diff --git a/official/cv/faster_rcnn/src/FasterRcnn/fpn_neck.py b/official/cv/faster_rcnn/src/FasterRcnn/fpn_neck.py
index f346ccfb36c91ecf359c92c37e5492953ddd7e4e..b22da232f057ebd9a8721d84c525cb188a70b65d 100644
--- a/official/cv/faster_rcnn/src/FasterRcnn/fpn_neck.py
+++ b/official/cv/faster_rcnn/src/FasterRcnn/fpn_neck.py
@@ -30,7 +30,7 @@ def bias_init_zeros(shape):
def _conv(in_channels, out_channels, kernel_size=3, stride=1, padding=0, pad_mode='pad'):
"""Conv2D wrapper."""
shape = (out_channels, in_channels, kernel_size, kernel_size)
- weights = ms.common.initializer.initializer("XavierUniform", shape=shape, dtype=ms.float32).to_tensor()
+ weights = ms.common.initializer.initializer("XavierUniform", shape=shape, dtype=ms.float32).init_data()
shape_bias = (out_channels,)
biass = bias_init_zeros(shape_bias)
return nn.Conv2d(in_channels, out_channels,
diff --git a/official/cv/faster_rcnn/src/FasterRcnn/rcnn.py b/official/cv/faster_rcnn/src/FasterRcnn/rcnn.py
index 6d68af5597e3fedf2545f29633eb300309af83d9..fa02da335afc218b02c580b5a671ce4872484f4c 100644
--- a/official/cv/faster_rcnn/src/FasterRcnn/rcnn.py
+++ b/official/cv/faster_rcnn/src/FasterRcnn/rcnn.py
@@ -95,18 +95,18 @@ class Rcnn(nn.Cell):
shape_0 = (self.rcnn_fc_out_channels, representation_size)
weights_0 = ms.common.initializer.initializer("XavierUniform", shape=shape_0[::-1], \
- dtype=self.ms_type).to_tensor()
+ dtype=self.ms_type).init_data()
shape_1 = (self.rcnn_fc_out_channels, self.rcnn_fc_out_channels)
weights_1 = ms.common.initializer.initializer("XavierUniform", shape=shape_1[::-1], \
- dtype=self.ms_type).to_tensor()
+ dtype=self.ms_type).init_data()
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 = ms.common.initializer.initializer('Normal', shape=[num_classes, self.rcnn_fc_out_channels][::-1],
- dtype=self.ms_type).to_tensor()
+ dtype=self.ms_type).init_data()
reg_weight = ms.common.initializer.initializer('Normal', shape=[self.num_classes_fronted * 4,
self.rcnn_fc_out_channels][::-1],
- dtype=self.ms_type).to_tensor()
+ dtype=self.ms_type).init_data()
self.cls_scores = DenseNoTranpose(self.rcnn_fc_out_channels, num_classes, cls_weight)
self.reg_scores = DenseNoTranpose(self.rcnn_fc_out_channels, self.num_classes_fronted * 4, reg_weight)
diff --git a/official/cv/faster_rcnn/src/FasterRcnn/rpn.py b/official/cv/faster_rcnn/src/FasterRcnn/rpn.py
index 49102d76f16d278e9390ac11c8a72fd4452e244a..99bf21fa88130ad61bb0da5e3fe9be26932f173f 100644
--- a/official/cv/faster_rcnn/src/FasterRcnn/rpn.py
+++ b/official/cv/faster_rcnn/src/FasterRcnn/rpn.py
@@ -165,18 +165,18 @@ class RPN(nn.Cell):
shp_weight_conv = (feat_channels, in_channels, 3, 3)
shp_bias_conv = (feat_channels,)
- weight_conv = ms.common.initializer.initializer('Normal', shape=shp_weight_conv, dtype=self.ms_type).to_tensor()
- bias_conv = ms.common.initializer.initializer(0, shape=shp_bias_conv, dtype=self.ms_type).to_tensor()
+ weight_conv = ms.common.initializer.initializer('Normal', shape=shp_weight_conv, dtype=self.ms_type).init_data()
+ bias_conv = ms.common.initializer.initializer(0, shape=shp_bias_conv, dtype=self.ms_type).init_data()
shp_weight_cls = (num_anchors * cls_out_channels, feat_channels, 1, 1)
shp_bias_cls = (num_anchors * cls_out_channels,)
- weight_cls = ms.common.initializer.initializer('Normal', shape=shp_weight_cls, dtype=self.ms_type).to_tensor()
- bias_cls = ms.common.initializer.initializer(0, shape=shp_bias_cls, dtype=self.ms_type).to_tensor()
+ weight_cls = ms.common.initializer.initializer('Normal', shape=shp_weight_cls, dtype=self.ms_type).init_data()
