def __init__(self, config, batch_size, num_bboxes, add_gt_as_proposals):
super(BboxAssignSample, self).__init__()
cfg = config
self.batch_size = batch_size
self.neg_iou_thr = Tensor(cfg.neg_iou_thr, mstype.float16)
self.pos_iou_thr = Tensor(cfg.pos_iou_thr, mstype.float16)
self.min_pos_iou = Tensor(cfg.min_pos_iou, mstype.float16)
self.zero_thr = Tensor(0.0, mstype.float16)
self.num_bboxes = num_bboxes
self.num_gts = cfg.num_gts
self.num_expected_pos = cfg.num_expected_pos
self.num_expected_neg = cfg.num_expected_neg
self.add_gt_as_proposals = add_gt_as_proposals
if self.add_gt_as_proposals:
self.label_inds = Tensor(np.arange(1, self.num_gts + 1))
self.concat = P.Concat(axis=0)
self.max_gt = P.ArgMaxWithValue(axis=0)
self.max_anchor = P.ArgMaxWithValue(axis=1)
self.sum_inds = P.ReduceSum()
self.iou = P.IOU()
self.greaterequal = P.GreaterEqual()
self.greater = P.Greater()
self.select = P.Select()
self.gatherND = P.GatherNd()
self.squeeze = P.Squeeze()
self.cast = P.Cast()
self.logicaland = P.LogicalAnd()
self.less = P.Less()
self.random_choice_with_mask_pos = P.RandomChoiceWithMask(self.num_expected_pos)
self.random_choice_with_mask_neg = P.RandomChoiceWithMask(self.num_expected_neg)
self.reshape = P.Reshape()
self.equal = P.Equal()
self.bounding_box_encode = BoundingBoxEncode()
self.scatterNdUpdate = P.ScatterNdUpdate()
self.scatterNd = P.ScatterNd()
self.logicalnot = P.LogicalNot()
self.tile = P.Tile()
self.zeros_like = P.ZerosLike()
self.assigned_gt_inds = Tensor(np.array(-1 * np.ones(num_bboxes), dtype=np.int32))
self.assigned_gt_zeros = Tensor(np.array(np.zeros(num_bboxes), dtype=np.int32))
self.assigned_gt_ones = Tensor(np.array(np.ones(num_bboxes), dtype=np.int32))
self.assigned_gt_ignores = Tensor(np.array(-1 * np.ones(num_bboxes), dtype=np.int32))
self.assigned_pos_ones = Tensor(np.array(np.ones(self.num_expected_pos), dtype=np.int32))
self.check_neg_mask = Tensor(np.array(np.ones(self.num_expected_neg - self.num_expected_pos), dtype=np.bool))
self.range_pos_size = Tensor(np.arange(self.num_expected_pos).astype(np.float16))
self.check_gt_one = Tensor(np.array(-1 * np.ones((self.num_gts, 4)), dtype=np.float16))
self.check_anchor_two = Tensor(np.array(-2 * np.ones((self.num_bboxes, 4)), dtype=np.float16))
self.print = P.Print()
'desc_inputs': (Tensor(np.ones((2, 3), np.float32)),
Tensor(np.ones((2, 2), np.int32)),
Tensor(np.ones((2,), np.float32))),
'desc_bprop': [[2, 3]]}),
('ScatterNd', {
'block': P.ScatterNd(),
'desc_const': [(3, 3)],
'desc_inputs': (Tensor(np.ones((2, 2), np.int32)),
Tensor(np.ones((2,), np.int32))),
'desc_bprop': [[3, 3]]}),
('SmoothL1Loss', {
'block': P.SmoothL1Loss(),
'desc_inputs': [[256, 4], [256, 4]],
'desc_bprop': [[256, 4]]}),
('IOU', {
'block': P.IOU(),
'desc_inputs': [Tensor(np.ones((256, 4), np.float16)), Tensor(np.ones((128, 4), np.float16))],
'desc_bprop': [[128, 256]]}),
('Summary', {
'block': SummaryNet(),
'desc_inputs': [Tensor(np.array([1.1]).astype(np.float32)),
Tensor(np.array([1.2]).astype(np.float32))],
'skip': ['backward']}),
('ConfusionMulGrad_1', {
'block': P.ConfusionMulGrad(axis = [0], keep_dims = False),
'desc_inputs': [[3, 2], [3, 2], [3, 2]],
