self.bptt = %d" % self.bptt

开发者ID:ryu577，项目名称:base，代码行数:14，代码来源:msushkov_rnnlm.py

示例15: init

    def __init__(self, wv, windowsize=3,
                 dims=[None, 100, 5],
                 reg=0.001, alpha=0.01, rseed=10):
        """
        Initialize classifier model.

        Arguments:
        wv : initial word vectors (array |V| x n)
            note that this is the transpose of the n x |V| matrix L
            described in the handout; you'll want to keep it in
            this |V| x n form for efficiency reasons, since numpy
            stores matrix rows continguously.
        windowsize : int, size of context window
        dims : dimensions of [input, hidden, output]
            input dimension can be computed from wv.shape
        reg : regularization strength (lambda)
        alpha : default learning rate
        rseed : random initialization seed
        """

        # Set regularization
        self.lreg = float(reg)
        self.alpha = alpha # default training rate

        #wv.shape: (100232,50)
        dims[0] = windowsize * wv.shape[1] # input dimension 3*50=150
        param_dims = dict(W=(dims[1], dims[0]),# W(100,150)
                          b1=(dims[1],),#b(100)
                          U=(dims[2], dims[1]),#U(5,100)
                          b2=(dims[2],),#(5,)
                          )
        param_dims_sparse = dict(L=wv.shape) #L(100232,50)

        # initialize parameters: don't change this line
        NNBase.__init__(self, param_dims, param_dims_sparse)

        random.seed(rseed) # be sure to seed this for repeatability!
        #### YOUR CODE HERE ####

        # any other initialization you need
        self.sparams.L = wv.copy() # store own representations,100232,50 matrix
        self.params.W = random_weight_matrix(*self.params.W.shape)
        self.params.U = random_weight_matrix(*self.params.U.shape)

        self.window_size = windowsize#3
        self.word_vec_size = wv.shape[1]#50

开发者ID:Tang7，项目名称:rnn224，代码行数:46，代码来源:nerwindow.py

示例16: init

    def __init__(self, L0, U0=None,
                 alpha=0.005, rseed=10, bptt=1):

        self.hdim = L0.shape[1] # word vector dimensions
        self.vdim = L0.shape[0] # vocab size
        param_dims = dict(H = (self.hdim, self.hdim),
                          U = L0.shape)
        # note that only L gets sparse updates
        param_dims_sparse = dict(L = L0.shape)
        NNBase.__init__(self, param_dims, param_dims_sparse)

        #### YOUR CODE HERE ####
        #random.seed(rseed)
        self.params.U=0.1*random.randn(*self.params.U.shape)
        self.sparams.L=0.1*random.randn(*self.sparams.L.shape)
        self.params.H=random_weight_matrix(*self.params.H.shape)
        self.bptt=bptt
        self.alpha=alpha

开发者ID:nflsalex，项目名称:CS224D，代码行数:18，代码来源:rnnlm.py

示例17: init

    def __init__(self, wv, windowsize=3,
                 dims=[None, 100, 5],
                 reg=0.001, alpha=0.01, rseed=10):
        """
        Initialize classifier model.

        Arguments:
        wv : initial word vectors (array |V| x n) n=50
            note that this is the transpose of the n x |V| matrix L
            described in the handout; you'll want to keep it in
            this |V| x n form for efficiency reasons, since numpy
            stores matrix rows continguously.
        windowsize : int, size of context window
        dims : dimensions of [input, hidden, output]
            input dimension can be computed from wv.shape
        reg : regularization strength (lambda)
        alpha : default learning rate
        rseed : random initialization seed
        """

        # Set regularization
        self.lreg = float(reg)
        self.alpha = alpha # default training rate
        self.nclass = dims[2]
        
        # input dimension, wv.shape is the dimension of each word vector representation
        dims[0] = windowsize * wv.shape[1] # 50*3
        param_dims = dict(W=(dims[1], dims[0]), # 100*150
                          b1=(dims[1]),
                          U=(dims[2], dims[1]),
                          b2=(dims[2]))
        param_dims_sparse = dict(L=wv.shape) # L.shape = (|V|*50)

        # initialize parameters: don't change this line
        NNBase.__init__(self, param_dims, param_dims_sparse)

        random.seed(rseed) # be sure to seed this for repeatability!

        self.params.W = random_weight_matrix(*self.params.W.shape) # 100*150
        self.params.U = random_weight_matrix(*self.params.U.shape) # 5*100
        #self.params.b1 = zeros((dims[1],))  # 100*1
        #self.params.b2 = zeros((self.nclass,)) # 5*1
        
        self.sparams.L = wv.copy()

开发者ID:WenyingLiu，项目名称:cs224d，代码行数:44，代码来源:nerwindow.py

示例18: init

    def __init__(self, wv, windowsize=3,
                 dims=[None, 100, 5],
                 reg=0.001, alpha=0.01, rseed=10):
        """
        Initialize classifier model.

