提交 6c5a5d07 编写于 作者: D dengkaipeng

format code. test=develop

上级 e7e4f084
...@@ -324,7 +324,7 @@ paddle.fluid.layers.generate_mask_labels ArgSpec(args=['im_info', 'gt_classes', ...@@ -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.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.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.polygon_box_transform ArgSpec(args=['input', 'name'], varargs=None, keywords=None, defaults=(None,))
paddle.fluid.layers.yolov3_loss ArgSpec(args=['x', 'gtbox', 'gtlabel', 'anchors', 'class_num', 'ignore_thresh', 'input_size', 'name'], varargs=None, keywords=None, defaults=(None,)) paddle.fluid.layers.yolov3_loss ArgSpec(args=['x', 'gtbox', 'gtlabel', 'anchors', 'anchor_mask', 'class_num', 'ignore_thresh', 'downsample', 'name'], varargs=None, keywords=None, defaults=(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.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.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.layers.auc ArgSpec(args=['input', 'label', 'curve', 'num_thresholds', 'topk', 'slide_steps'], varargs=None, keywords=None, defaults=('ROC', 4095, 1, 1))
......
...@@ -22,32 +22,6 @@ from op_test import OpTest ...@@ -22,32 +22,6 @@ from op_test import OpTest
from paddle.fluid import core from paddle.fluid import core
# def l1loss(x, y, weight):
# n = x.shape[0]
# x = x.reshape((n, -1))
# y = y.reshape((n, -1))
# weight = weight.reshape((n, -1))
# return (np.abs(y - x) * weight).sum(axis=1)
#
#
# def mse(x, y, weight):
# n = x.shape[0]
# x = x.reshape((n, -1))
# y = y.reshape((n, -1))
# weight = weight.reshape((n, -1))
# return ((y - x)**2 * weight).sum(axis=1)
#
#
# def sce(x, label, weight):
# n = x.shape[0]
# x = x.reshape((n, -1))
# label = label.reshape((n, -1))
# weight = weight.reshape((n, -1))
# sigmoid_x = expit(x)
# term1 = label * np.log(sigmoid_x)
# term2 = (1.0 - label) * np.log(1.0 - sigmoid_x)
# return ((-term1 - term2) * weight).sum(axis=1)
def l1loss(x, y): def l1loss(x, y):
return abs(x - y) return abs(x - y)
...@@ -60,116 +34,6 @@ def sce(x, label): ...@@ -60,116 +34,6 @@ def sce(x, label):
return -term1 - term2 return -term1 - term2
def box_iou(box1, box2):
b1_x1 = box1[0] - box1[2] / 2
b1_x2 = box1[0] + box1[2] / 2
b1_y1 = box1[1] - box1[3] / 2
b1_y2 = box1[1] + box1[3] / 2
b2_x1 = box2[0] - box2[2] / 2
b2_x2 = box2[0] + box2[2] / 2
b2_y1 = box2[1] - box2[3] / 2
b2_y2 = box2[1] + box2[3] / 2
b1_area = (b1_x2 - b1_x1) * (b1_y2 - b1_y1)
b2_area = (b2_x2 - b2_x1) * (b2_y2 - b2_y1)
inter_rect_x1 = max(b1_x1, b2_x1)
inter_rect_y1 = max(b1_y1, b2_y1)
inter_rect_x2 = min(b1_x2, b2_x2)
inter_rect_y2 = min(b1_y2, b2_y2)
inter_area = max(inter_rect_x2 - inter_rect_x1, 0) * max(
inter_rect_y2 - inter_rect_y1, 0)
return inter_area / (b1_area + b2_area + inter_area)
def build_target(gtboxes, gtlabel, attrs, grid_size):
n, b, _ = gtboxes.shape
ignore_thresh = attrs["ignore_thresh"]
anchors = attrs["anchors"]
class_num = attrs["class_num"]
input_size = attrs["input_size"]
an_num = len(anchors) // 2
conf_mask = np.ones((n, an_num, grid_size, grid_size)).astype('float32')
obj_mask = np.zeros((n, an_num, grid_size, grid_size)).astype('float32')
tx = np.zeros((n, an_num, grid_size, grid_size)).astype('float32')
ty = np.zeros((n, an_num, grid_size, grid_size)).astype('float32')
tw = np.zeros((n, an_num, grid_size, grid_size)).astype('float32')
th = np.zeros((n, an_num, grid_size, grid_size)).astype('float32')
tweight = np.zeros((n, an_num, grid_size, grid_size)).astype('float32')
tconf = np.zeros((n, an_num, grid_size, grid_size)).astype('float32')
