Skip to content

P
Paddle

PaddlePaddle / Paddle
1 年多 前同步成功

通知 2302
Star 20931
Fork 5422
P
Paddle
提交 af124dcd 编写于 作者: D dengkaipeng
浏览文件
操作

fix API error

上级 c945ffa7
隐藏空白更改
内联 并排
Showing with 43 addition and 27 deletion
paddle/fluid/API.spec
浏览文件 @ af124dcd
......@@ -324,7 +324,7 @@ paddle.fluid.layers.generate_mask_labels ArgSpec(args=['im_info', 'gt_classes',
paddle.fluid.layers.iou_similarity ArgSpec(args=['x', 'y', 'name'], varargs=None, keywords=None, defaults=(None,))
paddle.fluid.layers.box_coder ArgSpec(args=['prior_box', 'prior_box_var', 'target_box', 'code_type', 'box_normalized', 'name'], varargs=None, keywords=None, defaults=('encode_center_size', True, None))
paddle.fluid.layers.polygon_box_transform ArgSpec(args=['input', 'name'], varargs=None, keywords=None, defaults=(None,))
paddle.fluid.layers.yolov3_loss ArgSpec(args=['x', 'gtbox', 'gtlabel', 'gtscore', 'anchors', 'anchor_mask', 'class_num', 'ignore_thresh', 'downsample', 'label_smooth', 'name'], varargs=None, keywords=None, defaults=(None,))
paddle.fluid.layers.yolov3_loss ArgSpec(args=['x', 'gtbox', 'gtlabel', 'gtscore', 'anchors', 'anchor_mask', 'class_num', 'ignore_thresh', 'downsample', 'use_label_smooth', 'name'], varargs=None, keywords=None, defaults=(True, None,))
paddle.fluid.layers.multiclass_nms ArgSpec(args=['bboxes', 'scores', 'score_threshold', 'nms_top_k', 'keep_top_k', 'nms_threshold', 'normalized', 'nms_eta', 'background_label', 'name'], varargs=None, keywords=None, defaults=(0.3, True, 1.0, 0, None))
paddle.fluid.layers.accuracy ArgSpec(args=['input', 'label', 'k', 'correct', 'total'], varargs=None, keywords=None, defaults=(1, None, None))
paddle.fluid.layers.auc ArgSpec(args=['input', 'label', 'curve', 'num_thresholds', 'topk', 'slide_steps'], varargs=None, keywords=None, defaults=('ROC', 4095, 1, 1))
......
paddle/fluid/operators/yolov3_loss_op.h
浏览文件 @ af124dcd
......@@ -121,13 +121,13 @@ template <typename T>
static void CalcBoxLocationLoss(T* loss, const T* input, Box<T> gt,
std::vector<int> anchors, int an_idx,
int box_idx, int gi, int gj, int grid_size,
int input_size, int stride) {
int input_size, int stride, T score) {
T tx = gt.x * grid_size - gi;
T ty = gt.y * grid_size - gj;
T tw = std::log(gt.w * input_size / anchors[2 * an_idx]);
T th = std::log(gt.h * input_size / anchors[2 * an_idx + 1]);
T scale = 2.0 - gt.w * gt.h;
T scale = (2.0 - gt.w * gt.h) * score;
loss[0] += SCE<T>(input[box_idx], tx) * scale;
loss[0] += SCE<T>(input[box_idx + stride], ty) * scale;
loss[0] += L1Loss<T>(input[box_idx + 2 * stride], tw) * scale;
......@@ -138,13 +138,14 @@ template <typename T>
static void CalcBoxLocationLossGrad(T* input_grad, const T loss, const T* input,
Box<T> gt, std::vector<int> anchors,
int an_idx, int box_idx, int gi, int gj,
int grid_size, int input_size, int stride) {
int grid_size, int input_size, int stride,
T score) {
T tx = gt.x * grid_size - gi;
T ty = gt.y * grid_size - gj;
T tw = std::log(gt.w * input_size / anchors[2 * an_idx]);
T th = std::log(gt.h * input_size / anchors[2 * an_idx + 1]);
T scale = 2.0 - gt.w * gt.h;
T scale = (2.0 - gt.w * gt.h) * score;
input_grad[box_idx] = SCEGrad<T>(input[box_idx], tx) * scale * loss;
input_grad[box_idx + stride] =
SCEGrad<T>(input[box_idx + stride], ty) * scale * loss;
......@@ -157,10 +158,11 @@ static void CalcBoxLocationLossGrad(T* input_grad, const T loss, const T* input,
template <typename T>
