Home
last modified time | relevance | path

Searched refs:nn (Results 1 – 25 of 2194) sorted by relevance

12345678910>>...88

/third_party/mindspore/mindspore/lite/examples/export_models/models/
DNetworkInNetwork.py18 import mindspore.nn as nn namespace
24 class NiN(nn.Cell):
29 self.block0 = nn.SequentialCell(
31 … nn.Conv2d(in_channels=num_channel, out_channels=192, kernel_size=5, stride=1, has_bias=False),
32 nn.ReLU(),
33 nn.Conv2d(in_channels=192, out_channels=160, kernel_size=1, stride=1, has_bias=True),
34 nn.ReLU(),
35 nn.Conv2d(in_channels=160, out_channels=96, kernel_size=1, stride=1, has_bias=True),
36 nn.ReLU(),
37 nn.MaxPool2d(kernel_size=3, stride=2, pad_mode='same'),
[all …]
Deffnet.py18 import mindspore.nn as nn namespace
45 class Swish(nn.Cell):
48 self.sigmoid = nn.Sigmoid()
56 class AdaptiveAvgPool(nn.Cell):
66 class SELayer(nn.Cell):
73 …self.conv_reduce = nn.Conv2d(in_channels=channel, out_channels=reduced_chs, kernel_size=1, has_bia…
76 …self.conv_expand = nn.Conv2d(in_channels=reduced_chs, out_channels=channel, kernel_size=1, has_bia…
77 self.act2 = nn.Sigmoid()
88 class DepthwiseSeparableConv(nn.Cell):
98 …self.conv_dw = nn.Conv2d(in_channels=in_chs, out_channels=in_chs, kernel_size=dw_kernel_size, stri…
[all …]
/third_party/mindspore/mindspore/train/train_thor/
Dconvert_utils.py18 import mindspore.nn as nn namespace
28 self._convert_method_map = {nn.Dense: ConvertNetUtils._convert_dense,
29 nn.Embedding: ConvertNetUtils._convert_embedding,
30 nn.Conv2d: ConvertNetUtils._convert_conv2d,
31 nn.EmbeddingLookup: ConvertNetUtils._convert_embeddinglookup}
47 new_subcell = nn.DenseThor(in_channels=subcell.in_channels,
57 new_subcell = nn.DenseThor(in_channels=subcell.in_channels,
74 new_subcell = nn.EmbeddingThor(vocab_size=subcell.vocab_size,
86 new_subcell = nn.EmbeddingLookupThor(vocab_size=subcell.vocab_size,
108 new_subcell = nn.Conv2dThor(in_channel, out_channel,
[all …]
/third_party/skia/third_party/externals/freetype/src/tools/
Dapinames.c69 int nn, len; in names_add() local
80 for ( nn = 0; nn < len; nn++ ) in names_add()
81 h = h * 33 + name[nn]; in names_add()
84 for ( nn = 0; nn < num_names; nn++ ) in names_add()
86 nm = the_names + nn; in names_add()
139 int nn; in names_dump() local
151 for ( nn = 0; nn < num_names; nn++ ) in names_dump()
152 fprintf( out, " %s\n", the_names[nn].name ); in names_dump()
163 for ( nn = 0; nn < num_names; nn++ ) in names_dump()
164 fprintf( out, " _%s\n", the_names[nn].name ); in names_dump()
[all …]
/third_party/freetype/src/tools/
Dapinames.c68 int nn, len; in names_add() local
79 for ( nn = 0; nn < len; nn++ ) in names_add()
80 h = h * 33 + name[nn]; in names_add()
83 for ( nn = 0; nn < num_names; nn++ ) in names_add()
85 nm = the_names + nn; in names_add()
138 int nn; in names_dump() local
150 for ( nn = 0; nn < num_names; nn++ ) in names_dump()
151 fprintf( out, " %s\n", the_names[nn].name ); in names_dump()
162 for ( nn = 0; nn < num_names; nn++ ) in names_dump()
163 fprintf( out, " _%s\n", the_names[nn].name ); in names_dump()
