提交 c58ba827 编写于 作者: Y yi.wu

update

上级 7b54b30b
......@@ -156,7 +156,7 @@ Parameters(strides, paddings) are two elements. These two elements represent hei
and width, respectively.
The input(X) size and output(Out) size may be different.
Example:
For an example:
Input:
Input shape: $(N, C_{in}, H_{in}, W_{in})$
Filter shape: $(C_{in}, C_{out}, H_f, W_f)$
......
......@@ -53,17 +53,14 @@ sequence of observed tags.
The output of this operator changes according to whether Input(Label) is given:
1. Input(Label) is given:
This happens in training. This operator is used to co-work with the chunk_eval
operator.
When Input(Label) is given, the crf_decoding operator returns a row vector
with shape [N x 1] whose values are fixed to be 0, indicating an incorrect
prediction, or 1 indicating a tag is correctly predicted. Such an output is the
input to chunk_eval operator.
2. Input(Label) is not given:
This is the standard decoding process.
The crf_decoding operator returns a row vector with shape [N x 1] whose values
......
......@@ -149,7 +149,9 @@ The operator has three steps:
1. Dividing each region proposal into equal-sized sections with
the pooled_width and pooled_height
2. Finding the largest value in each section
3. Copying these max values to the output buffer
ROI Pooling for Faster-RCNN. The link below is a further introduction:
......
......@@ -109,8 +109,6 @@ class BlockGuardServ(BlockGuard):
class ListenAndServ(object):
"""
ListenAndServ layer.
ListenAndServ is used to create a rpc server bind and listen
on specific TCP port, this server will run the sub-block when
received variables from clients.
......@@ -121,6 +119,9 @@ class ListenAndServ(object):
fan_in(int): how many client are expected to report to this server, default: 1.
optimizer_mode(bool): whether to run the server as a parameter server, default: True.
Returns:
None
Examples:
.. code-block:: python
......
......@@ -806,7 +806,7 @@ def crf_decoding(input, param_attr, label=None):
label(${label_type}): ${label_comment}
Returns:
${viterbi_path_comment}
Variable: ${viterbi_path_comment}
"""
helper = LayerHelper('crf_decoding', **locals())
transition = helper.get_parameter(param_attr.name)
......@@ -828,7 +828,7 @@ def cos_sim(X, Y):
Args:
X (Variable): ${x_comment}
Y (Variable): ${x_comment}
Y (Variable): ${y_comment}
Returns:
Variable: the output of cosine(X, Y).
......@@ -1036,9 +1036,9 @@ def chunk_eval(input,
excluded_chunk_types (list): ${excluded_chunk_types_comment}
Returns:
tuple: tuple containing: (precision, recall, f1_score,
tuple: tuple containing: precision, recall, f1_score,
num_infer_chunks, num_label_chunks,
num_correct_chunks)
num_correct_chunks
"""
helper = LayerHelper("chunk_eval", **locals())
......@@ -3050,8 +3050,6 @@ def nce(input,
def transpose(x, perm, name=None):
"""
**transpose Layer**
Permute the dimensions of `input` according to `perm`.
The `i`-th dimension of the returned tensor will correspond to the
......@@ -3918,7 +3916,7 @@ def roi_pool(input, rois, pooled_height=1, pooled_width=1, spatial_scale=1.0):
spatial_scale (float): ${spatial_scale_comment} Default: 1.0
Returns:
roi_pool (Variable): ${out_comment}.
Variable: ${out_comment}.
Examples:
.. code-block:: python
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册