static inline void CalcLabelLoss(T* loss, const T* input, const int index,
const int label, const int class_num,
const int stride, const T pos, const T neg) {
const int stride, const T pos, const T neg,
T score) {
for (int i = 0; i < class_num; i++) {
T pred = input[index + i * stride];
loss[0] += SCE<T>(pred, (i == label) ? pos : neg);
loss[0] += SCE<T>(pred, (i == label) ? pos : neg) * score;
}
}
......@@ -168,12 +170,12 @@ template <typename T>
static inline void CalcLabelLossGrad(T* input_grad, const T loss,
const T* input, const int index,
const int label, const int class_num,
const int stride, const T pos,
const T neg) {
const int stride, const T pos, const T neg,
T score) {
for (int i = 0; i < class_num; i++) {
T pred = input[index + i * stride];
input_grad[index + i * stride] =
SCEGrad<T>(pred, (i == label) ? pos : neg) * loss;
SCEGrad<T>(pred, (i == label) ? pos : neg) * score * loss;
}
}
......@@ -187,8 +189,12 @@ static inline void CalcObjnessLoss(T* loss, const T* input, const T* objness,
for (int k = 0; k < h; k++) {
for (int l = 0; l < w; l++) {
T obj = objness[k * w + l];
if (obj > -0.5) {
loss[i] += SCE<T>(input[k * w + l], obj);
if (obj > 1e-5) {
// positive sample: obj = mixup score
loss[i] += SCE<T>(input[k * w + l], 1.0) * obj;
} else if (obj > -0.5) {
// negetive sample: obj = 0
loss[i] += SCE<T>(input[k * w + l], 0.0);
}
}
}
......@@ -209,8 +215,11 @@ static inline void CalcObjnessLossGrad(T* input_grad, const T* loss,
for (int k = 0; k < h; k++) {
for (int l = 0; l < w; l++) {
T obj = objness[k * w + l];
if (obj > -0.5) {
input_grad[k * w + l] = SCEGrad<T>(input[k * w + l], obj) * loss[i];
if (obj > 1e-5) {
input_grad[k * w + l] =
SCEGrad<T>(input[k * w + l], 1.0) * obj * loss[i];
} else if (obj > -0.5) {
input_grad[k * w + l] = SCEGrad<T>(input[k * w + l], 0.0) * loss[i];
}
}
}
......@@ -315,7 +324,7 @@ class Yolov3LossKernel : public framework::OpKernel<T> {
if (best_iou > ignore_thresh) {
int obj_idx = (i * mask_num + j) * stride + k * w + l;
obj_mask_data[obj_idx] = static_cast<T>(-1.0);
obj_mask_data[obj_idx] = static_cast<T>(-1);
}
// TODO(dengkaipeng): all losses should be calculated if best IoU
// is bigger then truth thresh should be calculated here, but
......@@ -357,12 +366,12 @@ class Yolov3LossKernel : public framework::OpKernel<T> {
int mask_idx = GetMaskIndex(anchor_mask, best_n);
gt_match_mask_data[i * b + t] = mask_idx;
if (mask_idx >= 0) {
T score = gt_score_data[i * b + t];
int box_idx = GetEntryIndex(i, mask_idx, gj * w + gi, mask_num,
an_stride, stride, 0);
CalcBoxLocationLoss<T>(loss_data + i, input_data, gt, anchors, best_n,
box_idx, gi, gj, h, input_size, stride);
box_idx, gi, gj, h, input_size, stride, score);
T score = gt_score_data[i * b + t];
int obj_idx = (i * mask_num + mask_idx) * stride + gj * w + gi;
obj_mask_data[obj_idx] = score;
......@@ -370,7 +379,7 @@ class Yolov3LossKernel : public framework::OpKernel<T> {
int label_idx = GetEntryIndex(i, mask_idx, gj * w + gi, mask_num,
an_stride, stride, 5);
CalcLabelLoss<T>(loss_data + i, input_data, label_idx, label,
class_num, stride, label_pos, label_neg);
class_num, stride, label_pos, label_neg, score);
}
}
}
......@@ -387,6 +396,7 @@ class Yolov3LossGradKernel : public framework::OpKernel<T> {
auto* input = ctx.Input<Tensor>("X");
auto* gt_box = ctx.Input<Tensor>("GTBox");
auto* gt_label = ctx.Input<Tensor>("GTLabel");
auto* gt_score = ctx.Input<Tensor>("GTScore");
