#
# http://www.apache.org/licenses/LICENSE-2.0
#
# Unless required by applicable law or agreed to in writing, software
# distributed under the License is distributed on an "AS IS" BASIS,
# WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
# See the License for the specific language governing permissions and
# limitations under the License.
# ============================================================================
from mindspore.ops import operations as P
from mindspore.ops import Primitive
select = P.Select()
maximum = P.Maximum()
minimum = P.Minimum()
greater = P.Greater()
real_div = P.RealDiv()
mul = P.Mul()
sub = P.Sub()
lamb_update_with_lr = Primitive('LambUpdateWithLR')
make_tuple = Primitive('make_tuple')
tuple_getitem = Primitive('tuple_getitem')
class FnDict:
def __init__(self):
self.fnDict = {}
def __call__(self, fn):
self.fnDict[fn.__name__] = fn
'desc_bprop': [[1, 512]]
}),
('LogicalNot', {
'block': P.LogicalNot(),
'desc_inputs': [convert([256], np.bool_)],
'desc_bprop': [convert([256], np.bool_)]
}),
('Equal', {
'block': P.Equal(),
'desc_inputs':
[convert([256], np.float16),
convert([256], np.float16)],
'desc_bprop': [convert([256], np.bool_)]
}),
('Greater', {
'block': P.Greater(),
'desc_inputs':
[convert([256], np.float16),
convert([256], np.float16)],
'desc_bprop': [convert([256], np.bool_)]
}),
('Dropout', {
'block': nn.Dropout(),
'desc_inputs': [[1, 512, 7, 7]],
'desc_bprop': [[1, 512, 7, 7]]
}),
('MatMul', {
'block': P.MatMul(),
'desc_inputs': [[64, 512], [512, 64]],
'desc_bprop': [[64, 64]]
}),
def _update_run_op(beta1, beta2, eps, lr, weight_decay_tensor, global_step, param, m, v,
gradient, decay_flag):
"""
Update parameters.
Args:
beta1 (Tensor): The exponential decay rate for the 1st moment estimates. Should be in range (0.0, 1.0).
beta2 (Tensor): The exponential decay rate for the 2nd moment estimates. Should be in range (0.0, 1.0).
eps (Tensor): Term added to the denominator to improve numerical stability. Should be greater than 0.
lr (Tensor): Learning rate.
weight_decay_tensor (Tensor): Weight decay. Should be equal to or greater than 0.
global_step (Tensor): Global step.
param (Tensor): Parameters.
m (Tensor): m value of parameters.
v (Tensor): v value of parameters.
gradient (Tensor): Gradient of parameters.
decay_flag (bool): Specifies whether param update with weight decay.
Returns:
Tensor, the new value of v after updating.
"""
op_mul = P.Mul()
op_sqrt = P.Sqrt()
op_rsqrt = P.Rsqrt()
op_square = P.Square()
op_cast = P.Cast()
op_reshape = P.Reshape()
op_shape = P.Shape()
op_pow = P.Pow()
op_norm = layer.Norm()
op_select = P.Select()
op_greater = P.Greater()
op_fill = P.Fill()
op_dtype = P.DType()
param_fp32 = op_cast(param, mstype.float32)
m_fp32 = op_cast(m, mstype.float32)
v_fp32 = op_cast(v, mstype.float32)
gradient_fp32 = op_cast(gradient, mstype.float32)
next_m = op_mul(beta1, m_fp32) + op_mul(op_cast(num_one, mstype.float32) - beta1, gradient_fp32)
next_v = op_mul(beta2, v_fp32) + op_mul(op_cast(num_one, mstype.float32) - beta2, op_square(gradient_fp32))
next_mm = next_m / (op_cast(num_one, mstype.float32)
- op_pow(beta1, op_cast(global_step + num_one, mstype.float32)))
next_vv = next_v / (op_cast(num_one, mstype.float32) -
op_pow(beta2, op_cast(global_step + num_one, mstype.float32)))
w_norm = op_norm(param_fp32)
g_norm = op_norm(gradient_fp32)
g_norm_hat = op_norm(op_mul(next_mm, op_rsqrt(next_vv + eps)) + weight_decay_tensor * param_fp32)
zeros = F.zeros_like(w_norm)
ones = op_fill(op_dtype(w_norm), op_shape(w_norm), 1.0)
trust_ratio = op_select(
op_greater(w_norm, zeros),
op_select(op_greater(g_norm, zeros), w_norm / g_norm_hat, ones),
ones)
tens = op_fill(op_dtype(trust_ratio), op_shape(trust_ratio), 10.0)
trust_ratio = C.clip_by_value(trust_ratio, zeros, tens)
update = next_mm / (op_sqrt(next_vv) + eps)
if decay_flag:
update = update + op_mul(weight_decay_tensor, param_fp32)
update_with_lr = op_mul(op_mul(trust_ratio, lr), update)
next_param = param_fp32 - op_reshape(update_with_lr, op_shape(param_fp32))
next_v = F.depend(next_v, F.assign(param, next_param))
next_v = F.depend(next_v, F.assign(m, next_m))