+ bias_cls = ms.common.initializer.initializer(0, shape=shp_bias_cls, dtype=self.ms_type).init_data()
shp_weight_reg = (num_anchors * 4, feat_channels, 1, 1)
shp_bias_reg = (num_anchors * 4,)
- weight_reg = ms.common.initializer.initializer('Normal', shape=shp_weight_reg, dtype=self.ms_type).to_tensor()
- bias_reg = ms.common.initializer.initializer(0, shape=shp_bias_reg, dtype=self.ms_type).to_tensor()
+ weight_reg = ms.common.initializer.initializer('Normal', shape=shp_weight_reg, dtype=self.ms_type).init_data()
+ bias_reg = ms.common.initializer.initializer(0, shape=shp_bias_reg, dtype=self.ms_type).init_data()
for i in range(num_layers):
rpn_reg_cls_block = RpnRegClsBlock(in_channels, feat_channels, num_anchors, cls_out_channels, \
diff --git a/research/cv/CascadeRCNN/src/CascadeRcnn/fpn_neck.py b/research/cv/CascadeRCNN/src/CascadeRcnn/fpn_neck.py
index 6cf4fc9c603f91770de12284ca07dccc2384ae05..0ad3950ba69927f7fede1163c2fb588b681d6879 100644
--- a/research/cv/CascadeRCNN/src/CascadeRcnn/fpn_neck.py
+++ b/research/cv/CascadeRCNN/src/CascadeRcnn/fpn_neck.py
@@ -30,7 +30,7 @@ def bias_init_zeros(shape):
def _conv(in_channels, out_channels, kernel_size=3, stride=1, padding=0, pad_mode='pad'):
"""Conv2D wrapper."""
shape = (out_channels, in_channels, kernel_size, kernel_size)
- weights = initializer("XavierUniform", shape=shape, dtype=mstype.float32).to_tensor()
+ weights = initializer("XavierUniform", shape=shape, dtype=mstype.float32).init_data()
shape_bias = (out_channels,)
biass = bias_init_zeros(shape_bias)
return nn.Conv2d(in_channels, out_channels,
diff --git a/research/cv/CascadeRCNN/src/CascadeRcnn/rcnn.py b/research/cv/CascadeRCNN/src/CascadeRcnn/rcnn.py
index d97411604aeec88201d6d7d484822c955d6960c6..00c0782183636356d71b2bc4394673bb417c6a0d 100644
--- a/research/cv/CascadeRCNN/src/CascadeRcnn/rcnn.py
+++ b/research/cv/CascadeRCNN/src/CascadeRcnn/rcnn.py
@@ -88,18 +88,18 @@ class Rcnn(nn.Cell):
self.test_batch_size = cfg.test_batch_size
shape_0 = (self.rcnn_fc_out_channels, representation_size)
- weights_0 = initializer("XavierUniform", shape=shape_0[::-1], dtype=self.ms_type).to_tensor()
+ weights_0 = initializer("XavierUniform", shape=shape_0[::-1], dtype=self.ms_type).init_data()
shape_1 = (self.rcnn_fc_out_channels, self.rcnn_fc_out_channels)
- weights_1 = initializer("XavierUniform", shape=shape_1[::-1], dtype=self.ms_type).to_tensor()
+ weights_1 = initializer("XavierUniform", shape=shape_1[::-1], dtype=self.ms_type).init_data()
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=self.ms_type).to_tensor()
+ dtype=self.ms_type).init_data()
reg_weight = initializer('Normal', shape=[num_classes * 4, self.rcnn_fc_out_channels][::-1],
- dtype=self.ms_type).to_tensor()
+ dtype=self.ms_type).init_data()
reg_weight_agn = initializer('Normal', shape=[4, self.rcnn_fc_out_channels][::-1],
- dtype=mstype.float32).to_tensor()
+ dtype=mstype.float32).init_data()
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.reg_scores_class_ang = DenseNoTranpose(self.rcnn_fc_out_channels, 4, reg_weight_agn)
diff --git a/research/cv/CascadeRCNN/src/CascadeRcnn/rcnn1.py b/research/cv/CascadeRCNN/src/CascadeRcnn/rcnn1.py
index 65c597c125580006cafcd4d4e2f3c82c2e0c3a43..d4330d98b4a0e17856848f0d5574c9383d76b0e6 100644
--- a/research/cv/CascadeRCNN/src/CascadeRcnn/rcnn1.py
+++ b/research/cv/CascadeRCNN/src/CascadeRcnn/rcnn1.py
@@ -88,18 +88,18 @@ class Rcnn_1(nn.Cell):
self.test_batch_size = cfg.test_batch_size
shape_0 = (self.rcnn_fc_out_channels, representation_size)
- weights_0 = initializer("XavierUniform", shape=shape_0[::-1], dtype=self.ms_type).to_tensor()
