MCPcopy Create free account
hub / github.com/apple/ml-pointersect / ParamGraves

Class ParamGraves

cdslib/core/nn/modules/graves.py:27–159  ·  view source on GitHub ↗

A dictionary that contains the hyper-parameters of Network_Graves.

Source from the content-addressed store, hash-verified

25
26
27class ParamGraves(HyperParams):
28 """
29 A dictionary that contains the hyper-parameters of Network_Graves.
30 """
31
32 def __init__(
33 self,
34 dim_x: int = HyperParams.TBD.INT, # dimension of the input
35 dim_c: int = HyperParams.TBD.INT, # dimension of the content
36 dim_p: int = HyperParams.TBD.INT, # dimension of the output
37 dim_z: int = 0, # dimension of the optional z
38 # attn_rnn
39 num_attn_rnn_layers: int = 1, # number of layers of the attn_rnn
40 dim_attn_rnn: T.Union[int, T.Sequence[int]] = 512, # dimension of the attn_rnn
41 # attn_layer
42 num_window_attn_mixtures: int = 10, # number of mixtures in the gaussian attention layer
43 num_window_attn_layers: int = 1, # number of layers in the gaussian attention layer
44 dim_window_attn_layers: T.Union[int, T.Sequence[int]] = 128, # , len = num_window_attn_layers-1
45 # decode_rnn
46 num_decode_rnn_layers: int = 2,
47 dim_decode_rnn: int = 512,
48 # output_layer
49 output_layer_type: str = "StackedLinearLayers",
50 feed_z_to_decode_rnn: bool = True,
51 num_output_layers: int = 1, # int
52 dim_output_layers: T.Union[int, T.Sequence[int]] = 128,
53 # T.Union[int, T.Sequence[int]], len = num_output_layers-1
54 output_layer_nonlinearity="relu",
55 output_layer_add_norm_layer=False,
56 output_layer_norm_fun: T.Callable = torch.nn.LayerNorm,
57 output_layer_dropout_prob: float = 0,
58 output_layer_normalize: bool = True,
59 output_layer_normalize_first: bool = True,
60 output_layer_init_freq_first_layer: float = 1.0,
61 output_layer_init_freq_other_layer: float = 25.0,
62 # style mapping layer
63 num_mapping_layers: int = 4,
64 dim_mapping_layers: int = 256,
65 mapping_layer_nonlinearity: str = "silu",
66 mapping_layer_dropout_prob: float = 0.0,
67 ):
68 """
69 Args:
70 dim_x: int
71 Dimension of the past input sequence xs
72 dim_c: int
73 Dimension of the content cs
74 dim_p: int
75 Output feature dimension of the network
76 dim_z: int = 0
77 Dimension of an additional latent vector zt if zt_fun is provided in forward. Default: 0
78
79 .. attn_rnn
80
81 num_attn_rnn_layers: int = 1
82 Number of layers in the attention lstm
83 dim_attn_rnn: T.Union[int, T.Sequence[int]] = 512
84 Dimension of the attention lstm. Can be a single integer or a list, one for each layer.

Callers 3

test_1Method · 0.90
__init__Method · 0.85
__init__Method · 0.85

Calls

no outgoing calls

Tested by 1

test_1Method · 0.72