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

dnn/dump_lpcnet.py

@@ -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()
-        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()
-        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__)

dnn/nnet.c

@@ -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++)
+   compute_activation(z, z, N, ACTIVATION_SIGMOID);
-      z[i] = sigmoid_approx(z[i]);
 
    /* 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++)
+   compute_activation(r, r, N, ACTIVATION_SIGMOID);
-      r[i] = sigmoid_approx(r[i]);
 
    /* 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];
 }

dnn/nnet.h

@@ -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);