+ weights_0 = initializer("XavierUniform", shape=shape_0[::-1], dtype=self.ms_type).init_data()
shape_1 = (self.rcnn_fc_out_channels, self.rcnn_fc_out_channels)
- weights_1 = initializer("XavierUniform", shape=shape_1[::-1], dtype=self.ms_type).to_tensor()
+ weights_1 = initializer("XavierUniform", shape=shape_1[::-1], dtype=self.ms_type).init_data()
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=self.ms_type).to_tensor()
+ dtype=self.ms_type).init_data()
reg_weight = initializer('Normal', shape=[num_classes * 4, self.rcnn_fc_out_channels][::-1],
- dtype=self.ms_type).to_tensor()
+ dtype=self.ms_type).init_data()
reg_weight_agn = initializer('Normal', shape=[4, self.rcnn_fc_out_channels][::-1],
- dtype=mstype.float32).to_tensor()
+ dtype=mstype.float32).init_data()
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.reg_scores_class_ang = DenseNoTranpose(self.rcnn_fc_out_channels, 4, reg_weight_agn)
diff --git a/research/cv/CascadeRCNN/src/CascadeRcnn/rcnn2.py b/research/cv/CascadeRCNN/src/CascadeRcnn/rcnn2.py
index e8cd7e2364090eebf975ced481936a5f9f1fc590..06fd550021bec0d38f8b203e56d65e2351da8f53 100644
--- a/research/cv/CascadeRCNN/src/CascadeRcnn/rcnn2.py
+++ b/research/cv/CascadeRCNN/src/CascadeRcnn/rcnn2.py
@@ -88,16 +88,16 @@ class Rcnn_2(nn.Cell):
self.test_batch_size = cfg.test_batch_size
shape_0 = (self.rcnn_fc_out_channels, representation_size)
- weights_0 = initializer("XavierUniform", shape=shape_0[::-1], dtype=self.ms_type).to_tensor()
+ weights_0 = initializer("XavierUniform", shape=shape_0[::-1], dtype=self.ms_type).init_data()
shape_1 = (self.rcnn_fc_out_channels, self.rcnn_fc_out_channels)
- weights_1 = initializer("XavierUniform", shape=shape_1[::-1], dtype=self.ms_type).to_tensor()
+ weights_1 = initializer("XavierUniform", shape=shape_1[::-1], dtype=self.ms_type).init_data()
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=self.ms_type).to_tensor()
+ dtype=self.ms_type).init_data()
reg_weight = initializer('Normal', shape=[num_classes * 4, self.rcnn_fc_out_channels][::-1],
- dtype=self.ms_type).to_tensor()
+ dtype=self.ms_type).init_data()
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)
diff --git a/research/cv/CascadeRCNN/src/CascadeRcnn/rpn.py b/research/cv/CascadeRCNN/src/CascadeRcnn/rpn.py
index 5a01d2c529a1cbc3acfa829f52b337d9f281221e..ae3749f6aad64774eea4ca1801b31e0144190672 100644
--- a/research/cv/CascadeRCNN/src/CascadeRcnn/rpn.py
+++ b/research/cv/CascadeRCNN/src/CascadeRcnn/rpn.py
@@ -167,18 +167,18 @@ class RPN(nn.Cell):
shp_weight_conv = (feat_channels, in_channels, 3, 3)
shp_bias_conv = (feat_channels,)
- weight_conv = initializer('Normal', shape=shp_weight_conv, dtype=self.ms_type).to_tensor()
- bias_conv = initializer(0, shape=shp_bias_conv, dtype=self.ms_type).to_tensor()
+ weight_conv = initializer('Normal', shape=shp_weight_conv, dtype=self.ms_type).init_data()
+ bias_conv = initializer(0, shape=shp_bias_conv, dtype=self.ms_type).init_data()
shp_weight_cls = (num_anchors * cls_out_channels, feat_channels, 1, 1)
shp_bias_cls = (num_anchors * cls_out_channels,)
- weight_cls = initializer('Normal', shape=shp_weight_cls, dtype=self.ms_type).to_tensor()
- bias_cls = initializer(0, shape=shp_bias_cls, dtype=self.ms_type).to_tensor()
+ weight_cls = initializer('Normal', shape=shp_weight_cls, dtype=self.ms_type).init_data()
+ bias_cls = initializer(0, shape=shp_bias_cls, dtype=self.ms_type).init_data()
shp_weight_reg = (num_anchors * 4, feat_channels, 1, 1)
shp_bias_reg = (num_anchors * 4,)
- weight_reg = initializer('Normal', shape=shp_weight_reg, dtype=self.ms_type).to_tensor()
