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

Fix bug in detection_output and mAP calculation in SSD. (#8985)

Browse Source 
* Clipping bbox in the mAP evaluator calculation.

* Fix bug in detection_output and mAP calculation in SSD.

* Fix bug in detection.py.

* Fix bug in test_detection_map_op.py.
shanyi15-patch-2
qingqing01 7 years ago committed by GitHub
parent e4ce4795dc
commit b3d26cd3ad
No known key found for this signature in database
GPG Key ID: 4AEE18F83AFDEB23
5 changed files with 50 additions and 61 deletions
Show Stats Download Patch File Download Diff File

10
paddle/fluid/operators/detection_map_op.h
Unescape View File

@ -273,7 +273,6 @@ class DetectionMAPOpKernel : public framework::OpKernel<T> {
std::map<int, std::vector<std::pair<T, int>>>& true_pos,
std::map<int, std::vector<std::pair<T, int>>>& false_pos,
const int class_num) const {
constexpr T kEPS = static_cast<T>(1e-6);
const int* pos_count_data = input_pos_count.data<int>();
for (int i = 0; i < class_num; ++i) {
label_pos_count[i] = pos_count_data[i];
@ -282,12 +281,11 @@ class DetectionMAPOpKernel : public framework::OpKernel<T> {
auto SetData = [](const framework::LoDTensor& pos_tensor,
std::map<int, std::vector<std::pair<T, int>>>& pos) {
const T* pos_data = pos_tensor.data<T>();
auto pos_data_lod = pos_tensor.lod();
for (size_t i = 0; i < pos_data_lod.size(); ++i) {
for (size_t j = pos_data_lod[0][i]; j < pos_data_lod[0][i + 1]; ++j) {
auto pos_data_lod = pos_tensor.lod()[0];
for (size_t i = 0; i < pos_data_lod.size() - 1; ++i) {
for (size_t j = pos_data_lod[i]; j < pos_data_lod[i + 1]; ++j) {
T score = pos_data[j * 2];
int flag = 1;
if (pos_data[j * 2 + 1] < kEPS) flag = 0;
int flag = pos_data[j * 2 + 1];
pos[i].push_back(std::make_pair(score, flag));
}
}

3
paddle/fluid/operators/prior_box_op.cc
Unescape View File

@ -111,7 +111,8 @@ class PriorBoxOpMaker : public framework::OpProtoAndCheckerMaker {
});
AddAttr<std::vector<float>>(
"max_sizes",
"(vector<float>) List of max sizes of generated prior boxes.");
"(vector<float>) List of max sizes of generated prior boxes.")
.SetDefault(std::vector<float>{});
AddAttr<std::vector<float>>(
"aspect_ratios",
"(vector<float>) List of aspect ratios of generated prior boxes.");

45
paddle/fluid/operators/prior_box_op.h
Unescape View File

@ -97,9 +97,6 @@ class PriorBoxOpKernel : public framework::OpKernel<T> {
boxes->mutable_data<T>(ctx.GetPlace());
vars->mutable_data<T>(ctx.GetPlace());
T inv_img_width = 1.0 / img_width;
T inv_img_height = 1.0 / img_height;
auto e_boxes = framework::EigenTensor<T, 4>::From(*boxes);
for (int h = 0; h < feature_height; ++h) {
for (int w = 0; w < feature_width; ++w) {
@ -110,36 +107,30 @@ class PriorBoxOpKernel : public framework::OpKernel<T> {
for (size_t s = 0; s < min_sizes.size(); ++s) {
auto min_size = min_sizes[s];
// first prior: aspect_ratio = 1, size = min_size
box_width = box_height = min_size;
box_width = box_height = min_size / 2.;
// xmin
e_boxes(h, w, idx, 0) = (center_x - box_width * 0.5) * inv_img_width;
e_boxes(h, w, idx, 0) = (center_x - box_width) / img_width;
// ymin
e_boxes(h, w, idx, 1) =
(center_y - box_height * 0.5) * inv_img_height;
e_boxes(h, w, idx, 1) = (center_y - box_height) / img_height;
// xmax
e_boxes(h, w, idx, 2) = (center_x + box_width * 0.5) * inv_img_width;
e_boxes(h, w, idx, 2) = (center_x + box_width) / img_width;
// ymax
e_boxes(h, w, idx, 3) =
(center_y + box_height * 0.5) * inv_img_height;
e_boxes(h, w, idx, 3) = (center_y + box_height) / img_height;
idx++;
if (max_sizes.size() > 0) {
auto max_size = max_sizes[s];
// second prior: aspect_ratio = 1,
// size = sqrt(min_size * max_size)
box_width = box_height = sqrt(min_size * max_size);
box_width = box_height = sqrt(min_size * max_size) / 2.;
// xmin
e_boxes(h, w, idx, 0) =
(center_x - box_width * 0.5) * inv_img_width;
e_boxes(h, w, idx, 0) = (center_x - box_width) / img_width;
// ymin
e_boxes(h, w, idx, 1) =
(center_y - box_height * 0.5) * inv_img_height;
e_boxes(h, w, idx, 1) = (center_y - box_height) / img_height;
// xmax
e_boxes(h, w, idx, 2) =
(center_x + box_width * 0.5) * inv_img_width;
e_boxes(h, w, idx, 2) = (center_x + box_width) / img_width;
// ymax
e_boxes(h, w, idx, 3) =
(center_y + box_height * 0.5) * inv_img_height;
e_boxes(h, w, idx, 3) = (center_y + box_height) / img_height;
idx++;
}
@ -149,20 +140,16 @@ class PriorBoxOpKernel : public framework::OpKernel<T> {
if (fabs(ar - 1.) < 1e-6) {
continue;
}
box_width = min_size * sqrt(ar);
box_height = min_size / sqrt(ar);
box_width = min_size * sqrt(ar) / 2.;
box_height = min_size / sqrt(ar) / 2.;
// xmin
e_boxes(h, w, idx, 0) =
(center_x - box_width * 0.5) * inv_img_width;
e_boxes(h, w, idx, 0) = (center_x - box_width) / img_width;
// ymin
e_boxes(h, w, idx, 1) =
(center_y - box_height * 0.5) * inv_img_height;
e_boxes(h, w, idx, 1) = (center_y - box_height) / img_height;
// xmax
e_boxes(h, w, idx, 2) =
(center_x + box_width * 0.5) * inv_img_width;
e_boxes(h, w, idx, 2) = (center_x + box_width) / img_width;
// ymax
e_boxes(h, w, idx, 3) =
(center_y + box_height * 0.5) * inv_img_height;
e_boxes(h, w, idx, 3) = (center_y + box_height) / img_height;
idx++;
}
}

