"comment":"\nIOU Similarity Operator.\nComputes intersection-over-union (IOU) between two box lists.\n Box list 'X' should be a LoDTensor and 'Y' is a common Tensor,\n boxes in 'Y' are shared by all instance of the batched inputs of X.\n Given two boxes A and B, the calculation of IOU is as follows:\n\n$$\nIOU(A, B) = \n\\frac{area(A\\cap B)}{area(A)+area(B)-area(A\\cap B)}\n$$\n\n",
"inputs":[
{
"name":"X",
"comment":"(LoDTensor, default LoDTensor<float>) Box list X is a 2-D LoDTensor with shape [N, 4] holds N boxes, each box is represented as [xmin, ymin, xmax, ymax], the shape of X is [N, 4]. [xmin, ymin] is the left top coordinate of the box if the input is image feature map, they are close to the origin of the coordinate system. [xmax, ymax] is the right bottom coordinate of the box. This tensor can contain LoD information to represent a batch of inputs. One instance of this batch can contain different numbers of entities.",
"duplicable":0,
"intermediate":0
},{
"name":"Y",
"comment":"(Tensor, default Tensor<float>) Box list Y holds M boxes, each box is represented as [xmin, ymin, xmax, ymax], the shape of X is [N, 4]. [xmin, ymin] is the left top coordinate of the box if the input is image feature map, and [xmax, ymax] is the right bottom coordinate of the box.",
"duplicable":0,
"intermediate":0
}],
"outputs":[
{
"name":"Out",
"comment":"(LoDTensor, the lod is same as input X) The output of iou_similarity op, a tensor with shape [N, M] representing pairwise iou scores.",
"duplicable":0,
"intermediate":0
}],
"attrs":[]
},{
"type":"conditional_block",
"comment":"Conditional block operator\n\nRun the sub-block if X is not empty. Params is the other inputs and Out is the\noutputs of the sub-block.\n",
"inputs":[
{
"name":"X",
"comment":"The conditional variable of this operator. If X is empty, the whole sub-block will not be executed.",
"duplicable":1,
"intermediate":0
},{
"name":"Params",
"comment":"The input variables of the sub-block.",
"duplicable":1,
"intermediate":0
}],
"outputs":[
{
"name":"Out",
"comment":"The output variables of the sub-block.",
"duplicable":1,
"intermediate":0
},{
"name":"Scope",
"comment":"(std::vector<Scope*>) The step scope of conditional block. To unify the conditional block, rnn and while op, the type of scope is std::vector<Scope*>",
"duplicable":0,
"intermediate":0
}],
"attrs":[
{
"name":"sub_block",
"type":"block id",
"comment":"The step block of conditional block operator",
"generated":0
}]
},{
"type":"rmsprop",
"comment":"\nRmsprop Optimizer. \n\n$$\nMeanSquareOut = decay * MeanSquare + (1 - decay) * Grad * Grad \\\\\nMomentOut = momentum * Moment +\n\\frac{LearningRate * Grad}{\\sqrt{MeanSquareOut + epsilon}} \\\\\nParamOut = Param - MomentOut\n$$\n\nThe original slides that proposed Rmsprop: Slide 29 of\nhttp://www.cs.toronto.edu/~tijmen/csc321/slides/lecture_slides_lec6.pdf)\n\n",
...
...
@@ -4725,40 +4800,6 @@
"intermediate":0
}],
"attrs":[]
},{
"type":"conditional_block",
"comment":"Conditional block operator\n\nRun the sub-block if X is not empty. Params is the other inputs and Out is the\noutputs of the sub-block.\n",
"inputs":[
{
"name":"X",
"comment":"The conditional variable of this operator. If X is empty, the whole sub-block will not be executed.",
"duplicable":1,
"intermediate":0
},{
"name":"Params",
"comment":"The input variables of the sub-block.",
"duplicable":1,
"intermediate":0
}],
"outputs":[
{
"name":"Out",
"comment":"The output variables of the sub-block.",
"duplicable":1,
"intermediate":0
},{
"name":"Scope",
"comment":"(std::vector<Scope*>) The step scope of conditional block. To unify the conditional block, rnn and while op, the type of scope is std::vector<Scope*>",
"duplicable":0,
"intermediate":0
}],
"attrs":[
{
"name":"sub_block",
"type":"block id",
"comment":"The step block of conditional block operator",
"generated":0
}]
},{
"type":"sum",
"comment":"\nSum operator.\n\nThis operators sums the input tensors. All the inputs can carry the\nLoD (Level of Details) information. However, the output only shares\nthe LoD information with the first input.\n",
