shithub: opus

Info  •  Files  •  Log  •  Branches

Precomputing sizes

--- a/dnn/dump_lpcnet.py

+++ b/dnn/dump_lpcnet.py

@@ -12,6 +12,9 @@

 import h5py

 import re

+max_rnn_neurons = 1

+max_conv_inputs = 1

+

 def printVector(f, vector, name):

     v = np.reshape(vector, (-1));

     #print('static const float ', name, '[', len(v), '] = \n', file=f)

@@ -36,6 +39,7 @@

 Layer.dump_layer = dump_layer_ignore

 def dump_gru_layer(self, f, hf):

+    global max_rnn_neurons

     name = self.name

     print("printing layer " + name + " of type " + self.__class__.__name__)

     weights = self.get_weights()

@@ -50,9 +54,12 @@

         reset_after = 0

     else:

         reset_after = 1

+    neurons = weights[0].shape[1]//3

+    max_rnn_neurons = max(max_rnn_neurons, neurons)

     f.write('const GRULayer {} = {{\n   {}_bias,\n   {}_weights,\n   {}_recurrent_weights,\n   {}, {}, ACTIVATION_{}, {}\n}};\n\n'

             .format(name, name, name, name, weights[0].shape[0], weights[0].shape[1]//3, activation, reset_after))

-    hf.write('#define {}_SIZE {}\n'.format(name.upper(), weights[0].shape[1]//3))

+    hf.write('#define {}_OUT_SIZE {}\n'.format(name.upper(), weights[0].shape[1]//3))

+    hf.write('#define {}_STATE_SIZE {}\n'.format(name.upper(), weights[0].shape[1]//3))

     hf.write('extern const GRULayer {};\n\n'.format(name));

     return True

 CuDNNGRU.dump_layer = dump_gru_layer

@@ -67,7 +74,7 @@

     activation = self.activation.__name__.upper()

     f.write('const DenseLayer {} = {{\n   {}_bias,\n   {}_weights,\n   {}, {}, ACTIVATION_{}\n}};\n\n'

             .format(name, name, name, weights[0].shape[0], weights[0].shape[1], activation))

-    hf.write('#define {}_SIZE {}\n'.format(name.upper(), weights[0].shape[1]))

+    hf.write('#define {}_OUT_SIZE {}\n'.format(name.upper(), weights[0].shape[1]))

     hf.write('extern const DenseLayer {};\n\n'.format(name));

     return False

 Dense.dump_layer = dump_dense_layer

@@ -82,12 +89,13 @@

     activation = self.activation.__name__.upper()

     f.write('const MDenseLayer {} = {{\n   {}_bias,\n   {}_weights,\n   {}_factor,\n   {}, {}, {}, ACTIVATION_{}\n}};\n\n'

             .format(name, name, name, name, weights[0].shape[0], weights[0].shape[1], weights[0].shape[2], activation))

-    hf.write('#define {}_SIZE {}\n'.format(name.upper(), weights[0].shape[0]))

+    hf.write('#define {}_OUT_SIZE {}\n'.format(name.upper(), weights[0].shape[0]))

     hf.write('extern const MDenseLayer {};\n\n'.format(name));

     return False

 MDense.dump_layer = dump_mdense_layer

 def dump_conv1d_layer(self, f, hf):

+    global max_conv_inputs

     name = self.name

     print("printing layer " + name + " of type " + self.__class__.__name__)

     weights = self.get_weights()

@@ -94,11 +102,13 @@

     printVector(f, weights[0], name + '_weights')

     printVector(f, weights[-1], name + '_bias')

     activation = self.activation.__name__.upper()

+    max_conv_inputs = max(max_conv_inputs, weights[0].shape[1]*weights[0].shape[0])

     f.write('const Conv1DLayer {} = {{\n   {}_bias,\n   {}_weights,\n   {}, {}, {}, ACTIVATION_{}\n}};\n\n'

             .format(name, name, name, weights[0].shape[1], weights[0].shape[0], weights[0].shape[2], activation))

-    hf.write('#define {}_SIZE {}\n'.format(name.upper(), weights[0].shape[1]))

+    hf.write('#define {}_OUT_SIZE {}\n'.format(name.upper(), weights[0].shape[2]))

+    hf.write('#define {}_STATE_SIZE ({}*{})\n'.format(name.upper(), weights[0].shape[1], (weights[0].shape[0]-1)))

     hf.write('extern const Conv1DLayer {};\n\n'.format(name));

-    return False

+    return True

 Conv1D.dump_layer = dump_conv1d_layer

@@ -109,7 +119,7 @@

     printVector(f, weights[0], name + '_weights')

     f.write('const EmbeddingLayer {} = {{\n   {}_weights,\n   {}, {}\n}};\n\n'

             .format(name, name, weights[0].shape[0], weights[0].shape[1]))

-    hf.write('#define {}_SIZE {}\n'.format(name.upper(), weights[0].shape[1]))

+    hf.write('#define {}_OUT_SIZE {}\n'.format(name.upper(), weights[0].shape[1]))

     hf.write('extern const EmbeddingLayer {};\n\n'.format(name));

     return False

 Embedding.dump_layer = dump_embedding_layer

@@ -125,7 +135,6 @@

 hf = open(sys.argv[3], 'w')

-

 f.write('/*This file is automatically generated from a Keras model*/\n\n')

 f.write('#ifdef HAVE_CONFIG_H\n#include "config.h"\n#endif\n\n#include "nnet.h"\n#include "foo.h"\n\n')

@@ -137,9 +146,12 @@

     if layer.dump_layer(f, hf):

         layer_list.append(layer.name)

+hf.write('#define MAX_RNN_NEURONS {}\n\n'.format(max_rnn_neurons))

+hf.write('#define MAX_CONV_INPUTS {}\n\n'.format(max_conv_inputs))

+

 hf.write('struct RNNState {\n')

 for i, name in enumerate(layer_list):

-    hf.write('  float {}_state[{}_SIZE];\n'.format(name, name.upper())) 

+    hf.write('  float {}_state[{}_STATE_SIZE];\n'.format(name, name.upper())) 

 hf.write('};\n')

 hf.write('\n\n#endif\n')

--- a/dnn/nnet.c

+++ b/dnn/nnet.c

@@ -157,11 +157,11 @@

    int i;

    int N, M;

    int stride;

-   float tmp[MAX_NEURONS];

-   float z[MAX_NEURONS];

-   float r[MAX_NEURONS];

-   float h[MAX_NEURONS];

-   celt_assert(gru->nb_neurons <= MAX_NEURONS);

+   float tmp[MAX_RNN_NEURONS];

+   float z[MAX_RNN_NEURONS];

+   float r[MAX_RNN_NEURONS];

+   float h[MAX_RNN_NEURONS];

+   celt_assert(gru->nb_neurons <= MAX_RNN_NEURONS);

    M = gru->nb_inputs;

    N = gru->nb_neurons;

    stride = 3*N;

--- a/dnn/nnet.h

+++ b/dnn/nnet.h

@@ -28,9 +28,6 @@

 #ifndef _NNET_H_

 #define _NNET_H_

-#define MAX_NEURONS 1024

-#define MAX_CONV_INPUTS 1024

-

 #define ACTIVATION_LINEAR  0

 #define ACTIVATION_SIGMOID 1

 #define ACTIVATION_TANH    2

-- 

⑨