        Arguments:
        wv : initial word vectors (array |V| x n) => n is the input dimension, length of input word-vector
            note that this is the transpose of the n x |V| matrix L
            described in the handout; you'll want to keep it in
            this |V| x n form for efficiency reasons, since numpy
            stores matrix rows continguously.
        windowsize : int, size of context window
        dims : dimensions of [input, hidden, output]
            input dimension can be computed from wv.shape
        reg : regularization strength (lambda)
        alpha : default learning rate
        rseed : random initialization seed
        """

        # Set regularization
        self.lreg = float(reg)
        self.alpha = alpha # default training rate

        dims[0] = windowsize * wv.shape[1] # input dimension
        param_dims = dict(W=(dims[1], dims[0]),
                          b1=(dims[1],),
                          U=(dims[2], dims[1]),
                          b2=(dims[2],),
                          )
        param_dims_sparse = dict(L=wv.shape)

        # initialize parameters
        NNBase.__init__(self, param_dims, param_dims_sparse)

        random.seed(rseed) # be sure to seed, re-show the result

        # random initialization
        self.sparams.L = wv.copy() # store own representations
        self.params.U = random_weight_matrix(*self.params.U.shape)
        self.params.W = random_weight_matrix(*self.params.W.shape)

        self.window_size = windowsize
        self.word_vec_size = wv.shape[1]

开发者ID:qcs4tracy，项目名称:NER-Project，代码行数:44，代码来源:nerwindow.py

示例19: init

    def __init__(self, L0, U0=None,
                 alpha=0.005, lreg = 0.00001, rseed=10, bptt=1,loadData=False):
        
        self.hdim = L0.shape[1] # word vector dimensions
        self.vdim = L0.shape[0] # vocab size
        param_dims = dict(H = (self.hdim, self.hdim), W = (self.hdim,self.hdim),
                          U = L0.shape)
        # note that only L gets sparse updates
        param_dims_sparse = dict(L = L0.shape)
        NNBase.__init__(self, param_dims, param_dims_sparse)

        self.alpha = alpha
        self.lreg = lreg
        #### YOUR CODE HERE ####
        
        # Initialize word vectors
        # either copy the passed L0 and U0 (and initialize in your notebook)
        # or initialize with gaussian noise here

        # Initialize H matrix, as with W and U in part 1
        self.bptt = bptt
        if loadData == True:
            with open("rnnlmWithW_hdim_150_bptt_4.H.npy") as fid:
                H = pickle.load(fid)
                self.params.H = H
            with open("rnnlmWithW_hdim_150_bptt_4.W.npy") as fid:
                W = pickle.load(fid)
                self.params.W = W
            with open("rnnlmWithW_hdim_150_bptt_4.U.npy") as fid:
                U = pickle.load(fid)
                self.params.U = U
            with open("rnnlmWithW_hdim_150_bptt_4.L.npy") as fid:
                L = pickle.load(fid)
                self.sparams.L = L
            return

        random.seed(rseed)
        self.params.H = random_weight_matrix(*self.params.H.shape)
        self.params.W = random_weight_matrix(*self.params.W.shape)
        self.params.U = 0.1*np.random.randn(*L0.shape)
        self.sparams.L = L0.copy()

开发者ID:alphadl，项目名称:cs224d，代码行数:41，代码来源:rnnlm.py

示例20: init

    def __init__(self, L0, U0=None,
                 alpha=0.005, rseed=10, bptt=1):

        self.vdim = L0.shape[0] # vocab size
        self.hdim = L0.shape[1] # word vector dimensions
        param_dims = dict(H = (self.hdim, self.hdim),
                          U = L0.shape)
        # note that only L gets sparse updates
        param_dims_sparse = dict(L = L0.shape)
        NNBase.__init__(self, param_dims, param_dims_sparse)

        #### YOUR CODE HERE ####

        # hyperparameters
        self.bptt = bptt
        self.alpha = alpha

        # weights
        self.sparams.L = random.normal(scale=sqrt(0.1), size=(self.vdim, self.hdim))
        self.sparams.U = random.normal(scale=sqrt(0.1), size=(self.vdim, self.hdim))
        self.params.H = random_weight_matrix(self.hdim, self.hdim)

开发者ID:hendrycks，项目名称:ML-Coursework，代码行数:21，代码来源:rnnlm.py

注：本文中的nn.base.NNBase类示例由纯净天空整理自Github/MSDocs等源码及文档管理平台，相关代码片段筛选自各路编程大神贡献的开源项目，源码版权归原作者所有，传播和使用请参考对应项目的License；未经允许，请勿转载。