- bias_reg = initializer(0, shape=shp_bias_reg, dtype=self.ms_type).to_tensor()
+ weight_reg = initializer('Normal', shape=shp_weight_reg, dtype=self.ms_type).init_data()
+ bias_reg = initializer(0, shape=shp_bias_reg, dtype=self.ms_type).init_data()
for i in range(num_layers):
rpn_reg_cls_block = RpnRegClsBlock(in_channels, feat_channels, num_anchors, cls_out_channels, \
diff --git a/research/cv/HRNetW48_cls/src/utils.py b/research/cv/HRNetW48_cls/src/utils.py
index 5cfe20f181fada9600adc8265f4d77b5874cd09a..0c7f3b0cf948d8c40cc2487f8049cf7457fe8e02 100644
--- a/research/cv/HRNetW48_cls/src/utils.py
+++ b/research/cv/HRNetW48_cls/src/utils.py
@@ -52,7 +52,7 @@ def calculate_fan_in_and_fan_out(shape):
def get_conv_bias(cell):
"""Bias initializer for conv."""
weight = initializer.initializer(initializer.HeUniform(negative_slope=math.sqrt(5)),
- cell.weight.shape, cell.weight.dtype).to_tensor()
+ cell.weight.shape, cell.weight.dtype).init_data()
fan_in, _ = calculate_fan_in_and_fan_out(weight.shape)
bound = 1 / math.sqrt(fan_in)
return initializer.initializer(initializer.Uniform(scale=bound),
diff --git a/research/cv/HRNetW48_seg/src/seg_hrnet.py b/research/cv/HRNetW48_seg/src/seg_hrnet.py
index fe513c892f77074effef96ce8c892828b94984e5..1a32a75aa18bfd48abe37561fe57dc0ec768f70d 100644
--- a/research/cv/HRNetW48_seg/src/seg_hrnet.py
+++ b/research/cv/HRNetW48_seg/src/seg_hrnet.py
@@ -554,7 +554,7 @@ def calculate_fan_in_and_fan_out(shape):
def get_conv_bias(cell):
"""Bias initializer for conv."""
weight = initializer.initializer(initializer.HeUniform(negative_slope=math.sqrt(5)),
- cell.weight.shape, cell.weight.dtype).to_tensor()
+ cell.weight.shape, cell.weight.dtype).init_data()
fan_in, _ = calculate_fan_in_and_fan_out(weight.shape)
bound = 1 / math.sqrt(fan_in)
return initializer.initializer(initializer.Uniform(scale=bound),
diff --git a/research/cv/OCRNet/src/utils.py b/research/cv/OCRNet/src/utils.py
index 6c5f5fc4a2f2fe64093d2ca481fc46b151629d7a..8d38e8db23133398c528acaff1a67886291d4a9d 100644
--- a/research/cv/OCRNet/src/utils.py
+++ b/research/cv/OCRNet/src/utils.py
@@ -47,7 +47,7 @@ def calculate_fan_in_and_fan_out(shape):
def get_conv_bias(cell):
weight = initializer.initializer(initializer.HeUniform(negative_slope=math.sqrt(5)),
- cell.weight.shape, cell.weight.dtype).to_tensor()
+ cell.weight.shape, cell.weight.dtype).init_data()
fan_in, _ = calculate_fan_in_and_fan_out(weight.shape)
bound = 1 / math.sqrt(fan_in)
return initializer.initializer(initializer.Uniform(scale=bound),
diff --git a/research/cv/advanced_east/src/vgg.py b/research/cv/advanced_east/src/vgg.py
index 6f608aeed71d46c0547b6891bd3f34718d57f747..930eb5aa2e9d61ed31b952bc7a2ad4dd83412723 100644
--- a/research/cv/advanced_east/src/vgg.py
+++ b/research/cv/advanced_east/src/vgg.py
@@ -38,7 +38,7 @@ def _make_layer(base, args, batch_norm):
weight = 'ones'
if args.initialize_mode == "XavierUniform":
weight_shape = (v, in_channels, 3, 3)
- weight = initializer('XavierUniform', shape=weight_shape, dtype=mstype.float32).to_tensor()
+ weight = initializer('XavierUniform', shape=weight_shape, dtype=mstype.float32).init_data()
conv2d = nn.Conv2d(in_channels=in_channels,
out_channels=v,
diff --git a/research/cv/efficientnet-b1/src/utils.py b/research/cv/efficientnet-b1/src/utils.py
index 3f63a075b661fb5254388e6635be8d87419ae3ed..7ddd11d279ecb2c48b6154eba6e619deb2ab0a1b 100644
--- a/research/cv/efficientnet-b1/src/utils.py
+++ b/research/cv/efficientnet-b1/src/utils.py
@@ -52,7 +52,7 @@ def calculate_fan_in_and_fan_out(shape):
def get_conv_bias(cell):
"""Bias initializer for conv."""
