From 5ca0b7628d90098298604ecf4f62d4845db99b7d Mon Sep 17 00:00:00 2001 From: wanghaox Date: Thu, 8 Feb 2018 17:43:32 +0800 Subject: [PATCH] add OutPosCount for detection_map op --- paddle/operators/detection_map_op.cc | 47 ++++++- paddle/operators/detection_map_op.h | 132 +++++++++++++++++- .../v2/fluid/tests/test_detection_map_op.py | 111 +++++++++++++-- 3 files changed, 271 insertions(+), 19 deletions(-) diff --git a/paddle/operators/detection_map_op.cc b/paddle/operators/detection_map_op.cc index 553adb215..1ab691eb4 100644 --- a/paddle/operators/detection_map_op.cc +++ b/paddle/operators/detection_map_op.cc @@ -1,4 +1,4 @@ -/* Copyright (c) 2016 PaddlePaddle Authors. All Rights Reserve. +/* Copyright (c) 2018 PaddlePaddle Authors. All Rights Reserve. Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with the License. @@ -28,6 +28,12 @@ class DetectionMAPOp : public framework::OperatorWithKernel { "Input(Detection) of DetectionMAPOp should not be null."); PADDLE_ENFORCE(ctx->HasInput("Label"), "Input(Label) of DetectionMAPOp should not be null."); + PADDLE_ENFORCE(ctx->HasOutput("OutPosCount"), + "Output(OutPosCount) of DetectionMAPOp should not be null."); + PADDLE_ENFORCE(ctx->HasOutput("OutTruePos"), + "Output(OutTruePos) of DetectionMAPOp should not be null."); + PADDLE_ENFORCE(ctx->HasOutput("OutFalsePos"), + "Output(OutFalsePos) of DetectionMAPOp should not be null."); PADDLE_ENFORCE(ctx->HasOutput("MAP"), "Output(MAP) of DetectionMAPOp should not be null."); @@ -44,9 +50,6 @@ class DetectionMAPOp : public framework::OperatorWithKernel { PADDLE_ENFORCE_EQ(label_dims[1], 6UL, "The shape is of Input(Label) [N, 6]."); - auto ap_type = GetAPType(ctx->Attrs().Get("ap_type")); - PADDLE_ENFORCE_NE(ap_type, APType::kNone, - "The ap_type should be 'integral' or '11point."); auto map_dim = framework::make_ddim({1}); ctx->SetOutputDim("MAP", map_dim); } @@ -55,7 +58,8 @@ class DetectionMAPOp : public framework::OperatorWithKernel { framework::OpKernelType GetExpectedKernelType( const framework::ExecutionContext& ctx) const override { return framework::OpKernelType( - framework::ToDataType(ctx.Input("Label")->type()), + framework::ToDataType( + ctx.Input("Detection")->type()), ctx.device_context()); } }; @@ -80,6 +84,33 @@ class DetectionMAPOpMaker : public framework::OpProtoAndCheckerMaker { "the offsets in first dimension are called LoD, the number of " "offset is N + 1, if LoD[i + 1] - LoD[i] == 0, means there is " "no detected data."); + AddInput("PosCount", + "(Tensor) A tensor with shape [Ncls, 1], store the " + "input positive example count of each class.") + .AsDispensable(); + AddInput("TruePos", + "(LodTensor) A 2-D LodTensor with shape [Ntp, 2], store the " + "input true positive example of each class.") + .AsDispensable(); + AddInput("FalsePos", + "(LodTensor) A 2-D LodTensor with shape [Nfp, 2], store the " + "input false positive example of each class.") + .AsDispensable(); + AddOutput("OutPosCount", + "(Tensor) A tensor with shape [Ncls, 1], store the " + "positive example count of each class. It combines the input " + "input(PosCount) and the positive example count computed from " + "input(Detection) and input(Label)."); + AddOutput("OutTruePos", + "(LodTensor) A LodTensor with shape [Ntp', 2], store the " + "true positive example of each class. It combines the " + "input(TruePos) and the true positive examples computed from " + "input(Detection) and input(Label)."); + AddOutput("OutFalsePos", + "(LodTensor) A LodTensor with shape [Nfp', 2], store the " + "false positive example of each class. It combines the " + "input(FalsePos) and the false positive examples computed from " + "input(Detection) and input(Label)."); AddOutput("MAP", "(Tensor) A tensor with shape [1], store the mAP evaluate " "result of the detection."); @@ -97,7 +128,11 @@ class DetectionMAPOpMaker : public