鲜花

握手

雷人

路过

鸡蛋

该文章已有0人参与评论

请发表评论

全部评论

专题导读

More+

10-27 六六分期app的软件客服如何联系？(六六分期

11-06 可心卡盟:win10系统火狐flash插件崩溃怎么

11-06 亲亲特价:怎么删除回收站图标

11-06 济南大学虚拟社区:鲁大师节能降温的具体办

11-06 xlueops.exe:无线网络安装向导

11-06 女斗合众国:win7系统cf与主机连接不稳定怎

11-06 0xc000022-[cf烟雾头]cf怎么调烟雾头

11-06 qizideyouhuo:应用程序无法正常启动0xc0000

11-06 ipz-185:win7系统vcf文件怎么打开

11-06 傻哥蹦迪:win10系统s4怎么打开usb调试

11-06 八神浩树gtaste:回收站清空了怎么恢复

11-06 妖尾之黑色守护:win10系统电脑没有1440x900

11-06 校园至尊魔王小说:win7系统浏览网页时字体

11-06 女斗合众国:win10系统访问共享文件夹提示请

11-06 tokyo hot n0654:恢复win7系统默认字体一招

11-06 雨酷仙境:设置win7系统转移临时文件夹腾出

11-06 阿穆纳伊之杖:win7系统开始菜单在右边还原

11-06 tunespotting:win10系统火狐flash插件总是

11-06 甘尔葛分析师：计谋网站seo关键词暴涨有什

11-06 蔡贵霖: 计谋网站seo关键词暴涨有什么秘密

11-06 博益网首页:ao3网页版进入不了解决方法

11-06 漏斗子专栏: 网站数据分析小白易懂精华篇

11-06 见证双虹怎么做:win7系统开启telnet命令的

11-06 颾狐蝶蜋:系统资源不足无法完成请求的服务

11-06 国光中学校歌:提交网站到alexa查询详细步骤

11-06 西安有情天:静态网页和动态网页的区别

11-06 红木雅尚斋:外部链接构造对网站的好处

11-06 前官礼遇：防止域名劫持–增强域安全性的10

11-06 密传二转答案: 中文分词算法有哪些

11-06 金泉家园邮编:百度快照劫持的表现及应对方

Python math.make_onehot函数代码示例发布时间：2022-05-27

Python nn.searchnet函数代码示例发布时间：2022-05-27

Python util.grid_equal函数代码示例

1 Python 入门教程

Python入门教程 Python 是一种解释型、面向对象、动态数据类型的高级程序设计语言。 P

阅读：13806|2022-01-22

2 Python wikiutil.getFrontPage函数代码示例

Python wikiutil.getFrontPage函数代码示例

阅读：10193|2022-05-24

3 Python 简介

Python 简介 Python 是一个高层次的结合了解释性、编译性、互动性和面向对象的脚本

阅读：4090|2022-01-22

4 Python tests.group函数代码示例

Python tests.group函数代码示例

阅读：4043|2022-05-27

5 Python util.check_if_user_has_permission

Python util.check_if_user_has_permission函数代码示例

阅读：3845|2022-05-27

6 Python 操练实例98

Python 练习实例98 Python 100例题目：从键盘输入一个字符串，将小写字母全部转换成大

阅读：3510|2022-01-22

7 Python 环境搭建

Python 环境搭建本章节我们将向大家介绍如何在本地搭建 Python 开发环境。 Py

阅读：3030|2022-01-22

8 Python output.darkgreen函数代码示例

Python output.darkgreen函数代码示例

阅读：2653|2022-05-25

9 Python 基础语法

Python 基础语法 Python 语言与 Perl，C 和 Java 等语言有许多相似之处。但是，也

阅读：2649|2022-01-22

10 Python 中文编码

Python 中文编码前面章节中我们已经学会了如何用 Python 输出 Hello, World!，英文没

阅读：2302|2022-01-22

客服电话

电子邮件

Python base.NNBase类代码示例

示例1: __init__

示例2: __init__

示例3: __init__

示例4: __init__

示例5: __init__

示例6: __init__

示例7: __init__

示例8: __init__

示例9: __init__

示例10: __init__

示例11: grad_check

示例12: __init__

示例13: __init__

示例14: grad_check

示例15: __init__

示例16: __init__

示例17: __init__

示例18: __init__

示例19: __init__

示例20: __init__

请发表评论

全部评论

上一篇：

下一篇：

Python util.grid_equal函数代码示例

Python util.get_worker_name函数代码示例

Python util.get_webmention_target函数代

Python util.get_uuid函数代码示例

Python util.get_type_by_name函数代码示例

Python util.grid_equal函数代码示例

Python util.get_worker_name函数代码示例

Python util.get_webmention_target函数代

Python util.get_uuid函数代码示例

Python util.get_type_by_name函数代码示例

Python util.get_stdout函数代码示例

关于我们

产品与服务

解决方案

139-2527-9053

示例1: init

示例2: init

示例3: init

示例4: init

示例5: init

示例6: init

示例7: init

示例8: init

示例9: init

示例10: init

示例12: init

示例13: init

示例15: init

示例16: init

示例17: init

示例18: init

示例19: init

示例20: init