m53297601
/
Paddle
1
0
Fork 0
Code Issues Pull Requests Releases Wiki Activity

Fix english doc api: sequence_slice, sigmoid_cross_entropy_with_logits, ssd_loss, DetectionMAP, detection_map (#20405)

Browse Source 
* Fix english doc api: sequence_slice, sigmoid_cross_entropy_with_logits, ssd_loss, DetectionMAP, detection_map
revert-20712-fix_depthwise_conv
Guanghua Yu 5 years ago committed by Kaipeng Deng
parent 9ee288ac87
commit bc4c7a9eb6
4 changed files with 89 additions and 76 deletions
Show Stats Download Patch File Download Diff File

6
paddle/fluid/API.spec
Unescape View File

@ -166,7 +166,7 @@ paddle.fluid.layers.reduce_all (ArgSpec(args=['input', 'dim', 'keep_dim', 'name'
paddle.fluid.layers.reduce_any (ArgSpec(args=['input', 'dim', 'keep_dim', 'name'], varargs=None, keywords=None, defaults=(None, False, None)), ('document', 'fbc9e73da7a2964ba5693864aed36abb'))
paddle.fluid.layers.sequence_first_step (ArgSpec(args=['input'], varargs=None, keywords=None, defaults=None), ('document', '227a75392ae194de0504f5c6812dade9'))
paddle.fluid.layers.sequence_last_step (ArgSpec(args=['input'], varargs=None, keywords=None, defaults=None), ('document', '34372f58331247749e8b0a1663cf233b'))
paddle.fluid.layers.sequence_slice (ArgSpec(args=['input', 'offset', 'length', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', '39fbc5437be389f6c0c769f82fc1fba2'))
paddle.fluid.layers.sequence_slice (ArgSpec(args=['input', 'offset', 'length', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', 'c051c1b17c1946a1f378bc457bcc63cb'))
paddle.fluid.layers.dropout (ArgSpec(args=['x', 'dropout_prob', 'is_test', 'seed', 'name', 'dropout_implementation'], varargs=None, keywords=None, defaults=(False, None, None, 'downgrade_in_infer')), ('document', '392dd4bad607fd853f71fec71801044f'))
paddle.fluid.layers.split (ArgSpec(args=['input', 'num_or_sections', 'dim', 'name'], varargs=None, keywords=None, defaults=(-1, None)), ('document', '64073050d3f172d71ace73d7bbb4168e'))
paddle.fluid.layers.ctc_greedy_decoder (ArgSpec(args=['input', 'blank', 'input_length', 'padding_value', 'name'], varargs=None, keywords=None, defaults=(None, 0, None)), ('document', '31e0cbec2898efae95853034adadfe2b'))
@ -271,7 +271,7 @@ paddle.fluid.layers.clip (ArgSpec(args=['x', 'min', 'max', 'name'], varargs=None
paddle.fluid.layers.clip_by_norm (ArgSpec(args=['x', 'max_norm', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', 'a5f4917fda557ceb834168cdbec6d51b'))
paddle.fluid.layers.mean (ArgSpec(args=['x', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', '597257fb94d0597c404a6a5c91ab5258'))
paddle.fluid.layers.mul (ArgSpec(args=['x', 'y', 'x_num_col_dims', 'y_num_col_dims', 'name'], varargs=None, keywords=None, defaults=(1, 1, None)), ('document', 'a91eb670033cd103cd8b24624fef5f69'))
paddle.fluid.layers.sigmoid_cross_entropy_with_logits (ArgSpec(args=['x', 'label', 'ignore_index', 'name', 'normalize'], varargs=None, keywords=None, defaults=(-100, None, False)), ('document', '7637c974f2d749d359acae9062c4d96f'))
paddle.fluid.layers.sigmoid_cross_entropy_with_logits (ArgSpec(args=['x', 'label', 'ignore_index', 'name', 'normalize'], varargs=None, keywords=None, defaults=(-100, None, False)), ('document', '8cdf9e34f73b6f0ed8b60b59a8207fb6'))