framework::OpProtoAndCheckerMaker { "(string, default 'integral') " "The AP algorithm type, 'integral' or '11point'.") .SetDefault("integral") - .InEnum({"integral", "11point"}); + .InEnum({"integral", "11point"}) + .AddCustomChecker([](const std::string& ap_type) { + PADDLE_ENFORCE_NE(GetAPType(ap_type), APType::kNone, + "The ap_type should be 'integral' or '11point."); + }); AddComment(R"DOC( Detection mAP evaluate operator. The general steps are as follows. First, calculate the true positive and diff --git a/paddle/operators/detection_map_op.h b/paddle/operators/detection_map_op.h index d29a6968e..fd0ddd10a 100644 --- a/paddle/operators/detection_map_op.h +++ b/paddle/operators/detection_map_op.h @@ -1,4 +1,4 @@ -/* Copyright (c) 2016 PaddlePaddle Authors. All Rights Reserve. +/* Copyright (c) 2018 PaddlePaddle Authors. All Rights Reserve. Licensed under the Apache License, Version 2.0 (the "License"); you may not use this file except in compliance with the License. @@ -58,6 +58,14 @@ class DetectionMAPOpKernel : public framework::OpKernel { auto* in_label = ctx.Input("Label"); auto* out_map = ctx.Output("MAP"); + auto* in_pos_count = ctx.Input("PosCount"); + auto* in_true_pos = ctx.Input("TruePos"); + auto* in_false_pos = ctx.Input("FalsePos"); + + auto* out_pos_count = ctx.Output("OutPosCount"); + auto* out_true_pos = ctx.Output("OutTruePos"); + auto* out_false_pos = ctx.Output("OutFalsePos"); + float overlap_threshold = ctx.Attr("overlap_threshold"); float evaluate_difficult = ctx.Attr("evaluate_difficult"); auto ap_type = GetAPType(ctx.Attr("ap_type")); @@ -79,12 +87,20 @@ class DetectionMAPOpKernel : public framework::OpKernel { std::map>> true_pos; std::map>> false_pos; + if (in_pos_count != nullptr) { + GetInputPos(*in_pos_count, *in_true_pos, *in_false_pos, label_pos_count, + true_pos, false_pos); + } + CalcTrueAndFalsePositive(gt_boxes, detect_boxes, evaluate_difficult, overlap_threshold, label_pos_count, true_pos, false_pos); T map = CalcMAP(ap_type, label_pos_count, true_pos, false_pos); + GetOutputPos(ctx, label_pos_count, true_pos, false_pos, *out_pos_count, + *out_true_pos, *out_false_pos); + T* map_data = out_map->mutable_data(ctx.GetPlace()); map_data[0] = map; } @@ -161,6 +177,119 @@ class DetectionMAPOpKernel : public framework::OpKernel { } } + void GetOutputPos( + const framework::ExecutionContext& ctx, + const std::map& label_pos_count, + const std::map>>& true_pos, + const std::map>>& false_pos, + framework::Tensor& output_pos_count, + framework::LoDTensor& output_true_pos, + framework::LoDTensor& output_false_pos) const { + int max_class_id = 0; + int true_pos_count = 0; + int false_pos_count = 0; + for (auto it = label_pos_count.begin(); it != label_pos_count.end(); ++it) { + int label = it->first; + if (label > max_class_id) max_class_id = label; + int label_num_pos = it->second; + if (label_num_pos == 0 || true_pos.find(label) == true_pos.end()) + continue; + auto label_true_pos = true_pos.find(label)->second; + auto label_false_pos = false_pos.find(label)->second; + true_pos_count += label_true_pos.size(); + false_pos_count += label_false_pos.size(); + } + + int* pos_count_data = output_pos_count.mutable_data( + framework::make_ddim({max_class_id + 1, 1}), ctx.GetPlace()); + T* true_pos_data = output_true_pos.mutable_data( + framework::make_ddim({true_pos_count, 2}), ctx.GetPlace()); + T* false_pos_data = output_false_pos.mutable_data( + framework::make_ddim({false_pos_count, 2}), ctx.GetPlace()); + true_pos_count = 0; + false_pos_count = 0; + std::vector true_pos_starts = {0}; + std::vector false_pos_starts = {0}; + for (int i = 0; i <= max_class_id; ++i) { + auto it_count = label_pos_count.find(i); + pos_count_data[i] = 0; + if (it_count != label_pos_count.end()) { + pos_count_data[i] = it_count->second; + } + auto it_true_pos = true_pos.find(i); + if (it_true_pos != true_pos.end()) { + const std::vector>& true_pos_vec = + it_true_pos->second; + for (const std::pair& tp : true_pos_vec) { + true_pos_data[true_pos_count * 2] = tp.first; + true_pos_data[true_pos_count * 2 + 1] = static_cast(tp.second); + true_pos_count++; + } + } + true_pos_starts.push_back(true_pos_count); + + auto it_false_pos = false_pos.find(i); + if (it_false_pos != false_pos.end()) { + const std::vector>& false_pos_vec = + it_false_pos->second; + for (const std::pair& fp : false_pos_vec) { + false_pos_data[false_pos_count * 2] = fp.first; + false_pos_data[false_pos_count * 2 + 1] = static_cast(fp.second); + false_pos_count++; + } + } + false_pos_starts.push_back(false_pos_count); + } + + framework::LoD true_pos_lod; + true_pos_lod.emplace_back(true_pos_starts); + framework::LoD false_pos_lod; + false_pos_lod.emplace_back(false_pos_starts); + + output_true_pos.set_lod(true_pos_lod); + output_false_pos.set_lod(false_pos_lod); + return; + } + + void GetInputPos( + const framework::Tensor& input_pos_count, + const framework::LoDTensor& input_true_pos, + const framework::LoDTensor& input_false_pos, + std::map& label_pos_count, + std::map>>& true_pos, + std::map>>& false_pos) const { + constexpr T kEPS = static_cast(1e-6); + int class_number = input_pos_count.dims()[0]; + const int* pos_count_data = input_pos_count.data(); + for (int i = 0; i < class_number; ++i) { + label_pos_count[i] = pos_count_data[i]; + } + + const T* true_pos_data = input_true_pos.data(); + auto true_pos_data_lod = input_true_pos.lod(); + for (int i = 0; i < true_pos_data_lod.size(); ++i) { + for (int j = true_pos_data_lod[0][i]; j < true_pos_data_lod[0][i + 1]; + ++j) { + T score = true_pos_data[j * 2]; + int flag = 1; + if (true_pos_data[j * 2 + 1] < kEPS) flag = 0; + true_pos[i].push_back(std::make_pair(score, flag)); + } + } + const T* false_pos_data = input_false_pos.data(); + auto false_pos_data_lod = input_false_pos.lod(); + for (int i = 0; i < false_pos_data_lod.size(); ++i) { + for (int j = false_pos_data_lod[0][i]; j < false_pos_data_lod[0][i + 1]; + ++j) { + T score = false_pos_data[j * 2]; + int flag = 1; + if (false_pos_data[j * 2 + 1] < kEPS) flag = 0; + false_pos[i].push_back(std::make_pair(score, flag)); + } + } + return; + } + void CalcTrueAndFalsePositive( const std::vector>>& gt_boxes, const std::vector>>>& @@ -283,7 +412,6 @@ class DetectionMAPOpKernel : public framework::OpKernel { size_t num = tp_sum.size(); // Compute Precision. for (size_t i = 0; i < num; ++i) { - // CHECK_LE(tpCumSum[i], labelNumPos); precision.push_back(static_cast(tp_sum[i]) / static_cast(tp_sum[i] + fp_sum[i])); recall.push_back(static_cast(tp_sum[i]) / label_num_pos); diff --git a/python/paddle/v2/fluid/tests/test_detection_map_op.py b/python/paddle/v2/fluid/tests/test_detection_map_op.py index db8012334..ec57ca4ad 100644 --- a/python/paddle/v2/fluid/tests/test_detection_map_op.py +++ b/python/paddle/v2/fluid/tests/test_detection_map_op.py @@ -29,10 +29,24 @@ class TestDetectionMAPOp(OpTest): self.detect = np.array(self.detect).astype('float32') self.mAP = np.array(self.mAP).astype('float32') - self.inputs = { - 'Label': (self.label, self.label_lod), - 'Detection': (self.detect, self.detect_lod) - } + if (len(self.class_pos_count) > 0): + self.class_pos_count = np.array(self.class_pos_count).astype( + 'int32') + self.true_pos = np.array(self.true_pos).astype('float32') + self.false_pos = np.array(self.false_pos).astype('float32') + + self.inputs = { + 'Label': (self.label, self.label_lod), + 'Detection': (self.detect, self.detect_lod), + 'PosCount': self.class_pos_count, + 'TruePos': (self.true_pos, self.true_pos_lod), + 'FalsePos': (self.false_pos, self.false_pos_lod) + } + else: + self.inputs = { + 'Label': (self.label, self.label_lod), + 'Detection': (self.detect, self.detect_lod), + } self.attrs = { 