'desc_bprop': [[3, 2], [2]],
'skip': ['backward']}),
('ConfusionMulGrad_2', {
'block': P.ConfusionMulGrad(axis = [0], keep_dims = True),
'desc_inputs': [[3, 2], [3, 2], [3, 2]],
def __init__(self, config, batch_size, num_bboxes, add_gt_as_proposals):
super(BboxAssignSampleForRcnn, self).__init__()
cfg = config
self.dtype = np.float32
self.ms_type = mstype.float32
self.batch_size = batch_size
self.neg_iou_thr = cfg.neg_iou_thr_stage2
self.pos_iou_thr = cfg.pos_iou_thr_stage2
self.min_pos_iou = cfg.min_pos_iou_stage2
self.num_gts = cfg.num_gts
self.num_bboxes = num_bboxes
self.num_expected_pos = cfg.num_expected_pos_stage2
self.num_expected_neg = cfg.num_expected_neg_stage2
self.num_expected_total = cfg.num_expected_total_stage2
self.add_gt_as_proposals = add_gt_as_proposals
self.label_inds = Tensor(
np.arange(1, self.num_gts + 1).astype(np.int32))
self.add_gt_as_proposals_valid = Tensor(
np.full(self.num_gts, self.add_gt_as_proposals, dtype=np.int32))
self.concat = P.Concat(axis=0)
self.max_gt = P.ArgMaxWithValue(axis=0)
self.max_anchor = P.ArgMaxWithValue(axis=1)
self.sum_inds = P.ReduceSum()
self.iou = P.IOU()
self.greaterequal = P.GreaterEqual()
self.greater = P.Greater()
self.select = P.Select()
self.gatherND = P.GatherNd()
self.squeeze = P.Squeeze()
self.cast = P.Cast()
self.logicaland = P.LogicalAnd()
self.less = P.Less()
self.random_choice_with_mask_pos = P.RandomChoiceWithMask(
self.num_expected_pos)
self.random_choice_with_mask_neg = P.RandomChoiceWithMask(
self.num_expected_neg)
self.reshape = P.Reshape()
self.equal = P.Equal()
self.bounding_box_encode = P.BoundingBoxEncode(means=(0.0, 0.0, 0.0,
0.0),
stds=(0.1, 0.1, 0.2,
0.2))
self.concat_axis1 = P.Concat(axis=1)
self.logicalnot = P.LogicalNot()
self.tile = P.Tile()
# Check
self.check_gt_one = Tensor(
np.full((self.num_gts, 4), -1, dtype=self.dtype))
self.check_anchor_two = Tensor(
np.full((self.num_bboxes, 4), -2, dtype=self.dtype))
# Init tensor
self.assigned_gt_inds = Tensor(np.full(num_bboxes, -1, dtype=np.int32))
self.assigned_gt_zeros = Tensor(
np.array(np.zeros(num_bboxes), dtype=np.int32))
self.assigned_gt_ones = Tensor(
np.array(np.ones(num_bboxes), dtype=np.int32))
self.assigned_gt_ignores = Tensor(
np.full(num_bboxes, -1, dtype=np.int32))
self.assigned_pos_ones = Tensor(
np.array(np.ones(self.num_expected_pos), dtype=np.int32))
self.gt_ignores = Tensor(np.full(self.num_gts, -1, dtype=np.int32))
self.range_pos_size = Tensor(
np.arange(self.num_expected_pos).astype(self.dtype))
self.check_neg_mask = Tensor(
np.array(np.ones(self.num_expected_neg - self.num_expected_pos),
dtype=np.bool))
self.bboxs_neg_mask = Tensor(
np.zeros((self.num_expected_neg, 4), dtype=self.dtype))
self.labels_neg_mask = Tensor(
np.array(np.zeros(self.num_expected_neg), dtype=np.uint8))
self.reshape_shape_pos = (self.num_expected_pos, 1)
self.reshape_shape_neg = (self.num_expected_neg, 1)
self.scalar_zero = Tensor(0.0, dtype=self.ms_type)
self.scalar_neg_iou_thr = Tensor(self.neg_iou_thr, dtype=self.ms_type)
self.scalar_pos_iou_thr = Tensor(self.pos_iou_thr, dtype=self.ms_type)
self.scalar_min_pos_iou = Tensor(self.min_pos_iou, dtype=self.ms_type)
('ScatterNd', {