weight = initializer.initializer(initializer.HeUniform(negative_slope=math.sqrt(5)),
- cell.weight.shape, cell.weight.dtype).to_tensor()
+ cell.weight.shape, cell.weight.dtype).init_data()
fan_in, _ = calculate_fan_in_and_fan_out(weight.shape)
bound = 1 / math.sqrt(fan_in)
return initializer.initializer(initializer.Uniform(scale=bound),
diff --git a/research/cv/faster_rcnn_dcn/src/FasterRcnn/fpn_neck.py b/research/cv/faster_rcnn_dcn/src/FasterRcnn/fpn_neck.py
index 0aedcefae9c773b5774a460a073ef35233044d20..c2916f285628d4c5e31de8cef9cc474e819c3ae8 100644
--- a/research/cv/faster_rcnn_dcn/src/FasterRcnn/fpn_neck.py
+++ b/research/cv/faster_rcnn_dcn/src/FasterRcnn/fpn_neck.py
@@ -30,7 +30,7 @@ def bias_init_zeros(shape):
def _conv(in_channels, out_channels, kernel_size=3, stride=1, padding=0, pad_mode='pad'):
"""Conv2D wrapper."""
shape = (out_channels, in_channels, kernel_size, kernel_size)
- weights = initializer("XavierUniform", shape=shape, dtype=mstype.float32).to_tensor()
+ weights = initializer("XavierUniform", shape=shape, dtype=mstype.float32).init_data()
shape_bias = (out_channels,)
biass = bias_init_zeros(shape_bias)
return nn.Conv2d(in_channels, out_channels,
diff --git a/research/cv/faster_rcnn_dcn/src/FasterRcnn/rcnn.py b/research/cv/faster_rcnn_dcn/src/FasterRcnn/rcnn.py
index 0c1cf0b8f530c1bb67069898ddd33193bde94101..11defd618a8618d7aa3fab32500368132264f951 100644
--- a/research/cv/faster_rcnn_dcn/src/FasterRcnn/rcnn.py
+++ b/research/cv/faster_rcnn_dcn/src/FasterRcnn/rcnn.py
@@ -88,16 +88,16 @@ class Rcnn(nn.Cell):
self.test_batch_size = cfg.test_batch_size
shape_0 = (self.rcnn_fc_out_channels, representation_size)
- weights_0 = initializer("XavierUniform", shape=shape_0[::-1], dtype=self.ms_type).to_tensor()
+ weights_0 = initializer("XavierUniform", shape=shape_0[::-1], dtype=self.ms_type).init_data()
shape_1 = (self.rcnn_fc_out_channels, self.rcnn_fc_out_channels)
- weights_1 = initializer("XavierUniform", shape=shape_1[::-1], dtype=self.ms_type).to_tensor()
+ weights_1 = initializer("XavierUniform", shape=shape_1[::-1], dtype=self.ms_type).init_data()
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=self.ms_type).to_tensor()
+ dtype=self.ms_type).init_data()
reg_weight = initializer('Normal', shape=[num_classes * 4, self.rcnn_fc_out_channels][::-1],
- dtype=self.ms_type).to_tensor()
+ dtype=self.ms_type).init_data()
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)
diff --git a/research/cv/faster_rcnn_dcn/src/FasterRcnn/rpn.py b/research/cv/faster_rcnn_dcn/src/FasterRcnn/rpn.py
index 2f9d2f84799814e01d674bae49b6080715302382..f8e324a66248e16fd680a1bd6aba9b71a3c4ab5f 100644
--- a/research/cv/faster_rcnn_dcn/src/FasterRcnn/rpn.py
+++ b/research/cv/faster_rcnn_dcn/src/FasterRcnn/rpn.py
@@ -168,18 +168,18 @@ class RPN(nn.Cell):
shp_weight_conv = (feat_channels, in_channels, 3, 3)
shp_bias_conv = (feat_channels,)
- weight_conv = initializer('Normal', shape=shp_weight_conv, dtype=self.ms_type).to_tensor()
- bias_conv = initializer(0, shape=shp_bias_conv, dtype=self.ms_type).to_tensor()
+ weight_conv = initializer('Normal', shape=shp_weight_conv, dtype=self.ms_type).init_data()
+ bias_conv = initializer(0, shape=shp_bias_conv, dtype=self.ms_type).init_data()
shp_weight_cls = (num_anchors * cls_out_channels, feat_channels, 1, 1)