[all …]
/third_party/flutter/skia/third_party/externals/freetype/src/tools/
Dapinames.c68 int nn, len; in names_add() local
79 for ( nn = 0; nn < len; nn++ ) in names_add()
80 h = h * 33 + name[nn]; in names_add()
83 for ( nn = 0; nn < num_names; nn++ ) in names_add()
85 nm = the_names + nn; in names_add()
138 int nn; in names_dump() local
150 for ( nn = 0; nn < num_names; nn++ ) in names_dump()
151 fprintf( out, " %s\n", the_names[nn].name ); in names_dump()
162 for ( nn = 0; nn < num_names; nn++ ) in names_dump()
163 fprintf( out, " _%s\n", the_names[nn].name ); in names_dump()
[all …]
/third_party/mindspore/tests/ut/python/nn/
Dtest_container.py20 import mindspore.nn as nn namespace
27 conv2 = nn.Conv2d(3, 64, (3, 3), stride=2, padding=0)
32 avg_pool = nn.AvgPool2d(kernel_size, stride)
39 m = nn.SequentialCell()
43 m = nn.SequentialCell([conv2])
47 m = nn.SequentialCell([conv2, avg_pool])
51 m = nn.SequentialCell(OrderedDict(
56 m = nn.SequentialCell(OrderedDict(
61 m = nn.SequentialCell(OrderedDict(
67 m = nn.SequentialCell(OrderedDict(
[all …]
Dtest_triu.py20 import mindspore.nn as nn namespace
28 class Net(nn.Cell):
34 triu = nn.Triu()
43 class Net(nn.Cell):
49 triu = nn.Triu()
58 class Net(nn.Cell):
64 triu = nn.Triu()
73 class Net(nn.Cell):
78 triu = nn.Triu()
86 class Net(nn.Cell):
[all …]
Dtest_tril.py20 import mindspore.nn as nn namespace
28 class Net(nn.Cell):
34 tril = nn.Tril()
43 class Net(nn.Cell):
49 tril = nn.Tril()
58 class Net(nn.Cell):
64 tril = nn.Tril()
73 class Net(nn.Cell):
78 tril = nn.Tril()
86 class Net(nn.Cell):
[all …]
Dtest_resizebilinear.py18 import mindspore.nn as nn namespace
27 class Net(nn.Cell):
33 interpolate = nn.ResizeBilinear()
41 class Net(nn.Cell):
47 interpolate = nn.ResizeBilinear()
55 class Net(nn.Cell):
60 interpolate = nn.ResizeBilinear()
68 class Net(nn.Cell):
73 interpolate = nn.ResizeBilinear()
81 class Net(nn.Cell):
[all …]
Dtest_dense.py20 import mindspore.nn as nn namespace
29 nn.Dense(3, 2, None, None)
34 dense = nn.Dense(1, 1, activation='relu')
35 assert isinstance(dense.activation, nn.ReLU)
43 dense = nn.Dense(1, 1, activation=nn.ReLU())
44 assert isinstance(dense.activation, nn.ReLU)
52 dense = nn.Dense(1, 1, activation=P.ReLU())
62 nn.Dense(3, 2, dim_error)
66 nn.Dense(2, 2, shape_error)
68 nn.Dense(3, 3, shape_error)
[all …]
Dtest_loss.py19 from mindspore import nn
25 loss = nn.L1Loss()
32 loss = nn.MSELoss()
41 loss = nn.SoftmaxCrossEntropyWithLogits()
50 loss = nn.SoftmaxCrossEntropyWithLogits(reduction="mean")
59 loss = nn.BCELoss()
68 loss = nn.BCELoss(reduction='mean')
78 loss = nn.BCELoss(weight=weight)
87 loss = nn.CosineEmbeddingLoss()
98 focalloss = nn.FocalLoss()
[all …]
/third_party/mindspore/tests/ut/python/pynative_mode/nn/
Dtest_container.py20 import mindspore.nn as nn namespace
27 conv2 = nn.Conv2d(3, 64, (3, 3), stride=2, padding=0)
32 avg_pool = nn.AvgPool2d(kernel_size, stride)
39 m = nn.SequentialCell()
43 m = nn.SequentialCell([conv2])
47 m = nn.SequentialCell([conv2, avg_pool])
