eden-emu/opus
15
0
Fork 0
mirror of https://github.com/xiph/opus.git synced 2025-05-18 17:38:29 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions

Implement MDense

Browse source
This commit is contained in:
Jean-Marc Valin 2018-11-24 12:23:11 -05:00
parent d4046036a9
commit 66486004ba
2 changed files with 23 additions and 4 deletions
Download patch file Download diff file Expand all files Collapse all files

4
dnn/dump_lpcnet.py
View file

@ -80,8 +80,8 @@ def dump_mdense_layer(self, f, hf):
printVector(f, weights[1], name + '_bias') printVector(f, weights[1], name + '_bias')
printVector(f, weights[1], name + '_factor') printVector(f, weights[1], name + '_factor')
activation = self.activation.__name__.upper() activation = self.activation.__name__.upper()
f.write('const MDenseLayer {} = {{\n {}_bias,\n {}_weights,\n {}_factor,\n {}, {}, ACTIVATION_{}\n}};\n\n' 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], activation)) .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 {}_SIZE {}\n'.format(name.upper(), weights[0].shape[0]))
hf.write('extern const MDenseLayer {};\n\n'.format(name)); hf.write('extern const MDenseLayer {};\n\n'.format(name));
return False return False

23
dnn/nnet.c
View file

@ -118,7 +118,6 @@ void compute_dense(const DenseLayer *layer, float *output, const float *input)
int i; int i;
int N, M; int N, M;
int stride; int stride;
celt_assert(layer->nb_neurons <= MAX_NEURONS);
M = layer->nb_inputs; M = layer->nb_inputs;
N = layer->nb_neurons; N = layer->nb_neurons;
stride = N; stride = N;
@ -130,6 +129,27 @@ void compute_dense(const DenseLayer *layer, float *output, const float *input)
void compute_mdense(const MDenseLayer *layer, float *output, const float *input) void compute_mdense(const MDenseLayer *layer, float *output, const float *input)
{ {
int i, c;
int N, M, C;
int stride;
M = layer->nb_inputs;
N = layer->nb_neurons;
C = layer->nb_channels;
/* FIXME: Make this C90. */
float tmp[N*C];
stride = N*C;
for (i=0;i<N*C;i++)
tmp[i] = layer->bias[i];
gemm_accum(tmp, layer->input_weights, N*C, M, stride, input);
compute_activation(tmp, tmp, N*C, ACTIVATION_TANH);
for (i=0;i<N;i++)
output[i] = 0;
for (c=0;c<C;c++)
{
for (i=0;i<N;i++)
output[i] += tmp[c*N + i]*layer->factor[c*N + i];
}
compute_activation(output, output, N, layer->activation);
} }
void compute_gru(const GRULayer *gru, float *state, const float *input) void compute_gru(const GRULayer *gru, float *state, const float *input)
@ -189,7 +209,6 @@ void compute_conv1d(const Conv1DLayer *layer, float *output, float *mem, const f
int N, M; int N, M;
int stride; int stride;
float tmp[MAX_CONV_INPUTS]; float tmp[MAX_CONV_INPUTS];
celt_assert(layer->nb_neurons <= MAX_NEURONS);
celt_assert(layer->nb_inputs*layer->kernel_size <= MAX_CONV_INPUTS); celt_assert(layer->nb_inputs*layer->kernel_size <= MAX_CONV_INPUTS);
M = layer->nb_inputs; M = layer->nb_inputs;
N = layer->nb_neurons; N = layer->nb_neurons;