Skip to content

Fix the input dimension for multiclass_nms_op. #8232

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 2 commits into from
Feb 11, 2018
Merged

Fix the input dimension for multiclass_nms_op. #8232

Show file tree
Hide file tree
Changes from all commits
Commits
Show all changes
2 commits
Select commit Hold shift + click to select a range
087de5c
Fix the input dimension for multiclass_nms_op.
qingqing01 Feb 7, 2018
048f9c9
Merge branch 'develop' of http://github.com/paddlepaddle/paddle into …
wangkuiyi Feb 10, 2018
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
29 changes: 19 additions & 10 deletions paddle/fluid/operators/multiclass_nms_op.cc
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -38,22 +38,22 @@ class MultiClassNMSOp : public framework::OperatorWithKernel {
auto box_dims = ctx->GetInputDim("BBoxes");
auto score_dims = ctx->GetInputDim("Scores");

PADDLE_ENFORCE_EQ(box_dims.size(), 2,
"The rank of Input(BBoxes) must be 2.");
PADDLE_ENFORCE_EQ(box_dims.size(), 3,
"The rank of Input(BBoxes) must be 3.");
PADDLE_ENFORCE_EQ(score_dims.size(), 3,
"The rank of Input(Scores) must be 3.");
PADDLE_ENFORCE_EQ(box_dims[1], 4,
PADDLE_ENFORCE_EQ(box_dims[2], 4,
"The 2nd dimension of Input(BBoxes) must be 4, "
"represents the layout of coordinate "
"[xmin, ymin, xmax, ymax]");
PADDLE_ENFORCE_EQ(box_dims[0], score_dims[2],
PADDLE_ENFORCE_EQ(box_dims[1], score_dims[2],
"The 1st dimensiong of Input(BBoxes) must be equal to "
"3rd dimension of Input(Scores), which represents the "
"predicted bboxes.");

// Here the box_dims[0] is not the real dimension of output.
// It will be rewritten in the computing kernel.
ctx->SetOutputDim("Out", {box_dims[0], 6});
ctx->SetOutputDim("Out", {box_dims[1], 6});
}

protected:
Expand Down Expand Up @@ -260,15 +260,20 @@ class MultiClassNMSKernel : public framework::OpKernel<T> {
int64_t batch_size = score_dims[0];
int64_t class_num = score_dims[1];
int64_t predict_dim = score_dims[2];
int64_t box_dim = boxes->dims()[2];

std::vector<std::map<int, std::vector<int>>> all_indices;
std::vector<size_t> batch_starts = {0};
for (int64_t i = 0; i < batch_size; ++i) {
Tensor ins_score = scores->Slice(i, i + 1);
ins_score.Resize({class_num, predict_dim});

Tensor ins_boxes = boxes->Slice(i, i + 1);
ins_boxes.Resize({predict_dim, box_dim});

std::map<int, std::vector<int>> indices;
int num_nmsed_out = 0;
MultiClassNMS(ctx, ins_score, *boxes, indices, num_nmsed_out);
MultiClassNMS(ctx, ins_score, ins_boxes, indices, num_nmsed_out);
all_indices.push_back(indices);
batch_starts.push_back(batch_starts.back() + num_nmsed_out);
}
Expand All @@ -282,11 +287,15 @@ class MultiClassNMSKernel : public framework::OpKernel<T> {
for (int64_t i = 0; i < batch_size; ++i) {
Tensor ins_score = scores->Slice(i, i + 1);
ins_score.Resize({class_num, predict_dim});

Tensor ins_boxes = boxes->Slice(i, i + 1);
ins_boxes.Resize({predict_dim, box_dim});

int64_t s = batch_starts[i];
int64_t e = batch_starts[i + 1];
if (e > s) {
Tensor out = outs->Slice(s, e);
MultiClassOutput(ins_score, *boxes, all_indices[i], &out);
MultiClassOutput(ins_score, ins_boxes, all_indices[i], &out);
}
}
}
Expand All @@ -303,9 +312,9 @@ class MultiClassNMSOpMaker : public framework::OpProtoAndCheckerMaker {
MultiClassNMSOpMaker(OpProto* proto, OpAttrChecker* op_checker)
: OpProtoAndCheckerMaker(proto, op_checker) {
AddInput("BBoxes",
"(Tensor) A 2-D Tensor with shape [M, 4] represents the "
"predicted locations of M bounding bboxes. Each bounding box "
"has four coordinate values and the layout is "
"(Tensor) A 3-D Tensor with shape [N, M, 4] represents the "
"predicted locations of M bounding bboxes, N is the batch size. "
"Each bounding box has four coordinate values and the layout is "
"[xmin, ymin, xmax, ymax].");
AddInput("Scores",
"(Tensor) A 3-D Tensor with shape [N, C, M] represents the "
Expand Down
10 changes: 5 additions & 5 deletions python/paddle/v2/fluid/tests/test_multiclass_nms_op.py
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -137,15 +137,15 @@ def batched_multiclass_nms(boxes, scores, background, score_threshold,
det_outs = []
lod = [0]
for n in range(batch_size):
nmsed_outs, nmsed_num = multiclass_nms(boxes, scores[n], background,
nmsed_outs, nmsed_num = multiclass_nms(boxes[n], scores[n], background,
score_threshold, nms_threshold,
nms_top_k, keep_top_k)
lod.append(lod[-1] + nmsed_num)
if nmsed_num == 0: continue

for c, indices in nmsed_outs.iteritems():
for idx in indices:
xmin, ymin, xmax, ymax = boxes[idx][:]
xmin, ymin, xmax, ymax = boxes[n][idx][:]
det_outs.append([c, scores[n][c][idx], xmin, ymin, xmax, ymax])

return det_outs, lod
Expand Down Expand Up @@ -179,9 +179,9 @@ def softmax(x):
scores = np.reshape(scores, (N, M, C))
scores = np.transpose(scores, (0, 2, 1))

boxes = np.random.random((M, BOX_SIZE)).astype('float32')
boxes[:, 0:2] = boxes[:, 0:2] * 0.5
boxes[:, 2:4] = boxes[:, 2:4] * 0.5 + 0.5
boxes = np.random.random((N, M, BOX_SIZE)).astype('float32')
boxes[:, :, 0:2] = boxes[:, :, 0:2] * 0.5
boxes[:, :, 2:4] = boxes[:, :, 2:4] * 0.5 + 0.5

nmsed_outs, lod = batched_multiclass_nms(boxes, scores, background,
score_threshold, nms_threshold,
Expand Down