| /external/tensorflow/tensorflow/python/keras/layers/ |
| D | kernelized_test.py | 69 _ = kernel_layers.RandomFourierFeatures(output_dim=-3, scale=2.0)
83 _ = kernel_layers.RandomFourierFeatures(output_dim=10, scale=0.0)
88 rff_layer = kernel_layers.RandomFourierFeatures(output_dim=10, scale=3.0)
100 output_dim=10,
104 self.assertEqual(rff_layer.output_dim, 10)
115 output_dim=10,
135 kernel_layers.RandomFourierFeatures(output_dim=4, name='rff')(inputs)
136 kernel_layers.RandomFourierFeatures(output_dim=10, scale=2.0)(inputs)
142 output_dim=7, name='random_fourier_features', trainable=True)
153 output_dim=5,
[all …]
|
| D | kernelized.py | 132 output_dim, argument
138 if output_dim <= 0:
141 output_dim))
152 self.output_dim = output_dim
173 self.kernel_initializer, shape=(input_dim, self.output_dim))
177 shape=(input_dim, self.output_dim),
184 shape=(self.output_dim,),
216 return input_shape[:-1].concatenate(self.output_dim)
223 'output_dim': self.output_dim,
|
| D | embeddings.py | 93 output_dim, argument
110 self.output_dim = output_dim
130 shape=(self.input_dim, self.output_dim),
137 shape=(self.input_dim, self.output_dim),
153 return input_shape + (self.output_dim,)
172 return (input_shape[0],) + tuple(in_lens) + (self.output_dim,)
184 'output_dim': self.output_dim,
|
| D | wrappers_test.py | 302 output_dim = 2
306 target_dim = 2 * output_dim if mode == 'concat' else output_dim
313 rnn(output_dim), merge_mode=mode, input_shape=(timesteps, dim)))
347 output_dim = 2
353 rnn(output_dim), input_shape=(timesteps, dim)))
366 output_dim = 2
371 target_dim = 2 * output_dim if mode == 'concat' else output_dim
377 rnn(output_dim, return_sequences=True),
380 model.add(keras.layers.Bidirectional(rnn(output_dim), merge_mode=mode))
387 rnn(output_dim), merge_mode=mode)(inputs)
[all …]
|
| D | cudnn_recurrent_test.py | 398 output_dim = 2
402 target_dim = 2 * output_dim if mode == 'concat' else output_dim
409 rnn(output_dim), merge_mode=mode, input_shape=(None, dim)))
422 rnn(output_dim, return_sequences=True),
425 model.add(keras.layers.Bidirectional(rnn(output_dim), merge_mode=mode))
432 rnn(output_dim), merge_mode=mode)(
441 rnn(output_dim, stateful=True), merge_mode=mode)(
|
| D | embeddings_test.py | 78 layer = keras.layers.Embedding(output_dim=2, input_dim=2)
88 l = keras.layers.Embedding(output_dim=2, input_dim=2)
|
| D | recurrent.py | 152 output_dim = cell.output_size
154 output_dim = cell.state_size[0]
156 output_dim = cell.state_size
158 tensor_shape.as_shape(output_dim).as_list())
450 output_dim = tensor_shape.as_shape(flat_output_size).as_list()
453 output_shape = tensor_shape.as_shape([time_step, batch] + output_dim)
455 output_shape = tensor_shape.as_shape([batch, time_step] + output_dim)
457 output_shape = tensor_shape.as_shape([batch] + output_dim)
|
| /external/tensorflow/tensorflow/python/keras/saving/ |
| D | hdf5_format_test.py | 103 output_dim = 3
117 (keras.layers.Conv1D(output_dim, size, use_bias=False)),
118 [np.random.random((output_dim, input_dim, size, 1))],
122 (keras.layers.Conv2D(output_dim, size,
124 [np.random.random((output_dim, input_dim, size, size))],
128 (keras.layers.Conv2DTranspose(output_dim, size,
131 [np.random.random((output_dim, input_dim, size, size))],
135 (keras.layers.Conv2DTranspose(output_dim, size,
138 [np.random.random((size, size, input_dim, output_dim))],
142 (keras.layers.Conv3D(output_dim, size,
[all …]
|
| /external/tensorflow/tensorflow/compiler/xla/client/lib/ |
| D | conv_grad_size_util.cc | 70 TF_ASSIGN_OR_RETURN(SpatialDimensionOutputSizeAndPadding output_dim, in ConvGradExtractAndVerifyDimension()
73 if (output_size != output_dim.output_size) { in ConvGradExtractAndVerifyDimension()
76 output_size, ", computed = ", output_dim.output_size, in ConvGradExtractAndVerifyDimension()
83 dim.output_size = (output_dim.output_size - 1) * stride + 1; in ConvGradExtractAndVerifyDimension()
85 dim.pad_before = effective_filter_size - 1 - output_dim.pad_before; in ConvGradExtractAndVerifyDimension()
|
| /external/tensorflow/tensorflow/contrib/kernel_methods/python/mappers/ |
| D | random_fourier_features.py | 60 def __init__(self, input_dim, output_dim, stddev=1.0, seed=1, name=None): argument
82 self._output_dim = output_dim
104 def output_dim(self): member in RandomFourierFeatureMapper
|
| D | dense_kernel_mapper.py | 56 def output_dim(self): member in DenseKernelMapper