51 m = nn.SequentialCell(OrderedDict(
56 m = nn.SequentialCell(OrderedDict(
61 m = nn.SequentialCell(OrderedDict(
67 m = nn.SequentialCell(OrderedDict(
[all …]
Dtest_dense.py19 import mindspore.nn as nn namespace
28 dense = nn.Dense(3, 2, weight)
39 dense = nn.Dense(3, 2, bias_init=bias)
50 dense = nn.Dense(3, 2, weight, bias)
60 dense = nn.Dense(3, 2, weight, has_bias=False)
70 nn.Dense(3, 2, None, None)
74 dense = nn.Dense(1, 1, activation='relu')
75 assert isinstance(dense.activation, nn.ReLU)
86 nn.Dense(3, 2, dim_error)
90 nn.Dense(2, 2, shape_error)
[all …]
/third_party/mindspore/mindspore/lite/examples/transfer_learning/model/
Deffnet.py3 import mindspore.nn as nn namespace
37 class Swish(nn.Cell):
40 self.sigmoid = nn.Sigmoid()
48 class AdaptiveAvgPool(nn.Cell):
58 class SELayer(nn.Cell):
67 self.conv_reduce = nn.Conv2d(
70 self.conv_expand = nn.Conv2d(
72 self.act2 = nn.Sigmoid()
83 class DepthwiseSeparableConv(nn.Cell):
96 … self.conv_dw = nn.Conv2d(in_channels=in_chs, out_channels=in_chs, kernel_size=dw_kernel_size,
[all …]
/third_party/mindspore/tests/ut/python/ops/
Dtest_nn_ops.py21 import mindspore.nn as nn namespace
42 return nn.Conv2d(in_channels, out_channels,
48 return nn.Conv2d(in_channels, out_channels,
56 class ResidualBlock(nn.Cell):
71 self.bn1 = nn.BatchNorm2d(out_chls)
74 self.bn2 = nn.BatchNorm2d(out_chls)
77 self.bn3 = nn.BatchNorm2d(out_channels)
79 self.relu = nn.ReLU()
84 self.bn_down_sample = nn.BatchNorm2d(out_channels)
159 class VirtualNetWithLoss(nn.Cell):
[all …]
/third_party/mindspore/tests/ut/python/transform/
Dtest_transform.py24 import mindspore.nn as nn namespace
35 return nn.Conv2d(in_channels, out_channels,
43 return nn.Conv2d(in_channels, out_channels,
48 class ResidualBlock(nn.Cell):
63 self.bn1 = nn.BatchNorm2d(out_chls)
66 self.bn2 = nn.BatchNorm2d(out_chls)
69 self.bn3 = nn.BatchNorm2d(out_channels)
71 self.relu = nn.ReLU()
77 self.bn_down_sample = nn.BatchNorm2d(out_channels)
104 class ResNet(nn.Cell):
[all …]
/third_party/mindspore/tests/st/networks/models/deeplabv3/src/backbone/
Dresnet_deeplab.py16 import mindspore.nn as nn namespace
32 return nn.SequentialCell(
33 [nn.Conv2d(in_channel,
40 nn.BatchNorm2d(out_channel, use_batch_statistics=use_batch_statistics),
41 nn.ReLU()]
54 return nn.SequentialCell(
62 nn.BatchNorm2d(channel_multiplier * in_channel, use_batch_statistics=use_batch_statistics),
63 nn.ReLU()]
80 return nn.SequentialCell(
90 nn.BatchNorm2d(channel_multiplier * in_channel, use_batch_statistics=use_batch_statistics),
[all …]
/third_party/mindspore/tests/ut/python/model/
Dres18_example.py20 import mindspore.nn as nn # pylint: disable=C0414 namespace
29 return nn.Conv2d(in_channels, out_channels,
35 return nn.Conv2d(in_channels, out_channels,
39 class ResidualBlock(nn.Cell):
54 self.bn1 = nn.BatchNorm2d(out_chls)
57 self.bn2 = nn.BatchNorm2d(out_chls)
60 self.bn3 = nn.BatchNorm2d(out_channels)
62 self.relu = nn.ReLU()
67 self.bn_down_sample = nn.BatchNorm2d(out_channels)
98 class ResNet18(nn.Cell):
[all …]