'overlap_threshold': self.overlap_threshold, @@ -40,7 +54,17 @@ class TestDetectionMAPOp(OpTest): 'ap_type': self.ap_type } - self.outputs = {'MAP': self.mAP} + self.out_class_pos_count = np.array(self.out_class_pos_count).astype( + 'int') + self.out_true_pos = np.array(self.out_true_pos).astype('float32') + self.out_false_pos = np.array(self.out_false_pos).astype('float32') + + self.outputs = { + 'MAP': self.mAP, + 'OutPosCount': self.out_class_pos_count, + 'OutTruePos': (self.out_true_pos, self.out_true_pos_lod), + 'OutFalsePos': (self.out_false_pos, self.out_false_pos_lod) + } def init_test_case(self): self.overlap_threshold = 0.3 @@ -67,13 +91,64 @@ class TestDetectionMAPOp(OpTest): [1, 0.2, 1, 0], [2, 0.8, 0, 1], [2, 0.1, 1, 0], [3, 0.2, 0, 1]] + self.class_pos_count = [] + self.true_pos_lod = [[]] + self.true_pos = [[]] + self.false_pos_lod = [[]] + self.false_pos = [[]] + def calc_map(self, tf_pos, tf_pos_lod): mAP = 0.0 count = 0 - class_pos_count = {} - true_pos = {} - false_pos = {} + def get_input_pos(class_pos_count, true_pos, true_pos_lod, false_pos, + false_pos_lod): + class_pos_count_dict = collections.Counter() + true_pos_dict = collections.defaultdict(list) + false_pos_dict = collections.defaultdict(list) + for i, count in enumerate(class_pos_count): + class_pos_count_dict[i] = count + + for i in range(len(true_pos_lod[0]) - 1): + start = true_pos_lod[0][i] + end = true_pos_lod[0][i + 1] + for j in range(start, end): + true_pos_dict[i].append(true_pos[j]) + + for i in range(len(false_pos_lod[0]) - 1): + start = false_pos_lod[0][i] + end = false_pos_lod[0][i + 1] + for j in range(start, end): + false_pos_dict[i].append(false_pos[j]) + + return class_pos_count_dict, true_pos_dict, false_pos_dict + + def get_output_pos(label_count, true_pos, false_pos): + max_label = 0 + for (label, label_pos_num) in label_count.items(): + if max_label < label: + max_label = label + + label_number = max_label + 1 + + out_class_pos_count = [] + out_true_pos_lod = [0] + out_true_pos = [] + out_false_pos_lod = [0] + out_false_pos = [] + + for i in range(label_number): + out_class_pos_count.append([label_count[i]]) + true_pos_list = true_pos[i] + out_true_pos += true_pos_list + out_true_pos_lod.append(len(out_true_pos)) + false_pos_list = false_pos[i] + out_false_pos += false_pos_list + out_false_pos_lod.append(len(out_false_pos)) + + return out_class_pos_count, out_true_pos, [ + out_true_pos_lod + ], out_false_pos, [out_false_pos_lod] def get_accumulation(pos_list): sorted_list = sorted(pos_list, key=lambda pos: pos[0], reverse=True) @@ -84,7 +159,9 @@ class TestDetectionMAPOp(OpTest): accu_list.append(sum) return accu_list - label_count = collections.Counter() + label_count, true_pos, false_pos = get_input_pos( + self.class_pos_count, self.true_pos, self.true_pos_lod, + self.false_pos, self.false_pos_lod) for (label, difficult, xmin, ymin, xmax, ymax) in self.label: if self.evaluate_difficult: label_count[label] += 1 @@ -143,8 +220,10 @@ class TestDetectionMAPOp(OpTest): mAP += average_precisions count += 1 - - if count != 0: mAP /= count + self.out_class_pos_count, self.out_true_pos, self.out_true_pos_lod, self.out_false_pos, self.out_false_pos_lod = get_output_pos( + label_count, true_pos, false_pos) + if count != 0: + mAP /= count return mAP * 100.0 def setUp(self): @@ -174,5 +253,15 @@ class TestDetectionMAPOp11Point(TestDetectionMAPOp): self.ap_type = "11point" +class TestDetectionMAPOpMultiBatch(TestDetectionMAPOp): + def init_test_case(self): + super(TestDetectionMAPOpMultiBatch, self).init_test_case() + self.class_pos_count = [0, 2, 1] + self.true_pos_lod = [[0, 0, 3, 5]] + self.true_pos = [[0.7, 1.], [0.3, 0.], [0.2, 1.], [0.8, 0.], [0.1, 1.]] + self.false_pos_lod = [[0, 0, 3, 5]] + self.false_pos = [[0.7, 0.], [0.3, 1.], [0.2, 0.], [0.8, 1.], [0.1, 0.]] + + if __name__ == '__main__': unittest.main() -- GitLab