<codeclass="descname">states</code><aclass="headerlink"href="#paddle.v2.fluid.evaluator.Evaluator.states"title="Permalink to this definition">¶</a></dt>
<dd><p><em>list</em>– The list of state variables. states will be reset to zero
<codeclass="descname">metrics</code><aclass="headerlink"href="#paddle.v2.fluid.evaluator.Evaluator.metrics"title="Permalink to this definition">¶</a></dt>
<dd><p><em>list</em>– The list of metrics variables. They will be calculate
<li><strong>input</strong> (<em>Variable</em>) – The input variable which is a Tensor or LoDTensor.</li>
<li><strong>dim</strong> (<em>int</em>) – The dimension along which to split. If <spanclass="math">\(dim < 0\)</span>, the
dimension to split along is <spanclass="math">\(rank(input) + dim\)</span>.</li>
</ul>
</td>
</tr>
<trclass="field-even field"><thclass="field-name">Returns:</th><tdclass="field-body"><pclass="first">The Tensor variable with half the size of input.</p>
<li><strong>query</strong> (<em>Variable</em>) – The input variable which is a Tensor or LoDTensor.</li>
<li><strong>key</strong> (<em>Variable</em>) – The input variable which is a Tensor or LoDTensor.</li>
<li><strong>value</strong> (<em>Variable</em>) – The input variable which is a Tensor or LoDTensor.</li>
</ul>
</td>
</tr>
<trclass="field-even field"><thclass="field-name">Returns:</th><tdclass="field-body"><pclass="first">The Tensor variables representing the output and attention scores.</p>
<divclass="highlight-python"><divclass="highlight"><pre><span></span><spanclass="c1"># Suppose q, k, v are tensor variables with the following shape:</span>
<li><strong>loss</strong>– the target that this optimization is for.</li>
<li><strong>parameters_and_grads</strong>– a list of (variable, gradient) pair to update.</li>
</ul>
</td>
</tr>
<trclass="field-even field"><thclass="field-name">Returns:</th><tdclass="field-body"><pclass="first">a list of operators that will complete one step of
optimization. This will include parameter update ops, global step
update ops and any other custom ops required by subclasses to manage
<spanid="l1decayregularizer"></span><h2>L1DecayRegularizer<aclass="headerlink"href="#module-paddle.v2.fluid.regularizer"title="Permalink to this headline">¶</a></h2>
<emclass="property">class </em><codeclass="descclassname">paddle.v2.fluid.regularizer.</code><codeclass="descname">L1DecayRegularizer</code><spanclass="sig-paren">(</span><em>regularization_coeff=0.0</em><spanclass="sig-paren">)</span><aclass="headerlink"href="#paddle.v2.fluid.regularizer.L1DecayRegularizer"title="Permalink to this definition">¶</a></dt>
<dd><p>Implements the L1 Weight Decay Regularization</p>
</dd></dl>
<divclass="section"id="l1decayregularizer">
<h2>L1DecayRegularizer<aclass="headerlink"href="#l1decayregularizer"title="Permalink to this headline">¶</a></h2>
<li><ahref="api/v2/fluid/regularizer.html#paddle.v2.fluid.regularizer.L1DecayRegularizer">L1DecayRegularizer (class in paddle.v2.fluid.regularizer)</a>
</li>
<li><ahref="api/v2/data/image.html#paddle.v2.image.left_right_flip">left_right_flip() (in module paddle.v2.image)</a>
</li>
</ul></td>
<tdstyle="width: 33%; vertical-align: top;"><ul>
<li><ahref="api/v2/data/image.html#paddle.v2.image.load_and_transform">load_and_transform() (in module paddle.v2.image)</a>
</li>
</ul></td>
<tdstyle="width: 33%; vertical-align: top;"><ul>
<li><ahref="api/v2/data/image.html#paddle.v2.image.load_image">load_image() (in module paddle.v2.image)</a>
</li>
<li><ahref="api/v2/data/image.html#paddle.v2.image.load_image_bytes">load_image_bytes() (in module paddle.v2.image)</a>
<li><ahref="api/v1/data_provider/pydataprovider2_en.html#paddle.trainer.PyDataProvider2.provider">provider() (in module paddle.trainer.PyDataProvider2)</a>
"comment":"\nLog Activation Operator.\n\n$out = \\ln(x)$\n\nNatural logarithm of x.\n\n",
"inputs":[
{
"name":"X",
"comment":"Input of Log operator",
"duplicable":0,
"intermediate":0