/third_party/mindspore/tests/st/probability/dpn/
Dtest_gpu_vae_gan.py22 import mindspore.nn as nn namespace
25 from mindspore.nn.probability.dpn import VAE
26 from mindspore.nn.probability.infer import ELBO, SVI
33 class Encoder(nn.Cell):
36 self.fc1 = nn.Dense(1024, 400)
37 self.relu = nn.ReLU()
38 self.flatten = nn.Flatten()
47 class Decoder(nn.Cell):
50 self.fc1 = nn.Dense(400, 1024)
51 self.relu = nn.ReLU()
[all …]
/third_party/mindspore/tests/st/networks/
Dtest_gpu_alexnet.py24 import mindspore.nn as nn namespace
26 from mindspore.nn import TrainOneStepCell, WithLossCell
27 from mindspore.nn.optim import Momentum
32 class AlexNet(nn.Cell):
36 self.conv1 = nn.Conv2d(3, 96, 11, stride=4, pad_mode="valid")
37 self.conv2 = nn.Conv2d(96, 256, 5, stride=1, pad_mode="same")
38 self.conv3 = nn.Conv2d(256, 384, 3, stride=1, pad_mode="same")
39 self.conv4 = nn.Conv2d(384, 384, 3, stride=1, pad_mode="same")
40 self.conv5 = nn.Conv2d(384, 256, 3, stride=1, pad_mode="same")
41 self.relu = nn.ReLU()
[all …]
/third_party/mindspore/tests/ut/python/utils/
Dtest_initializer_fuzz.py18 import mindspore.nn as nn namespace
22 class Net(nn.Cell):
37 self.conv = nn.Conv2d(a, b, c, pad_mode="valid")
38 self.bn = nn.BatchNorm2d(d)
39 self.relu = nn.ReLU()
40 self.flatten = nn.Flatten()
41 self.fc = nn.Dense(e * f * g, h)
52 class LeNet5(nn.Cell):
75 self.conv1 = nn.Conv2d(a1, a2, a3, pad_mode="valid")
76 self.conv2 = nn.Conv2d(a4, a5, a6, pad_mode="valid")
[all …]
/third_party/mindspore/tests/ut/python/communication/
Dtest_data_parallel_resnet.py21 import mindspore.nn as nn namespace
24 from mindspore.nn.optim import Momentum
31 return nn.Conv2d(in_channels, out_channels,
37 return nn.Conv2d(in_channels, out_channels,
41 class ResidualBlock(nn.Cell):
56 self.bn1 = nn.BatchNorm2d(out_chls)
59 self.bn2 = nn.BatchNorm2d(out_chls)
62 self.bn3 = nn.BatchNorm2d(out_channels)
64 self.relu = nn.ReLU()
69 self.bn_down_sample = nn.BatchNorm2d(out_channels)
[all …]
/third_party/mindspore/tests/st/networks/models/
Dalexnet.py15 import mindspore.nn as nn namespace
19 class AlexNet(nn.Cell):
23 self.conv1 = nn.Conv2d(3, 96, 11, stride=4, pad_mode="valid")
24 self.conv2 = nn.Conv2d(96, 256, 5, stride=1, pad_mode="same")
25 self.conv3 = nn.Conv2d(256, 384, 3, stride=1, pad_mode="same")
26 self.conv4 = nn.Conv2d(384, 384, 3, stride=1, pad_mode="same")
27 self.conv5 = nn.Conv2d(384, 256, 3, stride=1, pad_mode="same")
29 self.max_pool2d = nn.MaxPool2d(kernel_size=3, stride=2)
30 self.flatten = nn.Flatten()
31 self.fc1 = nn.Dense(66256, 4096)
[all …]
/third_party/mindspore/tests/perf_test/
Dresnet_example.py20 import mindspore.nn as nn namespace
26 return nn.Conv2d(in_channels, out_channels,
32 return nn.Conv2d(in_channels, out_channels,
36 class ResidualBlock(nn.Cell):
51 self.bn1 = nn.BatchNorm2d(out_chls)
54 self.bn2 = nn.BatchNorm2d(out_chls)
57 self.bn3 = nn.BatchNorm2d(out_channels)
59 self.relu = nn.ReLU()
64 self.bn_down_sample = nn.BatchNorm2d(out_channels)
95 class ResNet50(nn.Cell):
[all …]

12345678910>>...88