tcls = np.zeros(
(n, an_num, grid_size, grid_size, class_num)).astype('float32')
for i in range(n):
for j in range(b):
if gtboxes[i, j, :].sum() == 0:
continue
gt_label = gtlabel[i, j]
gx = gtboxes[i, j, 0] * grid_size
gy = gtboxes[i, j, 1] * grid_size
gw = gtboxes[i, j, 2] * input_size
gh = gtboxes[i, j, 3] * input_size
gi = int(gx)
gj = int(gy)
gtbox = [0, 0, gw, gh]
max_iou = 0
for k in range(an_num):
anchor_box = [0, 0, anchors[2 * k], anchors[2 * k + 1]]
iou = box_iou(gtbox, anchor_box)
if iou > max_iou:
max_iou = iou
best_an_index = k
if iou > ignore_thresh:
conf_mask[i, best_an_index, gj, gi] = 0
conf_mask[i, best_an_index, gj, gi] = 1
obj_mask[i, best_an_index, gj, gi] = 1
tx[i, best_an_index, gj, gi] = gx - gi
ty[i, best_an_index, gj, gi] = gy - gj
tw[i, best_an_index, gj, gi] = np.log(gw / anchors[2 *
best_an_index])
th[i, best_an_index, gj, gi] = np.log(
gh / anchors[2 * best_an_index + 1])
tweight[i, best_an_index, gj, gi] = 2.0 - gtboxes[
i, j, 2] * gtboxes[i, j, 3]
tconf[i, best_an_index, gj, gi] = 1
tcls[i, best_an_index, gj, gi, gt_label] = 1
return (tx, ty, tw, th, tweight, tconf, tcls, conf_mask, obj_mask)
def YoloV3Loss(x, gtbox, gtlabel, attrs):
n, c, h, w = x.shape
an_num = len(attrs['anchors']) // 2
class_num = attrs["class_num"]
x = x.reshape((n, an_num, 5 + class_num, h, w)).transpose((0, 1, 3, 4, 2))
pred_x = x[:, :, :, :, 0]
pred_y = x[:, :, :, :, 1]
pred_w = x[:, :, :, :, 2]
pred_h = x[:, :, :, :, 3]
pred_conf = x[:, :, :, :, 4]
pred_cls = x[:, :, :, :, 5:]
tx, ty, tw, th, tweight, tconf, tcls, conf_mask, obj_mask = build_target(
gtbox, gtlabel, attrs, x.shape[2])
obj_weight = obj_mask * tweight
obj_mask_expand = np.tile(
np.expand_dims(obj_mask, 4), (1, 1, 1, 1, int(attrs['class_num'])))
loss_x = sce(pred_x, tx, obj_weight)
loss_y = sce(pred_y, ty, obj_weight)
loss_w = l1loss(pred_w, tw, obj_weight)
loss_h = l1loss(pred_h, th, obj_weight)
loss_obj = sce(pred_conf, tconf, conf_mask)
loss_class = sce(pred_cls, tcls, obj_mask_expand)
return loss_x + loss_y + loss_w + loss_h + loss_obj + loss_class
def sigmoid(x): def sigmoid(x):
return 1.0 / (1.0 + np.exp(-1.0 * x)) return 1.0 / (1.0 + np.exp(-1.0 * x))
...@@ -291,8 +155,10 @@ class TestYolov3LossOp(OpTest): ...@@ -291,8 +155,10 @@ class TestYolov3LossOp(OpTest):
self.op_type = 'yolov3_loss' self.op_type = 'yolov3_loss'
x = logit(np.random.uniform(0, 1, self.x_shape).astype('float32')) x = logit(np.random.uniform(0, 1, self.x_shape).astype('float32'))
gtbox = np.random.random(size=self.gtbox_shape).astype('float32') gtbox = np.random.random(size=self.gtbox_shape).astype('float32')
gtlabel = np.random.randint(0, self.class_num, gtlabel = np.random.randint(0, self.class_num, self.gtbox_shape[:2])
self.gtbox_shape[:2]).astype('int32') gtmask = np.random.randint(0, 2, self.gtbox_shape[:2])
gtbox = gtbox * gtmask[:, :, np.newaxis]
gtlabel = gtlabel * gtmask
self.attrs = { self.attrs = {
"anchors": self.anchors, "anchors": self.anchors,
...@@ -302,7 +168,11 @@ class TestYolov3LossOp(OpTest): ...@@ -302,7 +168,11 @@ class TestYolov3LossOp(OpTest):
"downsample": self.downsample, "downsample": self.downsample,
} }
self.inputs = {'X': x, 'GTBox': gtbox, 'GTLabel': gtlabel} self.inputs = {
'X': x,
'GTBox': gtbox.astype('float32'),
'GTLabel': gtlabel.astype('int32')
}
self.outputs = {'Loss': YOLOv3Loss(x, gtbox, gtlabel, self.attrs)} self.outputs = {'Loss': YOLOv3Loss(x, gtbox, gtlabel, self.attrs)}
def test_check_output(self): def test_check_output(self):
......
Markdown is supported
0% .
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