}],
"outputs":[
{
"name":"Out",
"comment":"Output of Log operator",
"duplicable":0,
"intermediate":0
}],
"attrs":[]
},{
"type":"softmax",
"comment":"\nSoftmax Operator.\n\nThe input of the softmax operator is a 2-D tensor with shape N x K (N is the\nbatch_size, K is the dimension of input feature). The output tensor has the\nsame shape as the input tensor.\n\nFor each row of the input tensor, the softmax operator squashes the\nK-dimensional vector of arbitrary real values to a K-dimensional vector of real\nvalues in the range [0, 1] that add up to 1.\nIt computes the exponential of the given dimension and the sum of exponential\nvalues of all the other dimensions in the K-dimensional vector input.\nThen the ratio of the exponential of the given dimension and the sum of\nexponential values of all the other dimensions is the output of the softmax\noperator.\n\nFor each row $i$ and each column $j$ in Input(X), we have:\n $$Out[i, j] = \\frac{\\exp(X[i, j])}{\\sum_j(exp(X[i, j])}$$\n\n",
"comment":"\nRankLoss Operator.\n\nRankLoss operator for RankNet\n(http://icml.cc/2015/wp-content/uploads/2015/06/icml_ranking.pdf). \nRankNet is a pairwise ranking model with\none training sample consisting of a pair of doc A and B, and the label P\nindicating that A is ranked higher than B or not:\n\nP = {0, 1} or {0, 0.5, 1}, where 0.5 means no information about the rank of\nthe input pair.\n\nThe RankLoss operator takes three inputs: Left (o_i), Right (o_j) and Label\n(P_{i,j}), which represent the output score of RankNet for the two docs and \nthe label respectively, and yields the rank loss C_{i,j} using the following \nequation:\n\n$$\n C_{i,j} = -\\tilde{P_{ij}} * o_{i,j} + \\log(1 + e^{o_{i,j}}) \\\\\n o_{i,j} = o_i - o_j \\\\\n\\tilde{P_{i,j}} = \\left \\{0, 0.5, 1 \\right \\} \\ or \\\\left \\{0, 1 \\right \\}\n$$\n\nThe operator can take batch inputs with size batch_size (batch_size >= 1).\n\n",
"inputs":[
{
"name":"Label",
"comment":"(2-D Tensor with shape [batch_size x 1]) The label indicating A ranked higher than B or not.",
"duplicable":0,
"intermediate":0
},{
"name":"Left",
"comment":"(2-D Tensor with shape [batch_size x 1]) The output of RankNet for doc A.",
"duplicable":0,
"intermediate":0
},{
"name":"Right",
"comment":"(2-D Tensor with shape [batch_size x 1]) The output of RankNet for doc B.",
"duplicable":0,
"intermediate":0
}],
"outputs":[
{
"name":"Out",
"comment":"(2-D Tensor with shape [batch_size x 1]) The output loss of RankLoss operator.",
"comment":"(int, default -1). The start dimension index for broadcasting Y onto X.",
"generated":0
}]
},{
"type":"sequence_pool",
"comment":"\nSequence Pool Operator.\n\nThe SequencePoolOp pools features of all time-steps of each instance.\nIt supports six pooling types:\n1. AVERAGE: $$Out[i] = \\frac{\\sum_i X_i}{N}$$\n2. SUM: $$Out[i] = \\sum_jX_{ij}$$\n3. SQRT: $$Out[i] = \\frac{\\sum_jX_{ij}}{\\sqrt{len(X_i)}}$$\n4. LAST: Out[i] = last instance in i-th sequence X[i]\n5. FIRST: Out[i] = first instance in i-th sequence X[i]\n6. MAX: $$Out[i] = max(X_i)$$\n\nThe following example explains how this works:\nFor a mini-batch of 3 variable-length sentences,\ncontaining 2, 3, and 2 time-steps:\n\nAssume X is a [7,M,N] LoDTensor, and X->lod()[0] = [0, 2, 5, 7], 7=2+3+2.\nBesides, for the sake of simplicity, we assume M=1 and N=1,\nand the value of X = [[1, 3], [2, 4, 6], [5, 1]].\n\nThus, Out is a [3,1,1] Tensor without LoD infomation.\nAnd for different pooltype, the value of Out is as follows:\n\n- AVERAGE: [2, 4, 3], where 2=(1+3)/2, 4=(2+4+6)/3, 3=(5+1)/2\n- SUM: [4, 12, 6], where 4=1+3, 12=2+4+6, 6=5+1\n- SQRT: [2.82, 6.93, 4.24], where 2.82=(1+3)/sqrt(2),\n 6.93=(2+4+6)/sqrt(3), 4.24=(5+1)/sqrt(2)\n- MAX: [3, 6, 5], where 3=max(1,3), 6=max(2,4,6), 5=max(5,1)\n- LAST: [3, 6, 1], where 3=last(1,3), 6=last(2,4,6), 1=last(5,1)\n- FIRST: [1, 2, 5], where 1=first(1,3), 2=first(2,4,6), 5=first(5,1)\n\n ",
...