'block':
P.ScatterNd(),
'desc_const': [(3, 3)],
'desc_inputs': (Tensor(np.ones(
(2, 2), np.int32)), Tensor(np.ones((2, ), np.int32))),
'desc_bprop': [[3, 3]]
}),
('SmoothL1Loss', {
'block': P.SmoothL1Loss(),
'desc_inputs': [[256, 4], [256, 4]],
'desc_bprop': [[256, 4]]
}),
('IOU', {
'block':
P.IOU(),
'desc_inputs': [
Tensor(np.ones((256, 4), np.float16)),
Tensor(np.ones((128, 4), np.float16))
],
'desc_bprop': [[128, 256]]
}),
('Summary', {
'block':
SummaryNet(),
'desc_inputs': [
Tensor(np.array([1.1]).astype(np.float32)),
Tensor(np.array([1.2]).astype(np.float32))
],
'skip': ['backward']
}),
def __init__(self, num_classes, anchors, anchors_mask, reduction=32, seen=0, coord_scale=1.0, no_object_scale=1.0,
object_scale=1.0, class_scale=1.0, thresh=0.5, head_idx=0.0):
super(YoloLoss, self).__init__()
self.num_classes = num_classes
self.num_anchors = len(anchors_mask)
self.anchor_step = len(anchors[0]) # each scale has step anchors
self.anchors = np.array(anchors, dtype=np.float32) / reduction # scale every anchor for every scale
self.tensor_anchors = Tensor(self.anchors, mstype.float32)
self.anchors_mask = anchors_mask
anchors_w = []
anchors_h = []
for i in range(len(anchors_mask)):
anchors_w.append(self.anchors[self.anchors_mask[i]][0])
anchors_h.append(self.anchors[self.anchors_mask[i]][1])
self.anchors_w = Tensor(np.array(anchors_w).reshape(len(self.anchors_mask), 1))
self.anchors_h = Tensor(np.array(anchors_h).reshape(len(self.anchors_mask), 1))
self.reduction = reduction
self.seen = seen
self.head_idx = head_idx
self.zero = Tensor(0)
self.coord_scale = coord_scale
self.no_object_scale = no_object_scale
self.object_scale = object_scale
self.class_scale = class_scale
self.thresh = thresh
self.info = {'avg_iou': 0, 'class': 0, 'obj': 0, 'no_obj': 0,
'recall50': 0, 'recall75': 0, 'obj_cur': 0, 'obj_all': 0,
'coord_xy': 0, 'coord_wh': 0}
self.shape = P.Shape()
self.reshape = P.Reshape()
self.sigmoid = P.Sigmoid()
self.zeros_like = P.ZerosLike()
self.concat0 = P.Concat(0)
self.concat0_2 = P.Concat(0)
self.concat0_3 = P.Concat(0)
self.concat0_4 = P.Concat(0)
self.concat1 = P.Concat(1)
self.concat1_2 = P.Concat(1)
self.concat1_3 = P.Concat(1)
self.concat1_4 = P.Concat(1)
self.concat2 = P.Concat(2)
self.concat2_2 = P.Concat(2)
self.concat2_3 = P.Concat(2)
self.concat2_4 = P.Concat(2)
self.tile = P.Tile()
self.transpose = P.Transpose()
self.cast = P.Cast()
self.exp = P.Exp()
self.sum = P.ReduceSum()
self.smooth_l1_loss = P.SmoothL1Loss()
self.bce = P.SigmoidCrossEntropyWithLogits()
self.ce = P.SoftmaxCrossEntropyWithLogits()
self.pt_linspace = PtLinspace()
self.one_hot = nn.OneHot(-1, self.num_classes, 1.0, 0.0)
self.squeeze_2 = P.Squeeze(2)
self.reduce_sum = P.ReduceSum()
self.select = P.Select()
self.iou = P.IOU()
def __init__(self, config, batch_size, num_bboxes, add_gt_as_proposals):
super(BboxAssignSampleForRcnn, self).__init__()
cfg = config
self.batch_size = batch_size
self.neg_iou_thr = cfg.neg_iou_thr_stage2
self.pos_iou_thr = cfg.pos_iou_thr_stage2
self.min_pos_iou = cfg.min_pos_iou_stage2
self.num_gts = cfg.num_gts
self.num_bboxes = num_bboxes
self.num_expected_pos = cfg.num_expected_pos_stage2
