def __init__(self,
in_channels: int,
in_features: Optional[int] = None,
hparams: Optional[Union[HParams, Dict[str, Any]]] = None):
super().__init__(hparams=hparams)
encoder_hparams = utils.dict_fetch(hparams,
Conv1DEncoder.default_hparams())
self._encoder = Conv1DEncoder(in_channels=in_channels,
in_features=in_features,
hparams=encoder_hparams)
# Add an additional dense layer if needed
self._num_classes = self._hparams.num_classes
if self._num_classes > 0:
if self._hparams.num_dense_layers <= 0:
self._encoder.append_layer({"type": "Flatten"})
logit_kwargs = self._hparams.logit_layer_kwargs
if logit_kwargs is None:
logit_kwargs = {}
elif not isinstance(logit_kwargs, HParams):
raise ValueError(
"hparams['logit_layer_kwargs'] must be a dict.")
else:
logit_kwargs = logit_kwargs.todict()
logit_kwargs.update({"out_features": self._num_classes})
self._encoder.append_layer({
"type": "Linear",
"kwargs": logit_kwargs
})
def test_encode(self):
r"""Tests encode.
"""
inputs_1 = torch.ones([128, 32, 300])
encoder_1 = Conv1DEncoder(in_channels=inputs_1.size(1),
in_features=inputs_1.size(2))
self.assertEqual(len(encoder_1.layers), 4)
self.assertIsInstance(encoder_1.layer_by_name("MergeLayer"),
MergeLayer)
for layer in encoder_1.layers[0].layers:
self.assertIsInstance(layer, nn.Sequential)
outputs_1 = encoder_1(inputs_1)
self.assertEqual(outputs_1.size(), torch.Size([128, 256]))
self.assertEqual(outputs_1.size(-1), encoder_1.output_size)
inputs_2 = torch.ones([128, 64, 300])
hparams = {
# Conv layers
"num_conv_layers": 2,
"out_channels": 128,
"kernel_size": [[3, 4, 5], 4],
"other_conv_kwargs": {
"padding": 0
},
# Pooling layers
"pooling": "AvgPool1d",
"pool_size": 2,
"pool_stride": 1,
# Dense layers
"num_dense_layers": 3,
"out_features": [128, 128, 10],
"dense_activation": "ReLU",
"other_dense_kwargs": None,
# Dropout
"dropout_conv": [0, 1, 2],
"dropout_dense": 2
}
network_2 = Conv1DEncoder(in_channels=inputs_2.size(1),
in_features=inputs_2.size(2),
hparams=hparams)
# dropout-merge-dropout-conv-avgpool-dropout-flatten-
# (Sequential(Linear,ReLU))-(Sequential(Linear,ReLU))-dropout-linear
self.assertEqual(len(network_2.layers), 1 + 1 + 1 + 3 + 4 + 1)
self.assertIsInstance(network_2.layer_by_name("MergeLayer"),
MergeLayer)
for layer in network_2.layers[1].layers:
self.assertIsInstance(layer, nn.Sequential)
outputs_2 = network_2(inputs_2)
self.assertEqual(outputs_2.size(), torch.Size([128, 10]))
self.assertEqual(outputs_2.size(-1), network_2.output_size)
def default_hparams() -> Dict[str, Any]:
r"""Returns a dictionary of hyperparameters with default values.
.. code-block:: python
{
# (1) Same hyperparameters as in Conv1DEncoder
...
# (2) Additional hyperparameters
"num_classes": 2,
"logit_layer_kwargs": {
"use_bias": False
},
"name": "conv1d_classifier"
}
Here:
1. Same hyperparameters as in
:class:`~texar.torch.modules.Conv1DEncoder`.
See the :meth:`~texar.torch.modules.Conv1DEncoder.default_hparams`.
An instance of :class:`~texar.torch.modules.Conv1DEncoder` is created
for feature extraction.
2. Additional hyperparameters:
`"num_classes"`: int
Number of classes:
- If `> 0`, an additional :torch_nn:`Linear`
layer is appended to the encoder to compute the logits over
classes.
- If `<= 0`, no dense layer is appended. The number of
classes is assumed to be equal to ``out_features`` of the
final dense layer size of the encoder.
`"logit_layer_kwargs"`: dict
Keyword arguments for the logit :torch_nn:`Linear` layer
constructor, except for argument ``out_features`` which is set
to ``"num_classes"``. Ignored if no extra logit layer is
appended.
`"name"`: str
Name of the classifier.
"""
hparams = Conv1DEncoder.default_hparams()
hparams.update({
"name": "conv1d_classifier",
"num_classes": 2, # set to <=0 to avoid appending output layer
"logit_layer_kwargs": {
"in_features": hparams["out_features"],
"bias": True
}
})
return hparams
def __init__(self,
in_channels: int,
in_features: Optional[int] = None,
hparams: Optional[Union[HParams, Dict[str, Any]]] = None):
super().__init__(hparams=hparams)
encoder_hparams = utils.dict_fetch(hparams,
Conv1DEncoder.default_hparams())
self._encoder = Conv1DEncoder(in_channels=in_channels,
in_features=in_features,
hparams=encoder_hparams)
# Add an additional dense layer if needed
self._num_classes = self._hparams.num_classes
if self._num_classes > 0:
if self._hparams.num_dense_layers <= 0:
if in_features is None:
raise ValueError("'in_features' is required for logits "
"layer when 'num_dense_layers' <= 0")
self._encoder.append_layer({"type": "Flatten"})
ones = torch.ones(1, in_channels, in_features)
input_size = self._encoder._infer_dense_layer_input_size(ones) # pylint: disable=protected-access
self.hparams.logit_layer_kwargs.in_features = input_size[1]
logit_kwargs = self._hparams.logit_layer_kwargs
if logit_kwargs is None:
logit_kwargs = {}
elif not isinstance(logit_kwargs, HParams):
raise ValueError(
"hparams['logit_layer_kwargs'] must be a dict.")
else:
logit_kwargs = logit_kwargs.todict()
logit_kwargs.update({"out_features": self._num_classes})
self._encoder.append_layer({
"type": "Linear",
"kwargs": logit_kwargs
})