...
@@ -3197,57 +3213,6 @@
"comment":"Hyper parameter in huber loss.",
"generated":0
}]
},{
"type":"rank_loss",
"comment":"\nRankLoss Operator.\n\nRankLoss operator for RankNet\n(http://icml.cc/2015/wp-content/uploads/2015/06/icml_ranking.pdf). \nRankNet is a pairwise ranking model with\none training sample consisting of a pair of doc A and B, and the label P\nindicating that A is ranked higher than B or not:\n\nP = {0, 1} or {0, 0.5, 1}, where 0.5 means no information about the rank of\nthe input pair.\n\nThe RankLoss operator takes three inputs: Left (o_i), Right (o_j) and Label\n(P_{i,j}), which represent the output score of RankNet for the two docs and \nthe label respectively, and yields the rank loss C_{i,j} using the following \nequation:\n\n$$\n C_{i,j} = -\\tilde{P_{ij}} * o_{i,j} + \\log(1 + e^{o_{i,j}}) \\\\\n o_{i,j} = o_i - o_j \\\\\n\\tilde{P_{i,j}} = \\left \\{0, 0.5, 1 \\right \\} \\ or \\\\left \\{0, 1 \\right \\}\n$$\n\nThe operator can take batch inputs with size batch_size (batch_size >= 1).\n\n",
"inputs":[
{
"name":"Label",
"comment":"(2-D Tensor with shape [batch_size x 1]) The label indicating A ranked higher than B or not.",
"duplicable":0,
"intermediate":0
},{
"name":"Left",
"comment":"(2-D Tensor with shape [batch_size x 1]) The output of RankNet for doc A.",
"duplicable":0,
"intermediate":0
},{
"name":"Right",
"comment":"(2-D Tensor with shape [batch_size x 1]) The output of RankNet for doc B.",
"duplicable":0,
"intermediate":0
}],
"outputs":[
{
"name":"Out",
"comment":"(2-D Tensor with shape [batch_size x 1]) The output loss of RankLoss operator.",
"duplicable":0,
"intermediate":0
}],
"attrs":[]
},{
"type":"greater_than",
"comment":"greater_than Operator\n\nIt operates element-wise on X and Y, and returns the Out. Each of them is a\nN-dim tensor. X and Y could be any type. The each element of the Out tensor is\ncalculated by Out = X > Y\n",
"inputs":[
{
"name":"X",
"comment":"(LoDTensor) the left hand operand of greater_than operator",
"duplicable":0,
"intermediate":0
},{
"name":"Y",
"comment":"(LoDTensor) the right hand operand of greater_than operator",
"duplicable":0,
"intermediate":0
}],
"outputs":[
{
"name":"Out",
"comment":"(LoDTensor) n-dim bool tensor. Each element is Out = X > Y",
"duplicable":0,
"intermediate":0
}],
"attrs":[]
},{
"type":"sequence_softmax",
"comment":"\nSequence Softmax Operator.\n\nSequenceSoftmaxOp computes the softmax activation among all time-steps for each\nsequence. The dimension of each time-step should be 1. Thus, the shape of\ninput Tensor can be either [N, 1] or [N], where N is the sum of the length\nof all sequences.\n\nThe algorithm works as follows:\n\n for i-th sequence in a mini-batch:\n\n$$\nOut(X[lod[i]:lod[i+1]], :) = \\\n\\frac{\\exp(X[lod[i]:lod[i+1], :])} \\\n{\\sum(\\exp(X[lod[i]:lod[i+1], :]))}\n$$\n\nFor example, for a mini-batch of 3 sequences with variable-length,\neach containing 2, 3, 2 time-steps, the lod of which is [0, 2, 5, 7],\nthen softmax will be computed among X[0:2, :], X[2:5, :], X[5:7, :]\nand N turns out to be 7.\n\n",
...
...