self.num_expected_neg = cfg.num_expected_neg_stage2
self.num_expected_total = cfg.num_expected_total_stage2
self.add_gt_as_proposals = add_gt_as_proposals
self.label_inds = Tensor(
np.arange(1, self.num_gts + 1).astype(np.int32))
self.add_gt_as_proposals_valid = Tensor(
np.array(self.add_gt_as_proposals * np.ones(self.num_gts),
dtype=np.int32))
self.concat = P.Concat(axis=0)
self.max_gt = P.ArgMaxWithValue(axis=0)
self.max_anchor = P.ArgMaxWithValue(axis=1)
self.sum_inds = P.ReduceSum()
self.iou = P.IOU()
self.greaterequal = P.GreaterEqual()
self.greater = P.Greater()
self.select = P.Select()
self.gatherND = P.GatherNd()
self.squeeze = P.Squeeze()
self.cast = P.Cast()
self.logicaland = P.LogicalAnd()
self.less = P.Less()
self.random_choice_with_mask_pos = P.RandomChoiceWithMask(
self.num_expected_pos)
self.random_choice_with_mask_neg = P.RandomChoiceWithMask(
self.num_expected_neg)
self.reshape = P.Reshape()
self.equal = P.Equal()
self.bounding_box_encode = P.BoundingBoxEncode(means=(0.0, 0.0, 0.0,
0.0),
stds=(0.1, 0.1, 0.2,
0.2))
self.concat_axis1 = P.Concat(axis=1)
self.logicalnot = P.LogicalNot()
self.tile = P.Tile()
# Check
self.check_gt_one = Tensor(
np.array(-1 * np.ones((self.num_gts, 4)), dtype=np.float16))
self.check_anchor_two = Tensor(
np.array(-2 * np.ones((self.num_bboxes, 4)), dtype=np.float16))
# Init tensor
self.assigned_gt_inds = Tensor(
np.array(-1 * np.ones(num_bboxes), dtype=np.int32))
self.assigned_gt_zeros = Tensor(
np.array(np.zeros(num_bboxes), dtype=np.int32))
self.assigned_gt_ones = Tensor(
np.array(np.ones(num_bboxes), dtype=np.int32))
self.assigned_gt_ignores = Tensor(
np.array(-1 * np.ones(num_bboxes), dtype=np.int32))
self.assigned_pos_ones = Tensor(
np.array(np.ones(self.num_expected_pos), dtype=np.int32))
self.gt_ignores = Tensor(
np.array(-1 * np.ones(self.num_gts), dtype=np.int32))
self.range_pos_size = Tensor(
np.arange(self.num_expected_pos).astype(np.float16))
self.check_neg_mask = Tensor(
np.array(np.ones(self.num_expected_neg - self.num_expected_pos),
dtype=np.bool))
self.bboxs_neg_mask = Tensor(
np.zeros((self.num_expected_neg, 4), dtype=np.float16))
self.labels_neg_mask = Tensor(
np.array(np.zeros(self.num_expected_neg), dtype=np.uint8))
self.reshape_shape_pos = (self.num_expected_pos, 1)
self.reshape_shape_neg = (self.num_expected_neg, 1)
self.scalar_zero = Tensor(0.0, dtype=mstype.float16)
self.scalar_neg_iou_thr = Tensor(self.neg_iou_thr,
dtype=mstype.float16)
self.scalar_pos_iou_thr = Tensor(self.pos_iou_thr,
dtype=mstype.float16)
self.scalar_min_pos_iou = Tensor(self.min_pos_iou,
dtype=mstype.float16)
self.expand_dims = P.ExpandDims()
self.split = P.Split(axis=1, output_num=4)
self.concat_last_axis = P.Concat(axis=-1)
self.round = P.Round()
self.image_h_w = Tensor(
[cfg.img_height, cfg.img_width, cfg.img_height, cfg.img_width],
dtype=mstype.float16)
self.range = nn.Range(start=0, limit=cfg.num_expected_pos_stage2)
self.crop_and_resize = P.CropAndResize(method="bilinear_v2")
self.mask_shape = (cfg.mask_shape[0], cfg.mask_shape[1])
self.squeeze_mask_last = P.Squeeze(axis=-1)
def __init__(self, mode):
super(NetIOU, self).__init__()
self.encode = P.IOU(mode=mode)