auto* input_grad = ctx.Output<Tensor>(framework::GradVarName("X"));
auto* loss_grad = ctx.Input<Tensor>(framework::GradVarName("Loss"));
auto* objness_mask = ctx.Input<Tensor>("ObjectnessMask");
......@@ -418,6 +428,7 @@ class Yolov3LossGradKernel : public framework::OpKernel<T> {
const T* input_data = input->data<T>();
const T* gt_box_data = gt_box->data<T>();
const int* gt_label_data = gt_label->data<int>();
const T* gt_score_data = gt_score->data<T>();
const T* loss_grad_data = loss_grad->data<T>();
const T* obj_mask_data = objness_mask->data<T>();
const int* gt_match_mask_data = gt_match_mask->data<int>();
......@@ -429,22 +440,24 @@ class Yolov3LossGradKernel : public framework::OpKernel<T> {
for (int t = 0; t < b; t++) {
int mask_idx = gt_match_mask_data[i * b + t];
if (mask_idx >= 0) {
T score = gt_score_data[i * b + t];
Box<T> gt = GetGtBox(gt_box_data, i, b, t);
int gi = static_cast<int>(gt.x * w);
int gj = static_cast<int>(gt.y * h);
int box_idx = GetEntryIndex(i, mask_idx, gj * w + gi, mask_num,
an_stride, stride, 0);
CalcBoxLocationLossGrad<T>(
input_grad_data, loss_grad_data[i], input_data, gt, anchors,
anchor_mask[mask_idx], box_idx, gi, gj, h, input_size, stride);
CalcBoxLocationLossGrad<T>(input_grad_data, loss_grad_data[i],
input_data, gt, anchors,
anchor_mask[mask_idx], box_idx, gi, gj, h,
input_size, stride, score);
int label = gt_label_data[i * b + t];
int label_idx = GetEntryIndex(i, mask_idx, gj * w + gi, mask_num,
an_stride, stride, 5);
CalcLabelLossGrad<T>(input_grad_data, loss_grad_data[i], input_data,
label_idx, label, class_num, stride, label_pos,
label_neg);
label_neg, score);
}
}
}
......
python/paddle/fluid/layers/detection.py
浏览文件 @ af124dcd
......@@ -482,7 +482,7 @@ def yolov3_loss(x,
raise TypeError("Attr anchor_mask of yolov3_loss must be list or tuple")
if not isinstance(class_num, int):
raise TypeError("Attr class_num of yolov3_loss must be an integer")
if not isinstance(use_label_smooth, int):
if not isinstance(use_label_smooth, bool):
raise TypeError("Attr ues_label_smooth of yolov3 must be a bool value")
if not isinstance(ignore_thresh, float):
raise TypeError(
......
python/paddle/fluid/tests/unittests/test_yolov3_loss_op.py
浏览文件 @ af124dcd
......@@ -142,7 +142,7 @@ def YOLOv3Loss(x, gtbox, gtlabel, gtscore, attrs):
ty = gtbox[i, j, 1] * w - gj
tw = np.log(gtbox[i, j, 2] * input_size / mask_anchors[an_idx][0])
th = np.log(gtbox[i, j, 3] * input_size / mask_anchors[an_idx][1])
scale = 2.0 - gtbox[i, j, 2] * gtbox[i, j, 3]
scale = (2.0 - gtbox[i, j, 2] * gtbox[i, j, 3]) * gtscore[i, j]
loss[i] += sce(x[i, an_idx, gj, gi, 0], tx) * scale
loss[i] += sce(x[i, an_idx, gj, gi, 1], ty) * scale
loss[i] += l1loss(x[i, an_idx, gj, gi, 2], tw) * scale
......@@ -152,11 +152,14 @@ def YOLOv3Loss(x, gtbox, gtlabel, gtscore, attrs):
for label_idx in range(class_num):
loss[i] += sce(x[i, an_idx, gj, gi, 5 + label_idx], label_pos
if label_idx == gtlabel[i, j] else label_neg)
if label_idx == gtlabel[i, j] else
label_neg) * gtscore[i, j]
for j in range(mask_num * h * w):
if objness[i, j] >= 0:
loss[i] += sce(pred_obj[i, j], objness[i, j])
if objness[i, j] > 0:
loss[i] += sce(pred_obj[i, j], 1.0) * objness[i, j]
elif objness[i, j] == 0:
loss[i] += sce(pred_obj[i, j], 0.0)
return (loss, objness.reshape((n, mask_num, h, w)).astype('float32'), \
gt_matches.astype('int32'))
......
Markdown is supported
0% 或 .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑！
想要评论请 注册 或