paddle.fluid.layers.maxout (ArgSpec(args=['x', 'groups', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', '406eee439e41988c8a0304186626a0dd'))
paddle.fluid.layers.space_to_depth (ArgSpec(args=['x', 'blocksize', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', '26decdea9376b6b9a0d3432d82ca207b'))
paddle.fluid.layers.affine_grid (ArgSpec(args=['theta', 'out_shape', 'name'], varargs=None, keywords=None, defaults=(None,)), ('document', '315b50c1cbd9569375b098c56f1e91c9'))
@ -412,7 +412,7 @@ paddle.fluid.layers.multi_box_head (ArgSpec(args=['inputs', 'image', 'base_size'
paddle.fluid.layers.bipartite_match (ArgSpec(args=['dist_matrix', 'match_type', 'dist_threshold', 'name'], varargs=None, keywords=None, defaults=(None, None, None)), ('document', '6f795f407a8e3a3ec3da52726c73405a'))
paddle.fluid.layers.target_assign (ArgSpec(args=['input', 'matched_indices', 'negative_indices', 'mismatch_value', 'name'], varargs=None, keywords=None, defaults=(None, None, None)), ('document', 'e9685f32d21bec8c013626c0254502c5'))
paddle.fluid.layers.detection_output (ArgSpec(args=['loc', 'scores', 'prior_box', 'prior_box_var', 'background_label', 'nms_threshold', 'nms_top_k', 'keep_top_k', 'score_threshold', 'nms_eta', 'return_index'], varargs=None, keywords=None, defaults=(0, 0.3, 400, 200, 0.01, 1.0, False)), ('document', '5485bcaceb0cde2695565a2ffd5bbd40'))
paddle.fluid.layers.ssd_loss (ArgSpec(args=['location', 'confidence', 'gt_box', 'gt_label', 'prior_box', 'prior_box_var', 'background_label', 'overlap_threshold', 'neg_pos_ratio', 'neg_overlap', 'loc_loss_weight', 'conf_loss_weight', 'match_type', 'mining_type', 'normalize', 'sample_size'], varargs=None, keywords=None, defaults=(None, 0, 0.5, 3.0, 0.5, 1.0, 1.0, 'per_prediction', 'max_negative', True, None)), ('document', '14d1eeae0f41b6792be43c1c0be0589b'))
paddle.fluid.layers.ssd_loss (ArgSpec(args=['location', 'confidence', 'gt_box', 'gt_label', 'prior_box', 'prior_box_var', 'background_label', 'overlap_threshold', 'neg_pos_ratio', 'neg_overlap', 'loc_loss_weight', 'conf_loss_weight', 'match_type', 'mining_type', 'normalize', 'sample_size'], varargs=None, keywords=None, defaults=(None, 0, 0.5, 3.0, 0.5, 1.0, 1.0, 'per_prediction', 'max_negative', True, None)), ('document', '1f1ab4f908ceddef1d99a8363e6826af'))
paddle.fluid.layers.rpn_target_assign (ArgSpec(args=['bbox_pred', 'cls_logits', 'anchor_box', 'anchor_var', 'gt_boxes', 'is_crowd', 'im_info', 'rpn_batch_size_per_im', 'rpn_straddle_thresh', 'rpn_fg_fraction', 'rpn_positive_overlap', 'rpn_negative_overlap', 'use_random'], varargs=None, keywords=None, defaults=(256, 0.0, 0.5, 0.7, 0.3, True)), ('document', 'd46629656b4ce9b07809e32c0482cbef'))
paddle.fluid.layers.retinanet_target_assign (ArgSpec(args=['bbox_pred', 'cls_logits', 'anchor_box', 'anchor_var', 'gt_boxes', 'gt_labels', 'is_crowd', 'im_info', 'num_classes', 'positive_overlap', 'negative_overlap'], varargs=None, keywords=None, defaults=(1, 0.5, 0.4)), ('document', '543b2a40641260e745a76b1f7a25fb2a'))
paddle.fluid.layers.sigmoid_focal_loss (ArgSpec(args=['x', 'label', 'fg_num', 'gamma', 'alpha'], varargs=None, keywords=None, defaults=(2, 0.25)), ('document', '4702891755596c8853aaeb874a5fdb46'))