next_v = F.depend(next_v, F.assign(v, next_v))
return next_v
def __init__(self,
config,
representation_size,
batch_size,
num_classes,
target_means=(0., 0., 0., 0.),
target_stds=(0.1, 0.1, 0.2, 0.2)):
super(Rcnn, self).__init__()
cfg = config
self.rcnn_loss_cls_weight = Tensor(
np.array(cfg.rcnn_loss_cls_weight).astype(np.float32))
self.rcnn_loss_reg_weight = Tensor(
np.array(cfg.rcnn_loss_reg_weight).astype(np.float32))
self.rcnn_fc_out_channels = cfg.rcnn_fc_out_channels
self.target_means = target_means
self.target_stds = target_stds
self.num_classes = num_classes
self.in_channels = cfg.rcnn_in_channels
self.train_batch_size = batch_size
self.test_batch_size = cfg.test_batch_size
self.use_ambigous_sample = cfg.use_ambigous_sample
shape_0 = (self.rcnn_fc_out_channels, representation_size)
weights_0 = initializer("XavierUniform",
shape=shape_0[::-1],
dtype=mstype.float32).to_tensor()
shape_1 = (self.rcnn_fc_out_channels, self.rcnn_fc_out_channels)
weights_1 = initializer("XavierUniform",
shape=shape_1[::-1],
dtype=mstype.float32).to_tensor()
self.shared_fc_0 = DenseNoTranpose(representation_size,
self.rcnn_fc_out_channels,
weights_0)
self.shared_fc_1 = DenseNoTranpose(self.rcnn_fc_out_channels,
self.rcnn_fc_out_channels,
weights_1)
cls_weight = initializer(
'Normal',
shape=[num_classes, self.rcnn_fc_out_channels][::-1],
dtype=mstype.float32).to_tensor()
reg_weight = initializer(
'Normal',
shape=[num_classes * 4, self.rcnn_fc_out_channels][::-1],
dtype=mstype.float32).to_tensor()
self.cls_scores = DenseNoTranpose(self.rcnn_fc_out_channels,
num_classes, cls_weight)
self.reg_scores = DenseNoTranpose(self.rcnn_fc_out_channels,
num_classes * 4, reg_weight)
self.flatten = P.Flatten()
self.relu = P.ReLU()
self.logicaland = P.LogicalAnd()
self.loss_cls = P.SoftmaxCrossEntropyWithLogits()
self.loss_bbox = P.SmoothL1Loss(beta=1.0)
self.reshape = P.Reshape()
self.onehot = P.OneHot()
self.greater = P.Greater()
self.equal = P.Equal()
self.cast = P.Cast()
self.sum_loss = P.ReduceSum()
self.tile = P.Tile()
self.expandims = P.ExpandDims()
self.gather = P.GatherNd()
self.argmax = P.ArgMaxWithValue(axis=1)
self.on_value = Tensor(1.0, mstype.float32)
self.off_value = Tensor(0.0, mstype.float32)
self.value = Tensor(1.0, mstype.float32)
self.num_bboxes = (cfg.num_expected_pos_stage2 +
cfg.num_expected_neg_stage2) * batch_size
if self.use_ambigous_sample:
self.num_bboxes = (cfg.num_expected_pos_stage2 +
cfg.num_expected_amb_stage2 +
cfg.num_expected_neg_stage2) * batch_size
rmv_first = np.ones((self.num_bboxes, self.num_classes))
rmv_first[:, 0] = np.zeros((self.num_bboxes, ))
self.rmv_first_tensor = Tensor(rmv_first.astype(np.float32))
self.num_bboxes_test = cfg.rpn_max_num * cfg.test_batch_size
range_max = np.arange(self.num_bboxes_test).astype(np.int32)
self.range_max = Tensor(range_max)
# shape of x and y not match
('NotEqual2', {
'block': (P.NotEqual(), {
'exception': ValueError,
'error_keywords': ['NotEqual']
}),
'desc_inputs': [
Tensor(np.ones([3, 4]).astype(np.float32)),
Tensor(np.ones([3, 2]).astype(np.float32))
],
'skip': ['backward']
}),
# shape of x and y not match
('Greater2', {
'block': (P.Greater(), {
'exception': ValueError,
'error_keywords': ['Greater']
}),
'desc_inputs': [
Tensor(np.ones([3, 4]).astype(np.float32)),
Tensor(np.ones([3, 2]).astype(np.float32))
],
'skip': ['backward']
}),
# shape of x and y not match
('GreaterEqual2', {
'block': (P.GreaterEqual(), {
'exception': ValueError,
'error_keywords': ['GreaterEqual']
def __init__(self,
config,
batch_size,
num_classes,
use_sigmoid_cls,
target_means=(.0, .0, .0, .0),
target_stds=(1.0, 1.0, 1.0, 1.0)):
super(Proposal, self).__init__()
cfg = config
self.batch_size = batch_size
self.num_classes = num_classes
self.target_means = target_means
self.target_stds = target_stds
self.use_sigmoid_cls = use_sigmoid_cls
if self.use_sigmoid_cls:
self.cls_out_channels = num_classes - 1
self.activation = P.Sigmoid()
self.reshape_shape = (-1, 1)
else:
self.cls_out_channels = num_classes
self.activation = P.Softmax(axis=1)
self.reshape_shape = (-1, 2)
if self.cls_out_channels <= 0:
raise ValueError('num_classes={} is too small'.format(num_classes))