shp_bias_cls = (num_anchors * cls_out_channels,)
- weight_cls = initializer('Normal', shape=shp_weight_cls, dtype=self.ms_type).to_tensor()
- bias_cls = initializer(0, shape=shp_bias_cls, dtype=self.ms_type).to_tensor()
+ weight_cls = initializer('Normal', shape=shp_weight_cls, dtype=self.ms_type).init_data()
+ bias_cls = initializer(0, shape=shp_bias_cls, dtype=self.ms_type).init_data()
shp_weight_reg = (num_anchors * 4, feat_channels, 1, 1)
shp_bias_reg = (num_anchors * 4,)
- weight_reg = initializer('Normal', shape=shp_weight_reg, dtype=self.ms_type).to_tensor()
- bias_reg = initializer(0, shape=shp_bias_reg, dtype=self.ms_type).to_tensor()
+ weight_reg = initializer('Normal', shape=shp_weight_reg, dtype=self.ms_type).init_data()
+ bias_reg = initializer(0, shape=shp_bias_reg, dtype=self.ms_type).init_data()
for i in range(num_layers):
rpn_reg_cls_block = RpnRegClsBlock(in_channels, feat_channels, num_anchors, cls_out_channels, \
diff --git a/research/cv/res2net_faster_rcnn/src/FasterRcnn/fpn_neck.py b/research/cv/res2net_faster_rcnn/src/FasterRcnn/fpn_neck.py
index 2e8c9a01a0fb0f12d48b6cd5ed4a91a09560173e..f11383c0ec180f774f9f683ab3e8fe44fac6e996 100644
--- a/research/cv/res2net_faster_rcnn/src/FasterRcnn/fpn_neck.py
+++ b/research/cv/res2net_faster_rcnn/src/FasterRcnn/fpn_neck.py
@@ -34,7 +34,7 @@ def _conv(
shape = (out_channels, in_channels, kernel_size, kernel_size)
weights = initializer(
"XavierUniform", shape=shape, dtype=mstype.float32
- ).to_tensor()
+ ).init_data()
shape_bias = (out_channels,)
biass = bias_init_zeros(shape_bias)
return nn.Conv2d(
diff --git a/research/cv/res2net_faster_rcnn/src/FasterRcnn/rcnn.py b/research/cv/res2net_faster_rcnn/src/FasterRcnn/rcnn.py
index 4d1843b43251b4faf324a3407452fff9c983833d..2fc6c5b476fb7082826e8157bde622dcb3f76104 100644
--- a/research/cv/res2net_faster_rcnn/src/FasterRcnn/rcnn.py
+++ b/research/cv/res2net_faster_rcnn/src/FasterRcnn/rcnn.py
@@ -101,11 +101,11 @@ class Rcnn(nn.Cell):
shape_0 = (self.rcnn_fc_out_channels, representation_size)
weights_0 = initializer(
"XavierUniform", shape=shape_0[::-1], dtype=self.ms_type
- ).to_tensor()
+ ).init_data()
shape_1 = (self.rcnn_fc_out_channels, self.rcnn_fc_out_channels)
weights_1 = initializer(
"XavierUniform", shape=shape_1[::-1], dtype=self.ms_type
- ).to_tensor()
+ ).init_data()
self.shared_fc_0 = DenseNoTranpose(
representation_size, self.rcnn_fc_out_channels, weights_0
)
@@ -117,12 +117,12 @@ class Rcnn(nn.Cell):
"Normal",
shape=[num_classes, self.rcnn_fc_out_channels][::-1],
dtype=self.ms_type,
- ).to_tensor()
+ ).init_data()
reg_weight = initializer(
"Normal",
shape=[num_classes * 4, self.rcnn_fc_out_channels][::-1],
dtype=self.ms_type,
- ).to_tensor()
+ ).init_data()
self.cls_scores = DenseNoTranpose(
self.rcnn_fc_out_channels, num_classes, cls_weight
)
diff --git a/research/cv/res2net_faster_rcnn/src/FasterRcnn/rpn.py b/research/cv/res2net_faster_rcnn/src/FasterRcnn/rpn.py
index 1b0f4217be3609206fa7c3269d6d0eeeaea33ac4..ffbd2b0614c6d866baad2228bc0f4d301253b361 100644
--- a/research/cv/res2net_faster_rcnn/src/FasterRcnn/rpn.py
+++ b/research/cv/res2net_faster_rcnn/src/FasterRcnn/rpn.py
@@ -220,22 +220,22 @@ class RPN(nn.Cell):
shp_bias_conv = (feat_channels,)
weight_conv = initializer(
