本文整理汇总了Python中mxnet.gluon.nn.Embedding方法的典型用法代码示例。如果您正苦于以下问题:Python nn.Embedding方法的具体用法?Python nn.Embedding怎么用?Python nn.Embedding使用的例子?那么, 这里精选的方法代码示例或许可以为您提供帮助。您也可以进一步了解该方法所在类mxnet.gluon.nn
的用法示例。
在下文中一共展示了nn.Embedding方法的15个代码示例,这些例子默认根据受欢迎程度排序。您可以为喜欢或者感觉有用的代码点赞,您的评价将有助于系统推荐出更棒的Python代码示例。
示例1: __init__
# 需要导入模块: from mxnet.gluon import nn [as 别名]
# 或者: from mxnet.gluon.nn import Embedding [as 别名]
def __init__(self, vocab_size, tag2idx, embedding_dim, hidden_dim):
super(BiLSTM_CRF, self).__init__()
with self.name_scope():
self.embedding_dim = embedding_dim
self.hidden_dim = hidden_dim
self.vocab_size = vocab_size
self.tag2idx = tag2idx
self.tagset_size = len(tag2idx)
self.word_embeds = nn.Embedding(vocab_size, embedding_dim)
self.lstm = rnn.LSTM(hidden_dim // 2, num_layers=1, bidirectional=True)
# Maps the output of the LSTM into tag space.
self.hidden2tag = nn.Dense(self.tagset_size)
# Matrix of transition parameters. Entry i,j is the score of
# transitioning *to* i *from* j.
self.transitions = self.params.get("crf_transition_matrix",
shape=(self.tagset_size, self.tagset_size))
self.hidden = self.init_hidden()
示例2: test_summary
# 需要导入模块: from mxnet.gluon import nn [as 别名]
# 或者: from mxnet.gluon.nn import Embedding [as 别名]
def test_summary():
net = gluon.model_zoo.vision.resnet50_v1()
net.initialize()
net.summary(mx.nd.ones((32, 3, 224, 224)))
net2 = nn.Sequential()
with net2.name_scope():
net2.add(nn.Embedding(40, 30))
net2.add(gluon.rnn.LSTM(30))
net2.add(nn.Dense(40, flatten=False, params=net2[0].params))
net2.initialize()
net2.summary(mx.nd.ones((80, 32)))
net3 = gluon.rnn.LSTM(30)
net3.initialize()
begin_state = net3.begin_state(32)
net3.summary(mx.nd.ones((80, 32, 5)), begin_state)
net.hybridize()
assert_raises(AssertionError, net.summary, mx.nd.ones((32, 3, 224, 224)))
示例3: net_define
# 需要导入模块: from mxnet.gluon import nn [as 别名]
# 或者: from mxnet.gluon.nn import Embedding [as 别名]
def net_define():
net = nn.Sequential()
with net.name_scope():
net.add(nn.Embedding(config.MAX_WORDS, config.EMBEDDING_DIM))
net.add(rnn.GRU(128,layout='NTC',bidirectional=True, num_layers=2, dropout=0.2))
net.add(transpose(axes=(0,2,1)))
# net.add(nn.MaxPool2D(pool_size=(config.MAX_LENGTH,1)))
# net.add(nn.Conv2D(128, kernel_size=(101,1), padding=(50,0), groups=128,activation='relu'))
net.add(PrimeConvCap(8,32, kernel_size=(1,1), padding=(0,0)))
# net.add(AdvConvCap(8,32,8,32, kernel_size=(1,1), padding=(0,0)))
net.add(CapFullyBlock(8*(config.MAX_LENGTH)/2, num_cap=12, input_units=32, units=16, route_num=5))
# net.add(CapFullyBlock(8*(config.MAX_LENGTH-8), num_cap=12, input_units=32, units=16, route_num=5))
# net.add(CapFullyBlock(8, num_cap=12, input_units=32, units=16, route_num=5))
net.add(nn.Dropout(0.2))