|
| /external/tensorflow/tensorflow/python/keras/applications/ |
| D | applications_test.py | 46 def test_feature_extration_model(self, model_fn, output_dim): argument
49 self.assertEqual(model.output_shape[-1], output_dim)
|
| /external/tensorflow/tensorflow/lite/kernels/internal/ |
| D | batch_to_space_nd_test.cc | 25 int input_dim, int output_dim) { in GetIndexRange() argument
29 output_dim, &index_start, &index_end); in GetIndexRange()
|
| /external/tensorflow/tensorflow/python/debug/examples/ |
| D | debug_mnist.py | 77 def nn_layer(input_tensor, input_dim, output_dim, layer_name, act=tf.nn.relu): argument
83 weights = weight_variable([input_dim, output_dim])
85 biases = bias_variable([output_dim])
|
| /external/tensorflow/tensorflow/core/ops/ |
| D | image_ops.cc | 167 DimensionHandle output_dim; in CombinedNMSShapeFn() local
170 TF_RETURN_IF_ERROR(c->MakeDimForScalarInput(3, &output_dim)); in CombinedNMSShapeFn()
171 if (c->ValueKnown(output_dim) && c->Value(output_dim) <= 0) { in CombinedNMSShapeFn()
181 output_size = c->Value(output_dim); in CombinedNMSShapeFn()
188 output_size = std::min(c->Value(output_dim), in CombinedNMSShapeFn()
855 DimensionHandle output_dim; in __anon6a71d27f1802() local
856 TF_RETURN_IF_ERROR(c->MakeDimForScalarInput(2, &output_dim)); in __anon6a71d27f1802()
857 c->set_output(0, c->MakeShape({output_dim})); in __anon6a71d27f1802()
|
| /external/tensorflow/tensorflow/compiler/xla/service/ |
| D | indexed_array_analysis.cc | 215 for (int64 output_dim : output_dims) { in FoldGatherOfGather() local
216 simulated_index.insert(simulated_index.begin() + output_dim, in FoldGatherOfGather()
537 for (int64 output_dim : operand->output_dims()) { in ReshapeToAddDegenerateDims() local
538 output_dims_bitvector[output_dim] = true; in ReshapeToAddDegenerateDims()
564 for (int64 output_dim : new_output_dims) { in ReshapeToAddDegenerateDims() local
565 EraseAt(&new_source_shape_dims, output_dim); in ReshapeToAddDegenerateDims()
711 int64 output_dim = scalar_indexed->output_dims()[i]; in FoldReshapeOfGatherNoDegenerateDims() local
713 reshape_passthrough_dims, output_dim); in FoldReshapeOfGatherNoDegenerateDims()
877 auto is_broadcasted_dim = [&](int64 output_dim) { in ComputeArrayForElementwiseBinaryOp() argument
878 return absl::c_find(broadcast_dims, output_dim) == broadcast_dims.end(); in ComputeArrayForElementwiseBinaryOp()
|
| /external/tensorflow/tensorflow/examples/tutorials/mnist/ |
| D | mnist_with_summaries.py | 78 def nn_layer(input_tensor, input_dim, output_dim, layer_name, act=tf.nn.relu): argument
89 weights = weight_variable([input_dim, output_dim])
92 biases = bias_variable([output_dim])
|
| /external/tensorflow/tensorflow/python/keras/utils/ |
| D | multi_gpu_utils_test.py | 43 output_dim = 1
55 model.add(keras.layers.Dense(output_dim))
58 y = np.random.random((num_samples, output_dim))
|
| /external/tensorflow/tensorflow/contrib/distribute/python/ |
| D | keras_embedding_model_correctness_test.py | 38 output_dim=10)(word_ids)
92 output_dim=10,
|
| D | keras_lstm_model_correctness_test.py | 38 output_dim=10)(word_ids)
|
| D | keras_stateful_lstm_model_correctness_test.py | 59 output_dim=10)(word_ids)
|
| /external/tensorflow/tensorflow/python/keras/ |
| D | backend_test.py | 1006 output_dim = 3
1012 (num_samples, output_dim)).astype(np.float32)
1013 w_i_val = np.random.random((input_dim, output_dim)).astype(np.float32)
1014 w_o_val = np.random.random((output_dim, output_dim)).astype(np.float32)
1052 self.assertEqual(last_output.shape.as_list(), [num_samples, output_dim])
1054 [num_samples, timesteps, output_dim])
1056 self.assertEqual(state.shape.as_list(), [num_samples, output_dim])
1096 output_dim = 3
1102 (num_samples, output_dim)).astype(np.float32)
1103 w_i_val = np.random.random((input_dim, output_dim)).astype(np.float32)
[all …]
|
| D | optimizers_test.py | 34 def _get_model(input_dim, num_hidden, output_dim): argument
39 model.add(keras.layers.Dense(output_dim, activation='softmax'))
|
| /external/tensorflow/tensorflow/python/kernel_tests/ |
| D | broadcast_to_ops_test.py | 60 for output_dim in range(input_dim, 6):
63 output_shape = [2] * output_dim
|
| /external/tensorflow/tensorflow/contrib/kernel_methods/python/ |
| D | kernel_estimators.py | 93 new_dim = sum(mapper.output_dim for mapper in column_kernel_mappers)
|