def __init__(self):
super().__init__()
self.conv1 = Conv2d(3, 128, 3, padding=1, bias=False)
self.conv2 = Conv2d(3, 128, 3, dilation=2, bias=False)
self.bn1 = BatchNorm1d(128)
self.bn2 = BatchNorm2d(128)
self.pooling = MaxPool2d(kernel_size=2, padding=0)
modules = OrderedDict()
modules["depthwise"] = Conv2d(
256,
256,
3,
1,
0,
groups=256,
bias=False,
)
modules["pointwise"] = Conv2d(
256,
256,
kernel_size=1,
stride=1,
padding=0,
bias=True,
)
self.submodule1 = Sequential(modules)
self.list1 = [Dropout(drop_prob=0.1), [Softmax(axis=100)]]
self.tuple1 = (
Dropout(drop_prob=0.1),
(Softmax(axis=100), Dropout(drop_prob=0.2)),
)
self.dict1 = {"Dropout": Dropout(drop_prob=0.1)}
self.fc1 = Linear(512, 1024)
def __init__(self):
super().__init__()
self.conv1 = Conv2d(3, 128, 3, stride=2, bias=False)
self.conv2 = Conv2d(3, 128, 3, padding=1, bias=False)
self.conv3 = Conv2d(3, 128, 3, dilation=2, bias=False)
self.bn1 = BatchNorm2d(128)
self.bn2 = BatchNorm1d(128)
self.dropout = Dropout(drop_prob=0.1)
self.softmax = Softmax(axis=100)
self.pooling = MaxPool2d(kernel_size=2, padding=0)
self.submodule1 = Sequential(Dropout(drop_prob=0.1), Softmax(axis=100),)
self.fc1 = Linear(512, 1024)
def __init__(self, config, num_labels, bert=None):
if bert is None:
self.bert = BertModel(config)
else:
self.bert = bert
self.num_labels = num_labels
self.dropout = Dropout(config.hidden_dropout_prob)
self.classifier = Linear(config.hidden_size, num_labels)
def __init__(self, config):
super(BertEmbeddings, self).__init__()
self.word_embeddings = Embedding(config.vocab_size, config.hidden_size)
self.position_embeddings = Embedding(config.max_position_embeddings,
config.hidden_size)
self.token_type_embeddings = Embedding(config.type_vocab_size,
config.hidden_size)
# self.LayerNorm is not snake-cased to stick with TensorFlow model variable name and be able to load
# any TensorFlow checkpoint file
self.LayerNorm = BertLayerNorm(config.hidden_size, eps=1e-12)
self.dropout = Dropout(config.hidden_dropout_prob)
def __init__(self, config):
super().__init__()
if config.hidden_size % config.num_attention_heads != 0:
raise ValueError(
"The hidden size (%d) is not a multiple of the number of attention "
"heads (%d)" % (config.hidden_size, config.num_attention_heads)
)
self.num_attention_heads = config.num_attention_heads
self.attention_head_size = int(config.hidden_size / config.num_attention_heads)
self.all_head_size = self.num_attention_heads * self.attention_head_size
self.query = Linear(config.hidden_size, self.all_head_size)
self.key = Linear(config.hidden_size, self.all_head_size)
self.value = Linear(config.hidden_size, self.all_head_size)
self.dropout = Dropout(config.attention_probs_dropout_prob)
def __init__(self, config):
super(BertOutput, self).__init__()
self.dense = Linear(config.intermediate_size, config.hidden_size)
self.LayerNorm = BertLayerNorm(config.hidden_size, eps=1e-12)
self.dropout = Dropout(config.hidden_dropout_prob)
def __init__(self, config):
super().__init__()
self.dense = Linear(config.hidden_size, config.hidden_size)
self.LayerNorm = BertLayerNorm(config.hidden_size, eps=1e-12)
self.dropout = Dropout(config.hidden_dropout_prob)