self.num_pre = cfg.rpn_proposal_nms_pre
self.min_box_size = cfg.rpn_proposal_min_bbox_size
self.nms_thr = cfg.rpn_proposal_nms_thr
self.nms_post = cfg.rpn_proposal_nms_post
self.nms_across_levels = cfg.rpn_proposal_nms_across_levels
self.max_num = cfg.rpn_proposal_max_num
self.num_levels = cfg.fpn_num_outs
# Op Define
self.squeeze = P.Squeeze()
self.reshape = P.Reshape()
self.cast = P.Cast()
self.feature_shapes = cfg.feature_shapes
self.transpose_shape = (1, 2, 0)
self.decode = P.BoundingBoxDecode(max_shape=(cfg.img_height, cfg.img_width), \
means=self.target_means, \
stds=self.target_stds)
self.nms = P.NMSWithMask(self.nms_thr)
self.concat_axis0 = P.Concat(axis=0)
self.concat_axis1 = P.Concat(axis=1)
self.split = P.Split(axis=1, output_num=5)
self.min = P.Minimum()
self.gatherND = P.GatherNd()
self.slice = P.Slice()
self.select = P.Select()
self.greater = P.Greater()
self.transpose = P.Transpose()
self.tile = P.Tile()
self.set_train_local(config, training=True)
self.dtype = np.float32
self.ms_type = mstype.float32
self.multi_10 = Tensor(10.0, self.ms_type)
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 = P.BoundingBoxEncode(means=(0.0, 0.0, 0.0,
0.0),
stds=(1.0, 1.0, 1.0,
1.0))
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))
def __init__(self, config):
super(Faster_Rcnn_Resnet50, self).__init__()
self.train_batch_size = config.batch_size
self.num_classes = config.num_classes
self.anchor_scales = config.anchor_scales
self.anchor_ratios = config.anchor_ratios
self.anchor_strides = config.anchor_strides
self.target_means = tuple(config.rcnn_target_means)
self.target_stds = tuple(config.rcnn_target_stds)
# Anchor generator
anchor_base_sizes = None
self.anchor_base_sizes = list(
self.anchor_strides
) if anchor_base_sizes is None else anchor_base_sizes
self.anchor_generators = []
for anchor_base in self.anchor_base_sizes:
self.anchor_generators.append(
AnchorGenerator(anchor_base, self.anchor_scales,
self.anchor_ratios))
self.num_anchors = len(self.anchor_ratios) * len(self.anchor_scales)
featmap_sizes = config.feature_shapes
assert len(featmap_sizes) == len(self.anchor_generators)
self.anchor_list = self.get_anchors(featmap_sizes)
# Backbone resnet50
self.backbone = ResNetFea(ResidualBlockUsing, config.resnet_block,
config.resnet_in_channels,
config.resnet_out_channels, False)
# Fpn
self.fpn_ncek = FeatPyramidNeck(config.fpn_in_channels,
config.fpn_out_channels,
config.fpn_num_outs)
# Rpn and rpn loss
self.gt_labels_stage1 = Tensor(
np.ones((self.train_batch_size, config.num_gts)).astype(np.uint8))
self.rpn_with_loss = RPN(config, self.train_batch_size,
config.rpn_in_channels,
config.rpn_feat_channels, config.num_anchors,
config.rpn_cls_out_channels)
# Proposal
self.proposal_generator = Proposal(config, self.train_batch_size,
config.activate_num_classes,
config.use_sigmoid_cls)
self.proposal_generator.set_train_local(config, True)
self.proposal_generator_test = Proposal(config, config.test_batch_size,
config.activate_num_classes,
config.use_sigmoid_cls)
self.proposal_generator_test.set_train_local(config, False)
# Assign and sampler stage two
self.bbox_assigner_sampler_for_rcnn = BboxAssignSampleForRcnn(
config, self.train_batch_size, config.num_bboxes_stage2, True)
self.decode = P.BoundingBoxDecode(max_shape=(config.img_height, config.img_width), means=self.target_means, \
stds=self.target_stds)
# Roi
self.roi_align = SingleRoIExtractor(config, config.roi_layer,
config.roi_align_out_channels,
config.roi_align_featmap_strides,
self.train_batch_size,
config.roi_align_finest_scale)
self.roi_align.set_train_local(config, True)
self.roi_align_test = SingleRoIExtractor(
config, config.roi_layer, config.roi_align_out_channels,
config.roi_align_featmap_strides, 1, config.roi_align_finest_scale)
self.roi_align_test.set_train_local(config, False)
# Rcnn
self.rcnn = Rcnn(
config, config.rcnn_in_channels * config.roi_layer['out_size'] *
config.roi_layer['out_size'], self.train_batch_size,
self.num_classes)
# Op declare
self.squeeze = P.Squeeze()
self.cast = P.Cast()
self.concat = P.Concat(axis=0)
self.concat_1 = P.Concat(axis=1)
self.concat_2 = P.Concat(axis=2)
self.reshape = P.Reshape()