"Normal", shape=shp_weight_conv, dtype=self.ms_type
- ).to_tensor()
- bias_conv = initializer(0, shape=shp_bias_conv, dtype=self.ms_type).to_tensor()
+ ).init_data()
+ bias_conv = initializer(0, shape=shp_bias_conv, dtype=self.ms_type).init_data()
shp_weight_cls = (num_anchors * cls_out_channels, feat_channels, 1, 1)
shp_bias_cls = (num_anchors * cls_out_channels,)
weight_cls = initializer(
"Normal", shape=shp_weight_cls, dtype=self.ms_type
- ).to_tensor()
- bias_cls = initializer(0, shape=shp_bias_cls, dtype=self.ms_type).to_tensor()
+ ).init_data()
+ bias_cls = initializer(0, shape=shp_bias_cls, dtype=self.ms_type).init_data()
shp_weight_reg = (num_anchors * 4, feat_channels, 1, 1)
shp_bias_reg = (num_anchors * 4,)
weight_reg = initializer(
"Normal", shape=shp_weight_reg, dtype=self.ms_type
- ).to_tensor()
- bias_reg = initializer(0, shape=shp_bias_reg, dtype=self.ms_type).to_tensor()
+ ).init_data()
+ bias_reg = initializer(0, shape=shp_bias_reg, dtype=self.ms_type).init_data()
for i in range(num_layers):
rpn_reg_cls_block = RpnRegClsBlock(
diff --git a/research/cv/rfcn/src/rfcn/rpn.py b/research/cv/rfcn/src/rfcn/rpn.py
index 3e2a5f4c59519d4eff7371931f5d301cac4a7479..a3d7e8391fe51a3e631acc723f46fad6355dee7c 100644
--- a/research/cv/rfcn/src/rfcn/rpn.py
+++ b/research/cv/rfcn/src/rfcn/rpn.py
@@ -166,18 +166,18 @@ class RPN(nn.Cell):
shp_weight_conv = (feat_channels, in_channels, 3, 3)
shp_bias_conv = (feat_channels,)
- weight_conv = initializer('Normal', shape=shp_weight_conv, dtype=self.ms_type).to_tensor()
- bias_conv = initializer(0, shape=shp_bias_conv, dtype=self.ms_type).to_tensor()
+ weight_conv = initializer('Normal', shape=shp_weight_conv, dtype=self.ms_type).init_data()
+ bias_conv = initializer(0, shape=shp_bias_conv, dtype=self.ms_type).init_data()
shp_weight_cls = (num_anchors * cls_out_channels, feat_channels, 1, 1)
shp_bias_cls = (num_anchors * cls_out_channels,)
- weight_cls = initializer('Normal', shape=shp_weight_cls, dtype=self.ms_type).to_tensor()
- bias_cls = initializer(0, shape=shp_bias_cls, dtype=self.ms_type).to_tensor()
+ weight_cls = initializer('Normal', shape=shp_weight_cls, dtype=self.ms_type).init_data()
+ bias_cls = initializer(0, shape=shp_bias_cls, dtype=self.ms_type).init_data()
shp_weight_reg = (num_anchors * 4, feat_channels, 1, 1)
shp_bias_reg = (num_anchors * 4,)
- weight_reg = initializer('Normal', shape=shp_weight_reg, dtype=self.ms_type).to_tensor()
- bias_reg = initializer(0, shape=shp_bias_reg, dtype=self.ms_type).to_tensor()
+ weight_reg = initializer('Normal', shape=shp_weight_reg, dtype=self.ms_type).init_data()
+ bias_reg = initializer(0, shape=shp_bias_reg, dtype=self.ms_type).init_data()
for i in range(num_layers):
rpn_reg_cls_block = RpnRegClsBlock(in_channels, feat_channels, num_anchors, cls_out_channels, \
diff --git a/research/cv/tracktor/src/FasterRcnn/fpn_neck.py b/research/cv/tracktor/src/FasterRcnn/fpn_neck.py
index 8496b8636e16fa48ecdd14ef93f27ea2e24dcdc7..0cf8e819de896be8be73f3e028a59e9a0de918d3 100644
--- a/research/cv/tracktor/src/FasterRcnn/fpn_neck.py
+++ b/research/cv/tracktor/src/FasterRcnn/fpn_neck.py
@@ -31,7 +31,7 @@ def bias_init_zeros(shape):
def _conv(in_channels, out_channels, kernel_size=3, stride=1, padding=0, pad_mode='pad'):
"""Conv2D wrapper."""