84
python/paddle/fluid/layers/detection.py
Unescape View File

@ -1127,14 +1127,14 @@ def detection_map(detect_res,
overlap_threshold: ${overlap_threshold_comment}
evaluate_difficult: ${evaluate_difficult_comment}
has_state: ${has_state_comment}
input_states: If not None, It contains 3 elements:
1. pos_count ${pos_count_comment}.
2. true_pos ${true_pos_comment}.
3. false_pos ${false_pos_comment}.
out_states: If not None, it contains 3 elements.
1. accum_pos_count ${accum_pos_count_comment}.
2. accum_true_pos ${accum_true_pos_comment}.
3. accum_false_pos ${accum_false_pos_comment}.
input_states: (tuple|None) If not None, It contains 3 elements:
(1) pos_count ${pos_count_comment}.
(2) true_pos ${true_pos_comment}.
(3) false_pos ${false_pos_comment}.
out_states: (tuple|None) If not None, it contains 3 elements.
(1) accum_pos_count ${accum_pos_count_comment}.
(2) accum_true_pos ${accum_true_pos_comment}.
(3) accum_false_pos ${accum_false_pos_comment}.
ap_version: ${ap_type_comment}
Returns:
@ -1146,15 +1146,13 @@ def detection_map(detect_res,
import paddle.fluid as fluid
from fluid.layers import detection
detect_res = fluid.layers.data(
detect_res = fluid.data(
name='detect_res',
shape=[10, 6],
append_batch_size=False,
dtype='float32')
label = fluid.layers.data(
label = fluid.data(
name='label',
shape=[10, 6],
append_batch_size=False,
dtype='float32')
map_out = detection.detection_map(detect_res, label, 21)
@ -1446,22 +1444,28 @@ def ssd_loss(location,
location (Variable): The location predictions are a 3D Tensor with
shape [N, Np, 4], N is the batch size, Np is total number of
predictions for each instance. 4 is the number of coordinate values,
the layout is [xmin, ymin, xmax, ymax].
the layout is [xmin, ymin, xmax, ymax].The data type is float32 or
float64.
confidence (Variable): The confidence predictions are a 3D Tensor
with shape [N, Np, C], N and Np are the same as they are in
`location`, C is the class number.
`location`, C is the class number.The data type is float32 or
float64.
gt_box (Variable): The ground-truth bounding boxes (bboxes) are a 2D
LoDTensor with shape [Ng, 4], Ng is the total number of ground-truth
bboxes of mini-batch input.
bboxes of mini-batch input.The data type is float32 or float64.
gt_label (Variable): The ground-truth labels are a 2D LoDTensor
with shape [Ng, 1].
with shape [Ng, 1].Ng is the total number of ground-truth bboxes of
mini-batch input, 1 is the number of class. The data type is float32
or float64.
prior_box (Variable): The prior boxes are a 2D Tensor with shape [Np, 4].
Np and 4 are the same as they are in `location`. The data type is
float32 or float64.
prior_box_var (Variable): The variance of prior boxes are a 2D Tensor
with shape [Np, 4].
with shape [Np, 4]. Np and 4 are the same as they are in `prior_box`
background_label (int): The index of background label, 0 by default.
overlap_threshold (float): If match_type is 'per_prediction', use
`overlap_threshold` to determine the extra matching bboxes when
finding matched boxes. 0.5 by default.
'overlap_threshold' to determine the extra matching bboxes when finding \
matched boxes. 0.5 by default.
neg_pos_ratio (float): The ratio of the negative boxes to the positive
boxes, used only when mining_type is 'max_negative', 3.0 by default.
neg_overlap (float): The negative overlap upper bound for the unmatched
@ -1479,32 +1483,34 @@ def ssd_loss(location,
mining_type is 'hard_example'.
Returns:
The weighted sum of the localization loss and confidence loss, with \
shape [N * Np, 1], N and Np are the same as they are in `location`.
Variable(Tensor): The weighted sum of the localization loss and confidence loss, \
with shape [N * Np, 1], N and Np are the same as they are in
`location`.The data type is float32 or float64.
Raises:
ValueError: If mining_type is 'hard_example', now only support mining \
type of `max_negative`.
Examples:
>>> import paddle.fluid as fluid
>>> pb = fluid.layers.data(
>>> name='prior_box',
>>> shape=[10, 4],
>>> append_batch_size=False,
>>> dtype='float32')
>>> pbv = fluid.layers.data(
>>> name='prior_box_var',
>>> shape=[10, 4],
>>> append_batch_size=False,
>>> dtype='float32')
>>> loc = fluid.layers.data(name='target_box', shape=[10, 4], dtype='float32')
>>> scores = fluid.layers.data(name='scores', shape=[10, 21], dtype='float32')
>>> gt_box = fluid.layers.data(
>>> name='gt_box', shape=[4], lod_level=1, dtype='float32')
>>> gt_label = fluid.layers.data(
>>> name='gt_label', shape=[1], lod_level=1, dtype='float32')
>>> loss = fluid.layers.ssd_loss(loc, scores, gt_box, gt_label, pb, pbv)
.. code-block:: python
import paddle.fluid as fluid
pb = fluid.data(
name='prior_box',
shape=[10, 4],
dtype='float32')
pbv = fluid.data(
name='prior_box_var',
shape=[10, 4],
dtype='float32')
loc = fluid.data(name='target_box', shape=[10, 4], dtype='float32')
scores = fluid.data(name='scores', shape=[10, 21], dtype='float32')
gt_box = fluid.data(
name='gt_box', shape=[4], lod_level=1, dtype='float32')
gt_label = fluid.data(
name='gt_label', shape=[1], lod_level=1, dtype='float32')
loss = fluid.layers.ssd_loss(loc, scores, gt_box, gt_label, pb, pbv)
"""
helper = LayerHelper('ssd_loss', **locals())