# net.add(LengthBlock())
net.add(nn.Dense(6, activation='sigmoid'))
net.initialize(init=init.Xavier())
return net
示例4: net_define_eu
# 需要导入模块: from mxnet.gluon import nn [as 别名]
# 或者: from mxnet.gluon.nn import Embedding [as 别名]
def net_define_eu():
net = nn.Sequential()
with net.name_scope():
net.add(nn.Embedding(config.MAX_WORDS, config.EMBEDDING_DIM))
net.add(rnn.GRU(128,layout='NTC',bidirectional=True, num_layers=1, dropout=0.2))
net.add(transpose(axes=(0,2,1)))
net.add(nn.GlobalMaxPool1D())
'''
net.add(FeatureBlock1())
'''
net.add(extendDim(axes=3))
net.add(PrimeConvCap(16, 32, kernel_size=(1,1), padding=(0,0),strides=(1,1)))
net.add(CapFullyNGBlock(16, num_cap=12, input_units=32, units=16, route_num=3))
net.add(nn.Dropout(0.2))
net.add(nn.Dense(6, activation='sigmoid'))
net.initialize(init=init.Xavier())
return net
示例5: __init__
# 需要导入模块: from mxnet.gluon import nn [as 别名]
# 或者: from mxnet.gluon.nn import Embedding [as 别名]
def __init__(
self, num_bins: int, size: Optional[int] = None, *args, **kwargs
):
super().__init__(*args, **kwargs)
self.num_bins = num_bins
if size is None:
self.size = round(self.num_bins ** (1 / 4))
else:
self.size = size
self.embedding = nn.Embedding(
input_dim=self.num_bins, output_dim=self.size
)
# noinspection PyMethodOverriding
示例6: __init__
# 需要导入模块: from mxnet.gluon import nn [as 别名]
# 或者: from mxnet.gluon.nn import Embedding [as 别名]
def __init__(self, vocab_size, tag2idx, embedding_dim, hidden_dim,START_TAG = "<START>",STOP_TAG = "<STOP>",ctx=mx.cpu()):
super(BiLSTM_CRF, self).__init__()
with self.name_scope():
self.embedding_dim = embedding_dim
self.hidden_dim = hidden_dim
self.vocab_size = vocab_size
self.tag2idx = tag2idx
self.START_TAG = START_TAG
self.STOP_TAG = STOP_TAG
self.tagset_size = len(tag2idx)
self.ctx = ctx
self.word_embeds = nn.Embedding(vocab_size, embedding_dim)
self.lstm = rnn.LSTM(hidden_dim // 2, num_layers=1, bidirectional=True)
self.hidden2tag = nn.Dense(self.tagset_size)
self.transitions = nd.random.normal(shape=(self.tagset_size, self.tagset_size),ctx=ctx)
self.hidden = self.init_hidden()
示例7: __init__
# 需要导入模块: from mxnet.gluon import nn [as 别名]
# 或者: from mxnet.gluon.nn import Embedding [as 别名]
def __init__(self, vocab_size, tag2idx, embedding_dim, hidden_dim):
super(BiLSTM_CRF, self).__init__()
with self.name_scope():
self.embedding_dim = embedding_dim
self.hidden_dim = hidden_dim
self.vocab_size = vocab_size
self.tag2idx = tag2idx
self.tagset_size = len(tag2idx)
self.word_embeds = nn.Embedding(vocab_size, embedding_dim)
self.lstm = rnn.LSTM(hidden_dim // 2, num_layers=1, bidirectional=True)
# Maps the output of the LSTM into tag space.
self.hidden2tag = nn.Dense(self.tagset_size)