51
python/paddle/fluid/layers/detection.py
Unescape View File

@ -130,8 +130,13 @@ def detection_output(loc,
target_box=loc,
code_type='decode_center_size')
nmsed_outs = helper.create_tmp_variable(dtype=decoded_box.dtype)
old_shape = scores.shape
scores = ops.reshape(x=scores, shape=(-1, old_shape[-1]))
scores = ops.softmax(x=scores)
scores = ops.reshape(x=scores, shape=old_shape)
scores = nn.transpose(scores, perm=[0, 2, 1])
nmsed_outs = helper.create_tmp_variable(dtype=decoded_box.dtype)
helper.append_op(
type="multiclass_nms",
inputs={'Scores': scores,
@ -562,16 +567,16 @@ def multi_box_head(inputs,
base_size,
num_classes,
aspect_ratios,
min_ratio,
max_ratio,
min_ratio=None,
max_ratio=None,
min_sizes=None,
max_sizes=None,
steps=None,
step_w=None,
step_h=None,
offset=0.5,
variance=[0.1, 0.1, 0.1, 0.1],
flip=False,
variance=[0.1, 0.1, 0.2, 0.2],
flip=True,
clip=False,
kernel_size=1,
pad=0,
@ -614,7 +619,7 @@ def multi_box_head(inputs,
the inputs[i] will be automatically calculated. Default: None.
offset(float): Prior boxes center offset. Default: 0.5
variance(list|tuple): the variances to be encoded in prior boxes.
Default:[0.1, 0.1, 0.1, 0.1].
Default:[0.1, 0.1, 0.2, 0.2].
flip(bool): Whether to flip aspect ratios. Default:False.
clip(bool): Whether to clip out-of-boundary boxes. Default: False.
kernel_size(int): The kernel size of conv2d. Default: 1.
@ -668,6 +673,19 @@ def multi_box_head(inputs,
helper = LayerHelper("prior_box", **locals())
dtype = helper.input_dtype()
attrs = {
'min_sizes': min_sizes,
'aspect_ratios': aspect_ratios,
'variances': variance,
'flip': flip,
'clip': clip,
'step_w': step_w,
'step_h': step_h,
'offset': offset
}
if len(max_sizes) > 0 and max_sizes[0] > 0:
attrs['max_sizes'] = max_sizes
box = helper.create_tmp_variable(dtype)
var = helper.create_tmp_variable(dtype)
helper.append_op(
@ -676,17 +694,7 @@ def multi_box_head(inputs,
"Image": image},
outputs={"Boxes": box,
"Variances": var},
attrs={
'min_sizes': min_sizes,
'max_sizes': max_sizes,
'aspect_ratios': aspect_ratios,
'variances': variance,
'flip': flip,
'clip': clip,
'step_w': step_w,
'step_h': step_h,
'offset': offset
})
attrs=attrs, )
return box, var
def _reshape_with_axis_(input, axis=1):
@ -714,7 +722,7 @@ def multi_box_head(inputs,
if num_layer <= 2:
assert min_sizes is not None and max_sizes is not None
assert len(min_sizes) == num_layer and len(max_sizes) == num_layer
else:
elif min_sizes is None and max_sizes is None:
min_sizes = []
max_sizes = []
step = int(math.floor(((max_ratio - min_ratio)) / (num_layer - 2)))
@ -759,9 +767,6 @@ def multi_box_head(inputs,
min_size = [min_size]
if not _is_list_or_tuple_(max_size):
max_size = [max_size]
if not (len(max_size) == len(min_size)):
raise ValueError(
'the length of max_size and min_size should be equal.')
aspect_ratio = []
if aspect_ratios is not None:
@ -779,7 +784,7 @@ def multi_box_head(inputs,
num_boxes = box.shape[2]
# get box_loc
# get loc
num_loc_output = num_boxes * 4
mbox_loc = nn.conv2d(
input=input,
@ -796,7 +801,7 @@ def multi_box_head(inputs,
mbox_loc_flatten = ops.reshape(mbox_loc, shape=new_shape)
mbox_locs.append(mbox_loc_flatten)
# get conf_loc
# get conf
num_conf_output = num_boxes * num_classes
conf_loc = nn.conv2d(
input=input,

2
python/paddle/fluid/tests/unittests/test_detection_map_op.py
Unescape View File

@ -166,8 +166,6 @@ class TestDetectionMAPOp(OpTest):
elif not difficult:
label_count[label] += 1
true_pos = collections.defaultdict(list)
false_pos = collections.defaultdict(list)
for (label, score, tp, fp) in tf_pos:
true_pos[label].append([score, tp])
false_pos[label].append([score, fp])

Write Preview
Loading…
Cancel
Save