27
python/paddle/fluid/layers/nn.py
Unescape View File

@ -3220,12 +3220,15 @@ def sequence_slice(input, offset, length, name=None):
should be equal. The **offset** should start from 0.
Args:
input(Variable): The input Variable which consists of the complete
sequences.
offset(Variable): The offset to slice each sequence.
length(Variable): The length of each subsequence.
name(str|None): A name for this layer(optional). If set None, the
layer will be named automatically.
input(Variable): LoDTensor, The input Variable which consists of the complete
sequences.The data type is float32 or float64.
offset(Variable): LoDTensor, The offset to slice each sequence.The data
type is int32 or int64.
length(Variable): LoDTensor, The length of each subsequence.The data
type is int32 or int64.
name(str|None): The default value is None. Normally there is no need
for user to set this property. For more information,
please refer to :ref:`api_guide_Name`
Returns:
Variable: The output subsequences.
@ -3236,7 +3239,7 @@ def sequence_slice(input, offset, length, name=None):
import paddle.fluid as fluid
import numpy as np
seqs = fluid.layers.data(name='x', shape=[10, 5],
seqs = fluid.data(name='x', shape=[10, 5],
dtype='float32', lod_level=1)
offset = fluid.layers.assign(input=np.array([[0, 1]]).astype("int32"))
length = fluid.layers.assign(input=np.array([[2, 1]]).astype("int32"))
@ -13935,8 +13938,10 @@ def sigmoid_cross_entropy_with_logits(x,
Args:
x(${x_type}): ${x_comment}
label(${label_type}): ${label_comment}
ignore_index(&{ignore_index}): ${ignore_index_comment}
name(basestring|None): Name of the output.
ignore_index(int): ${ignore_index_comment}
name(str|None): The default value is None. Normally there is
no need for user to set this property. For more information,
please refer to :ref:`api_guide_Name`
normalize(bool): If true, divide the output by the number of
targets != ignore_index.
@ -13947,9 +13952,9 @@ def sigmoid_cross_entropy_with_logits(x,
.. code-block:: python
import paddle.fluid as fluid
input = fluid.layers.data(
input = fluid.data(
name='data', shape=[10], dtype='float32')
label = fluid.layers.data(
label = fluid.data(
name='data', shape=[10], dtype='float32')
loss = fluid.layers.sigmoid_cross_entropy_with_logits(
x=input,