# Matrix of transition parameters. Entry i,j is the score of
# transitioning *to* i *from* j.
self.transitions = nd.random.normal(shape=(self.tagset_size, self.tagset_size))
self.hidden = self.init_hidden()
示例8: __init__
# 需要导入模块: from mxnet.gluon import nn [as 别名]
# 或者: from mxnet.gluon.nn import Embedding [as 别名]
def __init__(self, mode, vocab_size, num_embed, num_hidden,
num_layers, dropout=0.5, tie_weights=False, **kwargs):
super(RNNModel, self).__init__(**kwargs)
with self.name_scope():
self.drop = nn.Dropout(dropout)
self.encoder = nn.Embedding(vocab_size, num_embed,
weight_initializer=mx.init.Uniform(0.1))
if mode == 'rnn_relu':
self.rnn = rnn.RNN(num_hidden, num_layers, dropout=dropout,
input_size=num_embed)
elif mode == 'rnn_tanh':
self.rnn = rnn.RNN(num_hidden, num_layers, 'tanh', dropout=dropout,
input_size=num_embed)
elif mode == 'lstm':
self.rnn = rnn.LSTM(num_hidden, num_layers, dropout=dropout,
input_size=num_embed)
elif mode == 'gru':
self.rnn = rnn.GRU(num_hidden, num_layers, dropout=dropout,
input_size=num_embed)
else:
raise ValueError("Invalid mode %s. Options are rnn_relu, "
"rnn_tanh, lstm, and gru"%mode)
if tie_weights:
self.decoder = nn.Dense(vocab_size, in_units=num_hidden,
params=self.encoder.params)
else:
self.decoder = nn.Dense(vocab_size, in_units=num_hidden)
self.num_hidden = num_hidden
示例9: __init__
# 需要导入模块: from mxnet.gluon import nn [as 别名]
# 或者: from mxnet.gluon.nn import Embedding [as 别名]
def __init__(self, sim_hidden_size, rnn_hidden_size, embed_in_size, embed_dim, num_classes):
super(SimilarityTreeLSTM, self).__init__()
with self.name_scope():
self.embed = nn.Embedding(embed_in_size, embed_dim, prefix='word_embed_')
self.childsumtreelstm = ChildSumLSTMCell(rnn_hidden_size, input_size=embed_dim)
self.similarity = Similarity(sim_hidden_size, rnn_hidden_size, num_classes)
示例10: test_embedding
# 需要导入模块: from mxnet.gluon import nn [as 别名]
# 或者: from mxnet.gluon.nn import Embedding [as 别名]
def test_embedding():
def check_embedding(sparse_grad):
layer = gluon.nn.Embedding(10, 100, sparse_grad=sparse_grad)
layer.initialize()
x = mx.nd.array([3,4,2,0,1])
with mx.autograd.record():
y = layer(x)
y.backward()
assert (layer.weight.grad().asnumpy()[:5] == 1).all()
assert (layer.weight.grad().asnumpy()[5:] == 0).all()
def check_embedding_large_input(sparse_grad):
embedding = mx.gluon.nn.Embedding(10, 1, sparse_grad=True)
embedding.initialize()
embedding.hybridize()
shape = (20481,)
with mx.autograd.record():
emb_in = embedding(mx.nd.ones(shape))
loss = emb_in.sum()
loss.backward()
assert embedding.weight.grad().data.sum().asscalar() == 20481
check_embedding(True)
check_embedding(False)
check_embedding_large_input(True)
check_embedding_large_input(False)
示例11: test_dtype
# 需要导入模块: from mxnet.gluon import nn [as 别名]
# 或者: from mxnet.gluon.nn import Embedding [as 别名]
def test_dtype():
net = mx.gluon.model_zoo.vision.resnet18_v1()
net.initialize()
net.cast('float64')
with mx.autograd.record():
y = net(mx.nd.ones((16, 3, 32, 32), dtype='float64'))
y.backward()
net = mx.gluon.model_zoo.vision.resnet18_v1()
net.initialize()
