From 130c108ad979ba8dd44b72eeb7c5f498de253bdd Mon Sep 17 00:00:00 2001 From: JYChen Date: Tue, 19 Jul 2022 10:43:24 +0800 Subject: [PATCH] [new api] add new api paddle.vision.ops.distribute_fpn_proposals (#43736) * add distribute_fpn_proposals * change to new dygraph * fix doc and example code * change fluid impl to current version --- python/paddle/fluid/layers/detection.py | 55 ++------ .../test_distribute_fpn_proposals_op.py | 61 ++++++++- python/paddle/vision/ops.py | 118 ++++++++++++++++++ 3 files changed, 187 insertions(+), 47 deletions(-) diff --git a/python/paddle/fluid/layers/detection.py b/python/paddle/fluid/layers/detection.py index f89c95b93a1..aa6df245480 100644 --- a/python/paddle/fluid/layers/detection.py +++ b/python/paddle/fluid/layers/detection.py @@ -17,6 +17,8 @@ All layers just related to the detection neural network. from __future__ import print_function +import paddle + from .layer_function_generator import generate_layer_fn from .layer_function_generator import autodoc, templatedoc from ..layer_helper import LayerHelper @@ -3774,52 +3776,13 @@ def distribute_fpn_proposals(fpn_rois, refer_level=4, refer_scale=224) """ - num_lvl = max_level - min_level + 1 - - if _non_static_mode(): - assert rois_num is not None, "rois_num should not be None in dygraph mode." - attrs = ('min_level', min_level, 'max_level', max_level, 'refer_level', - refer_level, 'refer_scale', refer_scale) - multi_rois, restore_ind, rois_num_per_level = _C_ops.distribute_fpn_proposals( - fpn_rois, rois_num, num_lvl, num_lvl, *attrs) - return multi_rois, restore_ind, rois_num_per_level - - check_variable_and_dtype(fpn_rois, 'fpn_rois', ['float32', 'float64'], - 'distribute_fpn_proposals') - helper = LayerHelper('distribute_fpn_proposals', **locals()) - dtype = helper.input_dtype('fpn_rois') - multi_rois = [ - helper.create_variable_for_type_inference(dtype) for i in range(num_lvl) - ] - - restore_ind = helper.create_variable_for_type_inference(dtype='int32') - - inputs = {'FpnRois': fpn_rois} - outputs = { - 'MultiFpnRois': multi_rois, - 'RestoreIndex': restore_ind, - } - - if rois_num is not None: - inputs['RoisNum'] = rois_num - rois_num_per_level = [ - helper.create_variable_for_type_inference(dtype='int32') - for i in range(num_lvl) - ] - outputs['MultiLevelRoIsNum'] = rois_num_per_level - - helper.append_op(type='distribute_fpn_proposals', - inputs=inputs, - outputs=outputs, - attrs={ - 'min_level': min_level, - 'max_level': max_level, - 'refer_level': refer_level, - 'refer_scale': refer_scale - }) - if rois_num is not None: - return multi_rois, restore_ind, rois_num_per_level - return multi_rois, restore_ind + return paddle.vision.ops.distribute_fpn_proposals(fpn_rois=fpn_rois, + min_level=min_level, + max_level=max_level, + refer_level=refer_level, + refer_scale=refer_scale, + rois_num=rois_num, + name=name) @templatedoc() diff --git a/python/paddle/fluid/tests/unittests/test_distribute_fpn_proposals_op.py b/python/paddle/fluid/tests/unittests/test_distribute_fpn_proposals_op.py index 06cdaed1988..7950c278422 100644 --- a/python/paddle/fluid/tests/unittests/test_distribute_fpn_proposals_op.py +++ b/python/paddle/fluid/tests/unittests/test_distribute_fpn_proposals_op.py @@ -1,4 +1,4 @@ -# Copyright (c) 2019 PaddlePaddle Authors. All Rights Reserved. +# Copyright (c) 2019 PaddlePaddle Authors. All Rights Reserved. # # Licensed under the Apache License, Version 2.0 (the "License"); # you may not use this file except in compliance with the License. @@ -18,6 +18,8 @@ import unittest import numpy as np import math import sys +import paddle + from op_test import OpTest @@ -164,5 +166,62 @@ class TestDistributeFPNProposalsOpNoOffset( self.pixel_offset = False +class TestDistributeFpnProposalsAPI(unittest.TestCase): + + def setUp(self): + np.random.seed(678) + self.rois_np = np.random.rand(10, 4).astype('float32') + self.rois_num_np = np.array([4, 6]).astype('int32') + + def test_dygraph_with_static(self): + paddle.enable_static() + rois = paddle.static.data(name='rois', shape=[10, 4], dtype='float32') + rois_num = paddle.static.data(name='rois_num', + shape=[None], + dtype='int32') + multi_rois, restore_ind, rois_num_per_level = paddle.vision.ops.distribute_fpn_proposals( + fpn_rois=rois, + min_level=2, + max_level=5, + refer_level=4, + refer_scale=224, + rois_num=rois_num) + fetch_list = multi_rois + [restore_ind] + rois_num_per_level + + exe = paddle.static.Executor() + output_stat = exe.run(paddle.static.default_main_program(), + feed={ + 'rois': self.rois_np, + 'rois_num': self.rois_num_np + }, + fetch_list=fetch_list, + return_numpy=False) + output_stat_np = [] + for output in output_stat: + output_np = np.array(output) + if len(output_np) > 0: + output_stat_np.append(output_np) + + paddle.disable_static() + rois_dy = paddle.to_tensor(self.rois_np) + rois_num_dy = paddle.to_tensor(self.rois_num_np) + multi_rois_dy, restore_ind_dy, rois_num_per_level_dy = paddle.vision.ops.distribute_fpn_proposals( + fpn_rois=rois_dy, + min_level=2, + max_level=5, + refer_level=4, + refer_scale=224, + rois_num=rois_num_dy) + output_dy = multi_rois_dy + [restore_ind_dy] + rois_num_per_level_dy + output_dy_np = [] + for output in output_dy: + output_np = output.numpy() + if len(output_np) > 0: + output_dy_np.append(output_np) + + for res_stat, res_dy in zip(output_stat_np, output_dy_np): + self.assertTrue(np.allclose(res_stat, res_dy)) + + if __name__ == '__main__': unittest.main() diff --git a/python/paddle/vision/ops.py b/python/paddle/vision/ops.py index 7febf4f740e..545ba25f5b4 100644 --- a/python/paddle/vision/ops.py +++ b/python/paddle/vision/ops.py @@ -28,6 +28,7 @@ __all__ = [ #noqa 'yolo_box', 'deform_conv2d', 'DeformConv2D', + 'distribute_fpn_proposals', 'read_file', 'decode_jpeg', 'roi_pool', @@ -835,6 +836,123 @@ class DeformConv2D(Layer): return out +def distribute_fpn_proposals(fpn_rois, + min_level, + max_level, + refer_level, + refer_scale, + pixel_offset=False, + rois_num=None, + name=None): + r""" + In Feature Pyramid Networks (FPN) models, it is needed to distribute + all proposals into different FPN level, with respect to scale of the proposals, + the referring scale and the referring level. Besides, to restore the order of + proposals, we return an array which indicates the original index of rois + in current proposals. To compute FPN level for each roi, the formula is given as follows: + + .. math:: + roi\_scale &= \sqrt{BBoxArea(fpn\_roi)} + level = floor(&\log(\\frac{roi\_scale}{refer\_scale}) + refer\_level) + where BBoxArea is a function to compute the area of each roi. + + Args: + fpn_rois (Tensor): The input fpn_rois. 2-D Tensor with shape [N, 4] and data type can be + float32 or float64. + min_level (int): The lowest level of FPN layer where the proposals come + from. + max_level (int): The highest level of FPN layer where the proposals + come from. + refer_level (int): The referring level of FPN layer with specified scale. + refer_scale (int): The referring scale of FPN layer with specified level. + pixel_offset (bool, optional): Whether there is pixel offset. If True, the offset of + image shape will be 1. 'False' by default. + rois_num (Tensor, optional): 1-D Tensor contains the number of RoIs in each image. + The shape is [B] and data type is int32. B is the number of images. + If rois_num not None, it will return a list of 1-D Tensor. Each element + is the output RoIs' number of each image on the corresponding level + and the shape is [B]. None by default. + name (str, optional): For detailed information, please refer + to :ref:`api_guide_Name`. Usually name is no need to set and + None by default. + + Returns: + multi_rois (List) : The proposals in each FPN level. It is a list of 2-D Tensor with shape [M, 4], where M is + and data type is same as `fpn_rois` . The length is max_level-min_level+1. + restore_ind (Tensor): The index used to restore the order of fpn_rois. It is a 2-D Tensor with shape [N, 1] + , where N is the number of total rois. The data type is int32. + rois_num_per_level (List): A list of 1-D Tensor and each Tensor is + the RoIs' number in each image on the corresponding level. The shape + is [B] and data type of int32, where B is the number of images. + + Examples: + .. code-block:: python + + import paddle + + fpn_rois = paddle.rand((10, 4)) + rois_num = paddle.to_tensor([3, 1, 4, 2], dtype=paddle.int32) + + multi_rois, restore_ind, rois_num_per_level = paddle.vision.ops.distribute_fpn_proposals( + fpn_rois=fpn_rois, + min_level=2, + max_level=5, + refer_level=4, + refer_scale=224, + rois_num=rois_num) + """ + num_lvl = max_level - min_level + 1 + + if _non_static_mode(): + assert rois_num is not None, "rois_num should not be None in dygraph mode." + attrs = ('min_level', min_level, 'max_level', max_level, 'refer_level', + refer_level, 'refer_scale', refer_scale, 'pixel_offset', + pixel_offset) + multi_rois, restore_ind, rois_num_per_level = _C_ops.distribute_fpn_proposals( + fpn_rois, rois_num, num_lvl, num_lvl, *attrs) + return multi_rois, restore_ind, rois_num_per_level + + else: + check_variable_and_dtype(fpn_rois, 'fpn_rois', ['float32', 'float64'], + 'distribute_fpn_proposals') + helper = LayerHelper('distribute_fpn_proposals', **locals()) + dtype = helper.input_dtype('fpn_rois') + multi_rois = [ + helper.create_variable_for_type_inference(dtype) + for i in range(num_lvl) + ] + + restore_ind = helper.create_variable_for_type_inference(dtype='int32') + + inputs = {'FpnRois': fpn_rois} + outputs = { + 'MultiFpnRois': multi_rois, + 'RestoreIndex': restore_ind, + } + + if rois_num is not None: + inputs['RoisNum'] = rois_num + rois_num_per_level = [ + helper.create_variable_for_type_inference(dtype='int32') + for i in range(num_lvl) + ] + outputs['MultiLevelRoIsNum'] = rois_num_per_level + else: + rois_num_per_level = None + + helper.append_op(type='distribute_fpn_proposals', + inputs=inputs, + outputs=outputs, + attrs={ + 'min_level': min_level, + 'max_level': max_level, + 'refer_level': refer_level, + 'refer_scale': refer_scale, + 'pixel_offset': pixel_offset + }) + return multi_rois, restore_ind, rois_num_per_level + + def read_file(filename, name=None): """ Reads and outputs the bytes contents of a file as a uint8 Tensor -- GitLab