48
python/paddle/fluid/metrics.py
Unescape View File

@ -701,6 +701,8 @@ class DetectionMAP(object):
1. calculate the true positive and false positive according to the input
of detection and labels.
2. calculate mAP value, support two versions: '11 point' and 'integral'.
11point: the 11-point interpolated average precision.
integral: the natural integral of the precision-recall curve.
Please get more information from the following articles:
@ -709,15 +711,18 @@ class DetectionMAP(object):
https://arxiv.org/abs/1512.02325
Args:
input (Variable): The detection results, which is a LoDTensor with shape
input (Variable): LoDTensor, The detection results, which is a LoDTensor with shape
[M, 6]. The layout is [label, confidence, xmin, ymin, xmax, ymax].
gt_label (Variable): The ground truth label index, which is a LoDTensor
with shape [N, 1].
gt_box (Variable): The ground truth bounding box (bbox), which is a
The data type is float32 or float64.
gt_label (Variable): LoDTensor, The ground truth label index, which is a LoDTensor
with shape [N, 1].The data type is float32 or float64.
gt_box (Variable): LoDTensor, The ground truth bounding box (bbox), which is a
LoDTensor with shape [N, 4]. The layout is [xmin, ymin, xmax, ymax].
gt_difficult (Variable|None): Whether this ground truth is a difficult
The data type is float32 or float64.
gt_difficult (Variable|None): LoDTensor, Whether this ground truth is a difficult
bounding bbox, which can be a LoDTensor [N, 1] or not set. If None,
it means all the ground truth labels are not difficult bbox.
it means all the ground truth labels are not difficult bbox.The
data type is int.
class_num (int): The class number.
background_label (int): The index of background label, the background
label will be ignored. If set to -1, then all categories will be
@ -727,47 +732,44 @@ class DetectionMAP(object):
evaluate_difficult (bool): Whether to consider difficult ground truth
for evaluation, True by default. This argument does not work when
gt_difficult is None.
ap_version (string): The average precision calculation ways, it must be
ap_version (str): The average precision calculation ways, it must be
'integral' or '11point'. Please check
https://sanchom.wordpress.com/tag/average-precision/ for details.
- 11point: the 11-point interpolated average precision.
- integral: the natural integral of the precision-recall curve.
Examples:
.. code-block:: python
import paddle.fluid as fluid
import paddle.fluid.layers as layers
batch_size = -1 # can be any size
batch_size = None # can be any size
image_boxs_num = 10
bounding_bboxes_num = 21
pb = layers.data(name='prior_box', shape=[image_boxs_num, 4],
append_batch_size=False, dtype='float32')
pb = fluid.data(name='prior_box', shape=[image_boxs_num, 4],
dtype='float32')
pbv = layers.data(name='prior_box_var', shape=[image_boxs_num, 4],
append_batch_size=False, dtype='float32')
pbv = fluid.data(name='prior_box_var', shape=[image_boxs_num, 4],
dtype='float32')
loc = layers.data(name='target_box', shape=[batch_size, bounding_bboxes_num, 4],
append_batch_size=False, dtype='float32')
loc = fluid.data(name='target_box', shape=[batch_size, bounding_bboxes_num, 4],
dtype='float32')
scores = layers.data(name='scores', shape=[batch_size, bounding_bboxes_num, image_boxs_num],
append_batch_size=False, dtype='float32')
scores = fluid.data(name='scores', shape=[batch_size, bounding_bboxes_num, image_boxs_num],
dtype='float32')
nmsed_outs = fluid.layers.detection_output(scores=scores,
loc=loc, prior_box=pb, prior_box_var=pbv)
gt_box = fluid.layers.data(name="gt_box", shape=[batch_size, 4], dtype="float32")
gt_label = fluid.layers.data(name="gt_label", shape=[batch_size, 1], dtype="float32")
difficult = fluid.layers.data(name="difficult", shape=[batch_size, 1], dtype="float32")
gt_box = fluid.data(name="gt_box", shape=[batch_size, 4], dtype="float32")
gt_label = fluid.data(name="gt_label", shape=[batch_size, 1], dtype="float32")
difficult = fluid.data(name="difficult", shape=[batch_size, 1], dtype="float32")
exe = fluid.Executor(fluid.CUDAPlace(0))
map_evaluator = fluid.metrics.DetectionMAP(nmsed_outs, gt_label, gt_box, difficult, class_num = 3)
cur_map, accum_map = map_evaluator.get_map_var()
"""
def __init__(self,

Write Preview
Loading…
Cancel
Save