net.hybridize()
net(mx.nd.ones((16, 3, 32, 32), dtype='float32'))
net.cast('float64')
net(mx.nd.ones((16, 3, 32, 32), dtype='float64'))
mx.nd.waitall()
class Net(gluon.Block):
def __init__(self, in_dim, output_dim):
super(Net, self).__init__()
with self.name_scope():
self.embed = gluon.nn.Embedding(input_dim=in_dim, output_dim=output_dim,dtype=np.float64)
self.dense = gluon.nn.Dense(2, dtype=np.float64)
def forward(self, x):
e = self.embed(x)
assert(e.dtype == np.float64)
y = self.dense(e)
assert(y.dtype == np.float64)
return y
net = Net(5, 10)
net.initialize()
out = net(mx.nd.ones((3,), dtype=np.float64))
mx.nd.waitall()
示例12: test_sparse_hybrid_block_grad
# 需要导入模块: from mxnet.gluon import nn [as 别名]
# 或者: from mxnet.gluon.nn import Embedding [as 别名]
def test_sparse_hybrid_block_grad():
class Embedding(mx.gluon.HybridBlock):
def __init__(self, num_tokens, embedding_size):
super(Embedding, self).__init__()
self.num_tokens = num_tokens
with self.name_scope():
self.embedding = mx.gluon.nn.Embedding(
num_tokens, embedding_size, sparse_grad=True)
def hybrid_forward(self, F, words):
emb = self.embedding(words)
return emb + F.ones_like(emb)
embedding = Embedding(20, 3)
embedding.initialize()
embedding.hybridize()
with mx.autograd.record():
emb0 = embedding(mx.nd.arange(10)).sum()
emb1 = embedding(mx.nd.arange(10)).sum()
loss = emb0 + emb1
loss.backward()
grad = embedding.embedding.weight.grad().asnumpy()
assert (grad[:10] == 2).all()
assert (grad[10:] == 0).all()
示例13: __init__
# 需要导入模块: from mxnet.gluon import nn [as 别名]
# 或者: from mxnet.gluon.nn import Embedding [as 别名]
def __init__(self,**kwargs):
super(SMN_Last,self).__init__(**kwargs)
with self.name_scope():
self.Embed = nn.Embedding(411721,256)
# agg param
self.gru = rnn.GRU(1024,2,layout='NTC')
self.mlp_1 = nn.Dense(units=60,flatten=False,activation='relu')
self.mlp_2 = nn.Dense(units=1,flatten=False)
# lstm param
self.topic_embedding = self.params.get('param_test',shape=(1024,2000))
示例14: __init__
# 需要导入模块: from mxnet.gluon import nn [as 别名]
# 或者: from mxnet.gluon.nn import Embedding [as 别名]
def __init__(self):
super(Net, self).__init__()
with self.name_scope():
self.embedding = nn.Embedding(vocab_size,region_size*emb_size)
self.embedding_region = nn.Embedding(vocab_size,emb_size)
self.max_pool = nn.GlobalMaxPool1D()
self.dense = nn.Dense(n_classes)
self.dense1 = nn.Dense(max_sequence_length*2,activation='relu')
self.dense2 = nn.Dense(1)
示例15: __init__
# 需要导入模块: from mxnet.gluon import nn [as 别名]
# 或者: from mxnet.gluon.nn import Embedding [as 别名]
def __init__(self, vocab_size=VOCAB_SIZE, embedding_size=32,
rnn_size=128, num_layers=2, drop_rate=0.0, **kwargs):
super(Model, self).__init__(**kwargs)
self.args = {"vocab_size": vocab_size, "embedding_size": embedding_size,
"rnn_size": rnn_size, "num_layers": num_layers,
"drop_rate": drop_rate}
with self.name_scope():
self.encoder = nn.Embedding(vocab_size, embedding_size)
self.dropout = nn.Dropout(drop_rate)
self.rnn = rnn.LSTM(rnn_size, num_layers, dropout=drop_rate,
input_size=embedding_size)
self.decoder = nn.Dense(vocab_size, in_units=rnn_size)