self.select = P.Select()
self.greater = P.Greater()
self.transpose = P.Transpose()
# Test mode
self.test_batch_size = config.test_batch_size
self.split = P.Split(axis=0, output_num=self.test_batch_size)
self.split_shape = P.Split(axis=0, output_num=4)
self.split_scores = P.Split(axis=1, output_num=self.num_classes)
self.split_cls = P.Split(axis=0, output_num=self.num_classes - 1)
self.tile = P.Tile()
self.gather = P.GatherNd()
self.rpn_max_num = config.rpn_max_num
self.zeros_for_nms = Tensor(
np.zeros((self.rpn_max_num, 3)).astype(np.float16))
self.ones_mask = np.ones((self.rpn_max_num, 1)).astype(np.bool)
self.zeros_mask = np.zeros((self.rpn_max_num, 1)).astype(np.bool)
self.bbox_mask = Tensor(
np.concatenate((self.ones_mask, self.zeros_mask, self.ones_mask,
self.zeros_mask),
axis=1))
self.nms_pad_mask = Tensor(
np.concatenate((self.ones_mask, self.ones_mask, self.ones_mask,
self.ones_mask, self.zeros_mask),
axis=1))
self.test_score_thresh = Tensor(
np.ones((self.rpn_max_num, 1)).astype(np.float16) *
config.test_score_thr)
self.test_score_zeros = Tensor(
np.ones((self.rpn_max_num, 1)).astype(np.float16) * 0)
self.test_box_zeros = Tensor(
np.ones((self.rpn_max_num, 4)).astype(np.float16) * -1)
self.test_iou_thr = Tensor(
np.ones((self.rpn_max_num, 1)).astype(np.float16) *
config.test_iou_thr)
self.test_max_per_img = config.test_max_per_img
self.nms_test = P.NMSWithMask(config.test_iou_thr)
self.softmax = P.Softmax(axis=1)
self.logicand = P.LogicalAnd()
self.oneslike = P.OnesLike()
self.test_topk = P.TopK(sorted=True)
self.test_num_proposal = self.test_batch_size * self.rpn_max_num
# Improve speed
self.concat_start = min(self.num_classes - 2, 55)
self.concat_end = (self.num_classes - 1)
# Init tensor
roi_align_index = [
np.array(np.ones((config.num_expected_pos_stage2 +
config.num_expected_neg_stage2, 1)) * i,
dtype=np.float16) for i in range(self.train_batch_size)
]
roi_align_index_test = [np.array(np.ones((config.rpn_max_num, 1)) * i, dtype=np.float16) \
for i in range(self.test_batch_size)]
self.roi_align_index_tensor = Tensor(np.concatenate(roi_align_index))
self.roi_align_index_test_tensor = Tensor(
np.concatenate(roi_align_index_test))
def __init__(self, config, batch_size, num_bboxes, add_gt_as_proposals):
super(BboxAssignSampleForRcnn, self).__init__()
cfg = config
self.use_ambigous_sample = cfg.use_ambigous_sample
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_amb = cfg.num_expected_amb_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.gatherV2 = P.GatherV2()
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_amb = P.RandomChoiceWithMask(self.num_expected_amb)
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_amb = Tensor(np.array(-3 * 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.range_amb_size = Tensor(np.arange(self.num_expected_amb).astype(np.float16))
self.check_neg_mask = Tensor(np.array(np.ones(self.num_expected_neg - self.num_expected_pos), dtype=np.bool))
if self.use_ambigous_sample:
self.check_neg_mask = Tensor(
np.array(np.ones(self.num_expected_neg - self.num_expected_pos - self.num_expected_amb), dtype=np.bool))
check_neg_mask_ignore_end = np.array(np.ones(self.num_expected_neg), dtype=np.bool)
check_neg_mask_ignore_end[-1] = False
self.check_neg_mask_ignore_end = Tensor(check_neg_mask_ignore_end)
self.bboxs_neg_mask = Tensor(np.zeros((self.num_expected_neg, 4), dtype=np.float16))
self.bboxs_amb_mask = Tensor(np.zeros((self.num_expected_amb, 4), dtype=np.float16))
self.labels_neg_mask = Tensor(np.array(np.zeros(self.num_expected_neg), dtype=np.uint8))
self.labels_amb_mask = Tensor(np.array(np.zeros(self.num_expected_amb) + 2, dtype=np.uint8))
self.reshape_shape_pos = (self.num_expected_pos, 1)
self.reshape_shape_amb = (self.num_expected_amb, 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)
def __init__(self):
super(ClipByNormNoDivSum, self).__init__()
self.greater = P.Greater()
self.select = P.Select()
self.sqrt = P.Sqrt()
self.maximum = P.Maximum()
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 _IgammacContinuedFraction(ax, x, a, enabled):
"""Helper function for computing Igammac using a continued fraction."""
