eden-emu/opus
15
0
Fork 0
mirror of https://github.com/xiph/opus.git synced 2025-05-17 17:08:29 +00:00
Code Issues Projects Releases Packages Wiki Activity Actions 4

Dump Conv1D (didn't check weight ordering at all)

Browse source
This commit is contained in:
Jean-Marc Valin 2018-11-24 11:32:01 -05:00
parent 477d08734d
commit d4046036a9
3 changed files with 27 additions and 13 deletions
Download patch file Download diff file Expand all files Collapse all files

21
dnn/dump_lpcnet.py
View file

@ -64,10 +64,7 @@ def dump_dense_layer(self, f, hf):
weights = self.get_weights()
printVector(f, weights[0], name + '_weights')
printVector(f, weights[-1], name + '_bias')
if hasattr(self, 'activation'):
activation = self.activation.__name__.upper()
else:
activation = 'TANH'
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]))
@ -82,10 +79,7 @@ def dump_mdense_layer(self, f, hf):
printVector(f, weights[0], name + '_weights')
printVector(f, weights[1], name + '_bias')
printVector(f, weights[1], name + '_factor')
if hasattr(self, 'activation'):
activation = self.activation.__name__.upper()
else:
activation = 'TANH'
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))
hf.write('#define {}_SIZE {}\n'.format(name.upper(), weights[0].shape[0]))
@ -93,6 +87,21 @@ def dump_mdense_layer(self, f, hf):
return False
MDense.dump_layer = dump_mdense_layer
def dump_conv1d_layer(self, f, hf):
name = self.name
print("printing layer " + name + " of type " + self.__class__.__name__)
weights = self.get_weights()
printVector(f, weights[0], name + '_weights')
printVector(f, weights[-1], name + '_bias')
activation = self.activation.__name__.upper()
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('extern const Conv1DLayer {};\n\n'.format(name));
return False
Conv1D.dump_layer = dump_conv1d_layer
def dump_embedding_layer(self, f, hf):
name = self.name
print("printing layer " + name + " of type " + self.__class__.__name__)

13
dnn/nnet.c
View file

@ -128,6 +128,10 @@ void compute_dense(const DenseLayer *layer, float *output, const float *input)
compute_activation(output, output, N, layer->activation);
}
void compute_mdense(const MDenseLayer *layer, float *output, const float *input)
{
}
void compute_gru(const GRULayer *gru, float *state, const float *input)
{
int i;
@ -146,16 +150,14 @@ void compute_gru(const GRULayer *gru, float *state, const float *input)
z[i] = gru->bias[i];
gemm_accum(z, gru->input_weights, N, M, stride, input);
gemm_accum(z, gru->recurrent_weights, N, N, stride, state);
for (i=0;i<N;i++)
z[i] = sigmoid_approx(z[i]);
compute_activation(z, z, N, ACTIVATION_SIGMOID);
/* Compute reset gate. */
for (i=0;i<N;i++)
r[i] = gru->bias[N + i];
gemm_accum(r, &gru->input_weights[N], N, M, stride, input);
gemm_accum(r, &gru->recurrent_weights[N], N, N, stride, state);
for (i=0;i<N;i++)
r[i] = sigmoid_approx(r[i]);
compute_activation(r, r, N, ACTIVATION_SIGMOID);
/* Compute output. */
for (i=0;i<N;i++)
@ -174,8 +176,9 @@ void compute_gru(const GRULayer *gru, float *state, const float *input)
gemm_accum(h, &gru->input_weights[2*N], N, M, stride, input);
gemm_accum(h, &gru->recurrent_weights[2*N], N, N, stride, tmp);
}
compute_activation(h, h, N, gru->activation);
for (i=0;i<N;i++)
h[i] = z[i]*state[i] + (1-z[i])*tansig_approx(h[i]);
h[i] = z[i]*state[i] + (1-z[i])*h[i];
for (i=0;i<N;i++)
state[i] = h[i];
}

2
dnn/nnet.h
View file

@ -84,6 +84,8 @@ void compute_activation(float *output, float *input, int N, int activation);
void compute_dense(const DenseLayer *layer, float *output, const float *input);
void compute_mdense(const MDenseLayer *layer, float *output, const float *input);
void compute_gru(const GRULayer *gru, float *state, const float *input);
void compute_conv1d(const Conv1DLayer *layer, float *output, float *mem, const float *input);