def construct(self, box_xy, box_wh, box_confidence, box_probs,
image_shape):
batch_size = F.shape(box_xy)[0]
x = box_xy[:, :, :, :, 0:1]
y = box_xy[:, :, :, :, 1:2]
box_yx = P.Concat(-1)((y, x))
w = box_wh[:, :, :, :, 0:1]
h = box_wh[:, :, :, :, 1:2]
box_hw = P.Concat(-1)((h, w))
new_shape = P.Round()(image_shape *
P.ReduceMin()(self.input_shape / image_shape))
offset = (self.input_shape - new_shape) / 2.0 / self.input_shape
scale = self.input_shape / new_shape
box_yx = (box_yx - offset) * scale
box_hw = box_hw * scale
box_min = box_yx - box_hw / 2.0
box_max = box_yx + box_hw / 2.0
boxes = P.Concat(-1)(
(box_min[:, :, :, :, 0:1], box_min[:, :, :, :, 1:2],
box_max[:, :, :, :, 0:1], box_max[:, :, :, :, 1:2]))
image_scale = P.Tile()(image_shape, (1, 2))
boxes = boxes * image_scale
boxes = F.reshape(boxes, (batch_size, -1, 4))
boxes_scores = box_confidence * box_probs
boxes_scores = F.reshape(boxes_scores,
(batch_size, -1, self.num_classes))
return boxes, boxes_scores
def __init__(self,
num_bits=8,
compute_type=mstype.float32,
clip_value=1.0,
per_channel=False):
super(QuantizeWeightCell, self).__init__()
self.num_bits = num_bits
self.compute_type = compute_type
self.clip_value = clip_value
self.per_channel = per_channel
self.clamp = C.clip_by_value
self.abs = P.Abs()
self.sum = P.ReduceSum()
self.nelement = F.size
self.div = P.Div()
self.cast = P.Cast()
self.max = P.ReduceMax()
self.min = P.ReduceMin()
self.round = P.Round()
('Sum_5', {
'block': P.ReduceSum(keep_dims=True),
'desc_const': [()],
'desc_inputs': [[2, 3, 4]],
'desc_bprop': [[1, 1, 1]]}),
('Sum_6', {
'block': P.ReduceSum(),
'desc_const': [()],
'desc_inputs': [[2, 3, 4]],
'desc_bprop': [[1]]}),
('Sign', {
'block': P.Sign(),
'desc_inputs': [[3]],
'desc_bprop': [[3]]}),
('Round', {
'block': P.Round(),
'desc_inputs': [[3]],
'desc_bprop': [[3]]}),
('Atan2', {
'block': P.Atan2(),
'desc_inputs': [Tensor(np.array([0, 1]).astype(np.float32)),
Tensor(np.array([1, 1]).astype(np.float32))],
'desc_bprop': [[2]]})
]
test_case_nn_ops = [
('BiasAdd', {
'block': P.BiasAdd(),
'desc_inputs': [[1, 3, 3, 3], [3]],
'desc_bprop': [[1, 3, 3, 3]]}),
('BiasAddGrad', {
def __init__(self, strategy1, strategy2):
super().__init__()
self.matmul = P.MatMul().set_strategy(strategy1)
self.round = P.Round().set_strategy(strategy2)
self.matmul2 = P.MatMul().set_strategy(strategy1)
'skip': ['backward']}),
# input is not tensor
('Sign0', {
'block': (P.Sign(), {'exception': TypeError, 'error_keywords': ['Sign']}),
'desc_inputs': [5.0],
'skip': ['backward']}),
# input is Tensor(bool)
('Sign1', {
'block': (P.Sign(), {'exception': TypeError, 'error_keywords': ['Sign']}),
'desc_inputs': [Tensor(np.ones([3, 4]).astype(np.bool_))],
'skip': ['backward']}),
# input is not tensor
('Round0', {
'block': (P.Round(), {'exception': TypeError, 'error_keywords': ['Round']}),
'desc_inputs': [5.0],
'skip': ['backward']}),
# input is Tensor(bool)
('Round1', {
'block': (P.Round(), {'exception': TypeError, 'error_keywords': ['Round']}),
'desc_inputs': [Tensor(np.ones([3, 4]).astype(np.bool_))],
'skip': ['backward']}),
# one input is scalar, and another is Tensor(float32)
('Atan20', {
'block': (P.Atan2(), {'exception': TypeError, 'error_keywords': ['Atan2']}),
'desc_inputs': [5.0, Tensor(np.ones([3, 4]).astype(np.float32))],
'skip': ['backward']}),
# input two tensors, but element types are not same
('Atan21', {
'desc_inputs': [5.0],
'skip': ['backward']
}),
# input is Tensor(bool)
('Sign1', {
'block': (P.Sign(), {
'exception': TypeError,
'error_keywords': ['Sign']
}),
'desc_inputs': [Tensor(np.ones([3, 4]).astype(np.bool_))],
'skip': ['backward']
}),
# input is not tensor
('Round0', {
'block': (P.Round(), {
'exception': TypeError,
'error_keywords': ['Round']
}),
'desc_inputs': [5.0],
'skip': ['backward']
}),
# input is Tensor(bool)
('Round1', {
'block': (P.Round(), {
'exception': TypeError,
'error_keywords': ['Round']
}),
'desc_inputs': [Tensor(np.ones([3, 4]).astype(np.bool_))],
'skip': ['backward']
}),
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):
super(RoundNet, self).__init__()
self.round = P.Round()