abs_x = P.Abs()
logicaland = P.LogicalAnd()
greater = P.Greater()
less = P.Less()
notequal = P.NotEqual()
fill = P.Fill()
shape = P.Shape()
dtype = P.DType()
select = P.Select()
if dtype(ax) == mstype.float16:
epsilon = eps_fp16
else:
epsilon = eps_fp32
def cond(vals):
enabled = vals[0]
c = vals[5]
return logicaland(less(c, 2000), enabled)
def body(vals):
enabled = vals[0]
ans = vals[1]
t = vals[2]
y = vals[3]
z = vals[4]
c = vals[5]
pkm1 = vals[6]
qkm1 = vals[7]
pkm2 = vals[8]
qkm2 = vals[9]
dpkm2_da = vals[10]
dqkm2_da = vals[11]
dpkm1_da = vals[12]
dqkm1_da = vals[13]
dans_da = vals[14]
c = c + 1
y = y + 1
z = z + 2
yc = y * c
pk = pkm1 * z - pkm2 * yc
qk = qkm1 * z - qkm2 * yc
qk_is_nonzero = notequal(qk, 0)
r = pk / qk
t = select(qk_is_nonzero, abs_x((ans - r) / r),
fill(dtype(t), shape(t), 1))
ans = select(qk_is_nonzero, r, ans)
dpk_da = dpkm1_da * z - pkm1 - dpkm2_da * yc + pkm2 * c
dqk_da = dqkm1_da * z - qkm1 - dqkm2_da * yc + qkm2 * c
dans_da_new = select(qk_is_nonzero, (dpk_da - ans * dqk_da) / qk,
dans_da)
grad_conditional = select(qk_is_nonzero, abs_x(dans_da_new - dans_da),
fill(dtype(dans_da), shape(dans_da), 1))
pkm2 = pkm1
pkm1 = pk
qkm2 = qkm1
qkm1 = qk
dpkm2_da = dpkm1_da
dqkm2_da = dqkm1_da
dpkm1_da = dpk_da
dqkm1_da = dqk_da
rescale = greater(abs_x(pk), 1 / epsilon)
pkm2 = select(rescale, pkm2 * epsilon, pkm2)
pkm1 = select(rescale, pkm1 * epsilon, pkm1)
qkm2 = select(rescale, qkm2 * epsilon, qkm2)
qkm1 = select(rescale, qkm1 * epsilon, qkm1)
dpkm2_da = select(rescale, dpkm2_da * epsilon, dpkm2_da)
dqkm2_da = select(rescale, dqkm2_da * epsilon, dqkm2_da)
dpkm1_da = select(rescale, dpkm1_da * epsilon, dpkm1_da)
dqkm1_da = select(rescale, dqkm1_da * epsilon, dqkm1_da)
conditional = logicaland(enabled, greater(grad_conditional, epsilon))
return (conditional, select(enabled, ans,
vals[1]), select(enabled, t, vals[2]),
select(enabled, y, vals[3]), select(enabled, z, vals[4]), c,
select(enabled, pkm1, vals[6]), select(enabled, qkm1, vals[7]),
select(enabled, pkm2, vals[8]), select(enabled, qkm2, vals[9]),
select(enabled, dpkm2_da,
vals[10]), select(enabled, dqkm2_da, vals[11]),
select(enabled, dpkm1_da,
vals[12]), select(enabled, dqkm1_da, vals[13]),
select(enabled, dans_da_new, vals[14]))
y = 1 - a
z = x + y + 1
c = fill(dtype(x), shape(x), 0)
pkm2 = fill(dtype(x), shape(x), 1)
qkm2 = x
pkm1 = x + 1
qkm1 = z * x
ans = pkm1 / qkm1
t = fill(dtype(x), shape(x), 1)
dpkm2_da = fill(dtype(x), shape(x), 0)
dqkm2_da = fill(dtype(x), shape(x), 0)
dpkm1_da = fill(dtype(x), shape(x), 0)
dqkm1_da = -x
dans_da = (dpkm1_da - ans * dqkm1_da) / qkm1
vals = (enabled, ans, t, y, z, c, pkm1, qkm1, pkm2, qkm2, dpkm2_da,
dqkm2_da, dpkm1_da, dqkm1_da, dans_da)
vals = _while_helper_func(cond, body, vals)
ans = vals[1]
return ans * ax
def __init__(self, config):
super(Deeptext_VGG16, self).__init__()
self.train_batch_size = config.batch_size
self.num_classes = config.num_classes
self.anchor_scales = config.anchor_scales
self.anchor_ratios = config.anchor_ratios
self.anchor_strides = config.anchor_strides
self.target_means = tuple(config.rcnn_target_means)
self.target_stds = tuple(config.rcnn_target_stds)
# Anchor generator
anchor_base_sizes = None
self.anchor_base_sizes = list(
self.anchor_strides
) if anchor_base_sizes is None else anchor_base_sizes
self.anchor_generators = []
for anchor_base in self.anchor_base_sizes:
self.anchor_generators.append(
AnchorGenerator(anchor_base, self.anchor_scales,
self.anchor_ratios))
self.num_anchors = len(self.anchor_ratios) * len(self.anchor_scales)
featmap_sizes = config.feature_shapes
assert len(featmap_sizes) == len(self.anchor_generators)
self.anchor_list = self.get_anchors(featmap_sizes)
# Rpn and rpn loss
self.gt_labels_stage1 = Tensor(
np.ones((self.train_batch_size, config.num_gts)).astype(np.uint8))
self.rpn_with_loss = RPN(config, self.train_batch_size,
config.rpn_in_channels,
config.rpn_feat_channels, config.num_anchors,
config.rpn_cls_out_channels)