shape = (out_channels, in_channels, kernel_size, kernel_size)
- weights = initializer("XavierUniform", shape=shape, dtype=mstype.float32).to_tensor()
+ weights = initializer("XavierUniform", shape=shape, dtype=mstype.float32).init_data()
shape_bias = (out_channels,)
biass = bias_init_zeros(shape_bias)
return nn.Conv2d(in_channels, out_channels,
diff --git a/research/cv/tracktor/src/FasterRcnn/rcnn.py b/research/cv/tracktor/src/FasterRcnn/rcnn.py
index 89a71c03dbcc2d74a4f899177adb8c6951e662ca..599895b8e812776f30286297740fdd5aac7500eb 100644
--- a/research/cv/tracktor/src/FasterRcnn/rcnn.py
+++ b/research/cv/tracktor/src/FasterRcnn/rcnn.py
@@ -88,16 +88,16 @@ class Rcnn(nn.Cell):
self.test_batch_size = cfg.test_batch_size
shape_0 = (self.rcnn_fc_out_channels, representation_size)
- weights_0 = initializer("XavierUniform", shape=shape_0[::-1], dtype=self.ms_type).to_tensor()
+ weights_0 = initializer("XavierUniform", shape=shape_0[::-1], dtype=self.ms_type).init_data()
shape_1 = (self.rcnn_fc_out_channels, self.rcnn_fc_out_channels)
- weights_1 = initializer("XavierUniform", shape=shape_1[::-1], dtype=self.ms_type).to_tensor()
+ weights_1 = initializer("XavierUniform", shape=shape_1[::-1], dtype=self.ms_type).init_data()
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=self.ms_type).to_tensor()
+ dtype=self.ms_type).init_data()
reg_weight = initializer('Normal', shape=[num_classes * 4, self.rcnn_fc_out_channels][::-1],
- dtype=self.ms_type).to_tensor()
+ dtype=self.ms_type).init_data()
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)
diff --git a/research/cv/tracktor/src/FasterRcnn/rpn.py b/research/cv/tracktor/src/FasterRcnn/rpn.py
index f4c92caf1a013f309dceb88a87cca666c00fcdaa..0cc498238acdba1aa39cfefe07209c794f5f1f9d 100644
--- a/research/cv/tracktor/src/FasterRcnn/rpn.py
+++ b/research/cv/tracktor/src/FasterRcnn/rpn.py
@@ -167,18 +167,18 @@ class RPN(nn.Cell):
shp_weight_conv = (feat_channels, in_channels, 3, 3)
shp_bias_conv = (feat_channels,)
- weight_conv = initializer('Normal', shape=shp_weight_conv, dtype=self.ms_type).to_tensor()
- bias_conv = initializer(0, shape=shp_bias_conv, dtype=self.ms_type).to_tensor()
+ weight_conv = initializer('Normal', shape=shp_weight_conv, dtype=self.ms_type).init_data()
+ bias_conv = initializer(0, shape=shp_bias_conv, dtype=self.ms_type).init_data()
shp_weight_cls = (num_anchors * cls_out_channels, feat_channels, 1, 1)
shp_bias_cls = (num_anchors * cls_out_channels,)
- weight_cls = initializer('Normal', shape=shp_weight_cls, dtype=self.ms_type).to_tensor()
- bias_cls = initializer(0, shape=shp_bias_cls, dtype=self.ms_type).to_tensor()
+ weight_cls = initializer('Normal', shape=shp_weight_cls, dtype=self.ms_type).init_data()
+ bias_cls = initializer(0, shape=shp_bias_cls, dtype=self.ms_type).init_data()
shp_weight_reg = (num_anchors * 4, feat_channels, 1, 1)
shp_bias_reg = (num_anchors * 4,)
- weight_reg = initializer('Normal', shape=shp_weight_reg, dtype=self.ms_type).to_tensor()
- bias_reg = initializer(0, shape=shp_bias_reg, dtype=self.ms_type).to_tensor()
+ weight_reg = initializer('Normal', shape=shp_weight_reg, dtype=self.ms_type).init_data()
+ bias_reg = initializer(0, shape=shp_bias_reg, dtype=self.ms_type).init_data()
for i in range(num_layers):
rpn_reg_cls_block = RpnRegClsBlock(in_channels, feat_channels, num_anchors, cls_out_channels, \