@@ -4515,29 +4480,6 @@
"comment":"(int) the specific lod level to split.",
"generated":0
}]
},{
"type":"greater_equal",
"comment":"greater_equal Operator\n\nIt operates element-wise on X and Y, and returns the Out. Each of them is a\nN-dim tensor. X and Y could be any type. The each element of the Out tensor is\ncalculated by Out = X >= Y\n",
"inputs":[
{
"name":"X",
"comment":"(LoDTensor) the left hand operand of greater_equal operator",
"duplicable":0,
"intermediate":0
},{
"name":"Y",
"comment":"(LoDTensor) the right hand operand of greater_equal operator",
"duplicable":0,
"intermediate":0
}],
"outputs":[
{
"name":"Out",
"comment":"(LoDTensor) n-dim bool tensor. Each element is Out = X >= Y",
"duplicable":0,
"intermediate":0
}],
"attrs":[]
},{
"type":"crop",
"comment":"\nCrop Operator.\n\nCrop input into output, as specified by offsets and shape.\n\nThere are two ways to set shape:\n1. reference input: crop input X into the same shape as reference input.\n The dimension of reference input should\n be the same as the dimension of input X.\n2. shape list: crop input X into the shape described by a list<int>.\n The size of shape list should be the same as\n the dimension size of input X.\n\nThe input should be a k-D tensor(k > 0 and k < 7). As an example:\n\nCase 1:\nGiven\n\n X = [[0, 1, 2, 0, 0]\n [0, 3, 4, 0, 0]\n [0, 0, 0, 0, 0]],\n\nand\n\n offsets = [0, 1],\n\nand\n\n shape = [2, 2],\n\nwe get:\n\n Out = [[1, 2],\n [3, 4]].\n\n\nCase 2:\nGiven\n\n X = [[0, 1, 2, 5, 0]\n [0, 3, 4, 6, 0]\n [0, 0, 0, 0, 0]],\n\nand\n\n offsets = [0, 1],\n\nand\n\n Y = [[0, 0, 0]\n [0, 0, 0]],\n\nwe get:\n\n Out = [[1, 2, 5],\n [3, 4, 6]].\n",
...
...
@@ -4750,7 +4692,13 @@
"duplicable":0,
"intermediate":0
}],
"attrs":[]
"attrs":[
{
"name":"axis",
"type":"int",
"comment":"(int, default -1). The start dimension index for broadcasting Y onto X.",
"generated":0
}]
},{
"type":"equal",
"comment":"equal Operator\n\nIt operates element-wise on X and Y, and returns the Out. Each of them is a\nN-dim tensor. X and Y could be any type. The each element of the Out tensor is\ncalculated by Out = X == Y\n",
...
...
@@ -4773,7 +4721,13 @@
"duplicable":0,
"intermediate":0
}],
"attrs":[]
"attrs":[
{
"name":"axis",
"type":"int",
"comment":"(int, default -1). The start dimension index for broadcasting Y onto X.",
"generated":0
}]
},{
"type":"gather",
"comment":"\nGather Operator.\n\n$Out = X[Index]$\n\nOut is obtained by gathering entries of the outer-most dimension \nof X indexed by Index and concatenate them together.\n\nExample:\n\nX = [[1, 2],\n [3, 4],\n [5, 6]]\n\nIndex = [[1, 2]]\n\nThen:\n\nOut = [[3, 4],\n [5, 6]]\n\n",
...
...
@@ -5359,6 +5313,24 @@
"comment":"(float, default 1.0e-6) Constant for numerical stability",
"generated":0
}]
},{
"type":"log",
"comment":"\nLog Activation Operator.\n\n$out = \\ln(x)$\n\nNatural logarithm of x.\n\n",
"inputs":[
{
"name":"X",
"comment":"Input of Log operator",
"duplicable":0,
"intermediate":0
}],
"outputs":[
{
"name":"Out",
"comment":"Output of Log operator",
"duplicable":0,
"intermediate":0
}],
"attrs":[]
},{
"type":"nce",
"comment":"\nCompute and return the noise-contrastive estimation training loss.\nSee [Noise-contrastive estimation: A new estimation principle for unnormalized statistical models](http://www.jmlr.org/proceedings/papers/v9/gutmann10a/gutmann10a.pdf).\nBy default this operator uses a uniform distribution for sampling.\n",
<li><strong>query</strong> (<em>Variable</em>) – The input variable which is a Tensor or LoDTensor.</li>
<li><strong>key</strong> (<em>Variable</em>) – The input variable which is a Tensor or LoDTensor.</li>
<li><strong>value</strong> (<em>Variable</em>) – The input variable which is a Tensor or LoDTensor.</li>
</ul>
</td>
</tr>
<trclass="field-even field"><thclass="field-name">返回:</th><tdclass="field-body"><pclass="first">The Tensor variables representing the output and attention scores.</p>
<divclass="highlight-python"><divclass="highlight"><pre><span></span><spanclass="c1"># Suppose q, k, v are tensor variables with the following shape:</span>