# Proposal
self.proposal_generator = Proposal(config, self.train_batch_size,
config.activate_num_classes,
config.use_sigmoid_cls)
self.proposal_generator.set_train_local(config, True)
self.proposal_generator_test = Proposal(config, config.test_batch_size,
config.activate_num_classes,
config.use_sigmoid_cls)
self.proposal_generator_test.set_train_local(config, False)
# Assign and sampler stage two
self.bbox_assigner_sampler_for_rcnn = BboxAssignSampleForRcnn(
config, self.train_batch_size, config.num_bboxes_stage2, True)
self.decode = P.BoundingBoxDecode(max_shape=(576, 960), means=self.target_means, \
stds=self.target_stds)
# Rcnn
self.rcnn = Rcnn(
config, config.rcnn_in_channels * config.roi_layer['out_size'] *
config.roi_layer['out_size'], self.train_batch_size,
self.num_classes)
# Op declare
self.squeeze = P.Squeeze()
self.cast = P.Cast()
self.concat = P.Concat(axis=0)
self.concat_1 = P.Concat(axis=1)
self.concat_2 = P.Concat(axis=2)
self.reshape = P.Reshape()
self.select = P.Select()
self.greater = P.Greater()
self.transpose = P.Transpose()
# Test mode
self.test_batch_size = config.test_batch_size
self.split = P.Split(axis=0, output_num=self.test_batch_size)
self.split_shape = P.Split(axis=0, output_num=4)
self.split_scores = P.Split(axis=1, output_num=self.num_classes)
self.split_cls = P.Split(axis=0, output_num=self.num_classes - 1)
self.tile = P.Tile()
self.gather = P.GatherNd()
self.rpn_max_num = config.rpn_max_num
self.zeros_for_nms = Tensor(
np.zeros((self.rpn_max_num, 3)).astype(np.float32))
self.ones_mask = np.ones((self.rpn_max_num, 1)).astype(np.bool)
self.zeros_mask = np.zeros((self.rpn_max_num, 1)).astype(np.bool)
self.bbox_mask = Tensor(
np.concatenate((self.ones_mask, self.zeros_mask, self.ones_mask,
self.zeros_mask),
axis=1))
self.nms_pad_mask = Tensor(
np.concatenate((self.ones_mask, self.ones_mask, self.ones_mask,
self.ones_mask, self.zeros_mask),
axis=1))
self.test_score_thresh = Tensor(
np.ones((self.rpn_max_num, 1)).astype(np.float32) *
config.test_score_thr)
self.test_score_zeros = Tensor(
np.ones((self.rpn_max_num, 1)).astype(np.float32) * 0)
self.test_box_zeros = Tensor(
np.ones((self.rpn_max_num, 4)).astype(np.float32) * -1)
self.test_iou_thr = Tensor(
np.ones((self.rpn_max_num, 1)).astype(np.float32) *
config.test_iou_thr)
self.test_max_per_img = config.test_max_per_img
self.nms_test = P.NMSWithMask(config.test_iou_thr)
self.softmax = P.Softmax(axis=1)
self.logicand = P.LogicalAnd()
self.oneslike = P.OnesLike()
self.test_topk = P.TopK(sorted=True)
self.test_num_proposal = self.test_batch_size * self.rpn_max_num
# Improve speed
self.concat_start = (self.num_classes - 2)
self.concat_end = (self.num_classes - 1)
# Init tensor
self.use_ambigous_sample = config.use_ambigous_sample
roi_align_index = [
np.array(np.ones((config.num_expected_pos_stage2 +
config.num_expected_neg_stage2, 1)) * i,
dtype=np.float32) for i in range(self.train_batch_size)
]
if self.use_ambigous_sample:
roi_align_index = [
np.array(np.ones((config.num_expected_pos_stage2 +
config.num_expected_amb_stage2 +
config.num_expected_neg_stage2, 1)) * i,
dtype=np.float32)
for i in range(self.train_batch_size)
]
roi_align_index_test = [np.array(np.ones((config.rpn_max_num, 1)) * i, dtype=np.float32) \
for i in range(self.test_batch_size)]
self.roi_align_index_tensor = Tensor(np.concatenate(roi_align_index))
self.roi_align_index_test_tensor = Tensor(
np.concatenate(roi_align_index_test))
self.roi_align4 = P.ROIAlign(pooled_width=7,
pooled_height=7,
spatial_scale=0.125)
self.roi_align5 = P.ROIAlign(pooled_width=7,
pooled_height=7,
spatial_scale=0.0625)
self.concat1 = P.Concat(axis=1)
self.roi_align_fuse = _conv(in_channels=1024,
out_channels=512,
kernel_size=1,
padding=0,
stride=1)
self.vgg16_feature_extractor = VGG16FeatureExtraction()
def __init__(self, config):
super(Mask_Rcnn_Mobilenetv1, self).__init__()
self.train_batch_size = config.batch_size
self.num_classes = config.num_classes
self.anchor_scales = config.anchor_scales
self.anchor_ratios = config.anchor_ratios
self.anchor_strides = config.anchor_strides
self.target_means = tuple(config.rcnn_target_means)
self.target_stds = tuple(config.rcnn_target_stds)
# Anchor generator
anchor_base_sizes = None
self.anchor_base_sizes = list(
self.anchor_strides
) if anchor_base_sizes is None else anchor_base_sizes
self.anchor_generators = []
for anchor_base in self.anchor_base_sizes:
self.anchor_generators.append(
AnchorGenerator(anchor_base, self.anchor_scales,
self.anchor_ratios))
self.num_anchors = len(self.anchor_ratios) * len(self.anchor_scales)
featmap_sizes = config.feature_shapes
assert len(featmap_sizes) == len(self.anchor_generators)
self.anchor_list = self.get_anchors(featmap_sizes)
# Backbone mobilenetv1
self.backbone = MobileNetV1_FeatureSelector(
1001, features_only=True).to_float(mstype.float16)
# Fpn
self.fpn_ncek = FeatPyramidNeck(config.fpn_in_channels,
config.fpn_out_channels,
config.fpn_num_outs)
# Rpn and rpn loss
self.gt_labels_stage1 = Tensor(
np.ones((self.train_batch_size, config.num_gts)).astype(np.uint8))
self.rpn_with_loss = RPN(config, self.train_batch_size,
config.rpn_in_channels,
config.rpn_feat_channels, config.num_anchors,
config.rpn_cls_out_channels)
# Proposal
self.proposal_generator = Proposal(config, self.train_batch_size,
config.activate_num_classes,
config.use_sigmoid_cls)
self.proposal_generator.set_train_local(config, True)
self.proposal_generator_test = Proposal(config, config.test_batch_size,
config.activate_num_classes,
config.use_sigmoid_cls)
self.proposal_generator_test.set_train_local(config, False)
# Assign and sampler stage two
self.bbox_assigner_sampler_for_rcnn = BboxAssignSampleForRcnn(
config, self.train_batch_size, config.num_bboxes_stage2, True)
self.decode = P.BoundingBoxDecode(max_shape=(768, 1280), means=self.target_means, \
stds=self.target_stds)
# Roi
self.roi_align = SingleRoIExtractor(config,
config.roi_layer,
config.roi_align_out_channels,
config.roi_align_featmap_strides,
self.train_batch_size,
config.roi_align_finest_scale,
mask=False)
self.roi_align.set_train_local(config, True)
self.roi_align_mask = SingleRoIExtractor(
config,
config.roi_layer,
config.roi_align_out_channels,
config.roi_align_featmap_strides,
self.train_batch_size,
config.roi_align_finest_scale,
mask=True)
self.roi_align_mask.set_train_local(config, True)
self.roi_align_test = SingleRoIExtractor(
config,
config.roi_layer,
config.roi_align_out_channels,
config.roi_align_featmap_strides,
1,
config.roi_align_finest_scale,
mask=False)
self.roi_align_test.set_train_local(config, False)
self.roi_align_mask_test = SingleRoIExtractor(
config,
config.roi_layer,
config.roi_align_out_channels,
config.roi_align_featmap_strides,
1,
config.roi_align_finest_scale,
mask=True)
self.roi_align_mask_test.set_train_local(config, False)
# Rcnn
self.rcnn_cls = RcnnCls(config, self.train_batch_size,
self.num_classes)
self.rcnn_mask = RcnnMask(config, self.train_batch_size,
self.num_classes)
# Op declare
self.squeeze = P.Squeeze()
self.cast = P.Cast()
self.concat = P.Concat(axis=0)
self.concat_1 = P.Concat(axis=1)
self.concat_2 = P.Concat(axis=2)
self.reshape = P.Reshape()
self.select = P.Select()
self.greater = P.Greater()
self.transpose = P.Transpose()
# Test mode
self.test_batch_size = config.test_batch_size
self.split = P.Split(axis=0, output_num=self.test_batch_size)
self.split_shape = P.Split(axis=0, output_num=4)
self.split_scores = P.Split(axis=1, output_num=self.num_classes)
self.split_fb_mask = P.Split(axis=1, output_num=self.num_classes)
self.split_cls = P.Split(axis=0, output_num=self.num_classes - 1)
self.tile = P.Tile()
self.gather = P.GatherNd()
self.rpn_max_num = config.rpn_max_num
self.zeros_for_nms = Tensor(
np.zeros((self.rpn_max_num, 3)).astype(np.float16))
self.ones_mask = np.ones((self.rpn_max_num, 1)).astype(np.bool)
self.zeros_mask = np.zeros((self.rpn_max_num, 1)).astype(np.bool)
self.bbox_mask = Tensor(
np.concatenate((self.ones_mask, self.zeros_mask, self.ones_mask,
self.zeros_mask),
axis=1))
self.nms_pad_mask = Tensor(
np.concatenate((self.ones_mask, self.ones_mask, self.ones_mask,
self.ones_mask, self.zeros_mask),
axis=1))
self.test_score_thresh = Tensor(
np.ones((self.rpn_max_num, 1)).astype(np.float16) *
config.test_score_thr)
self.test_score_zeros = Tensor(
np.ones((self.rpn_max_num, 1)).astype(np.float16) * 0)
self.test_box_zeros = Tensor(
np.ones((self.rpn_max_num, 4)).astype(np.float16) * -1)
self.test_iou_thr = Tensor(
np.ones((self.rpn_max_num, 1)).astype(np.float16) *
config.test_iou_thr)
self.test_max_per_img = config.test_max_per_img
self.nms_test = P.NMSWithMask(config.test_iou_thr)
self.softmax = P.Softmax(axis=1)
self.logicand = P.LogicalAnd()
self.oneslike = P.OnesLike()
self.test_topk = P.TopK(sorted=True)
self.test_num_proposal = self.test_batch_size * self.rpn_max_num
# Improve speed
self.concat_start = min(self.num_classes - 2, 55)
self.concat_end = (self.num_classes - 1)
# Init tensor
roi_align_index = [
np.array(np.ones((config.num_expected_pos_stage2 +
config.num_expected_neg_stage2, 1)) * i,
dtype=np.float16) for i in range(self.train_batch_size)
]
roi_align_index_test = [np.array(np.ones((config.rpn_max_num, 1)) * i, dtype=np.float16) \
for i in range(self.test_batch_size)]
self.roi_align_index_tensor = Tensor(np.concatenate(roi_align_index))
self.roi_align_index_test_tensor = Tensor(
np.concatenate(roi_align_index_test))
roi_align_index_pos = [
np.array(np.ones((config.num_expected_pos_stage2, 1)) * i,
dtype=np.float16) for i in range(self.train_batch_size)
]
self.roi_align_index_tensor_pos = Tensor(
np.concatenate(roi_align_index_pos))
self.rcnn_loss_cls_weight = Tensor(
np.array(config.rcnn_loss_cls_weight).astype(np.float16))
self.rcnn_loss_reg_weight = Tensor(
np.array(config.rcnn_loss_reg_weight).astype(np.float16))
self.rcnn_loss_mask_fb_weight = Tensor(
np.array(config.rcnn_loss_mask_fb_weight).astype(np.float16))
self.argmax_with_value = P.ArgMaxWithValue(axis=1)
self.on_value = Tensor(1.0, mstype.float32)
self.off_value = Tensor(0.0, mstype.float32)
self.onehot = P.OneHot()
self.reducesum = P.ReduceSum()
self.sigmoid = P.Sigmoid()
self.expand_dims = P.ExpandDims()
self.test_mask_fb_zeros = Tensor(
np.zeros((self.rpn_max_num, 28, 28)).astype(np.float16))
self.value = Tensor(1.0, mstype.float16)
def __init__(self):
super(Greater, self).__init__()
self.greater = P.Greater()
def __init__(self, strategy1, strategy2):
super().__init__()
self.matmul = P.MatMul().set_strategy(strategy1)
self.greater = P.Greater().set_strategy(strategy2)
# type of x and y not match
('EqualCount1', {
'block': (P.EqualCount(), {'exception': TypeError, 'error_keywords': ['EqualCount']}),
'desc_inputs': [Tensor(np.ones([3, 4]).astype(np.int32)), Tensor(np.ones([3, 4]).astype(np.float32))],
'skip': ['backward']}),
# shape of x and y not match
# shape of x and y not match
('NotEqual2', {
'block': (P.NotEqual(), {'exception': ValueError, 'error_keywords': ['NotEqual']}),
'desc_inputs': [Tensor(np.ones([3, 4]).astype(np.float32)), Tensor(np.ones([3, 2]).astype(np.float32))],
'skip': ['backward']}),
# shape of x and y not match
('Greater2', {
'block': (P.Greater(), {'exception': ValueError, 'error_keywords': ['Greater']}),
'desc_inputs': [Tensor(np.ones([3, 4]).astype(np.float32)), Tensor(np.ones([3, 2]).astype(np.float32))],
'skip': ['backward']}),
# shape of x and y not match
('GreaterEqual2', {
'block': (P.GreaterEqual(), {'exception': ValueError, 'error_keywords': ['GreaterEqual']}),
'desc_inputs': [Tensor(np.ones([3, 4]).astype(np.float32)), Tensor(np.ones([3, 2]).astype(np.float32))],
'skip': ['backward']}),
# shape of x and y not match
('Less2', {
'block': (P.Less(), {'exception': ValueError, 'error_keywords': ['Less']}),
'desc_inputs': [Tensor(np.ones([3, 4]).astype(np.float32)), Tensor(np.ones([3, 2]).astype(np.float32))],
'skip': ['backward']}),
