15 + 1 -> 16

official-pikafish · Oct 6, 2024 · ceb7139 · ceb7139
1 parent baec5cd
commit ceb7139
Showing 1 changed file with 12 additions and 14 deletions.
diff --git a/src/nnue/nnue_architecture.h b/src/nnue/nnue_architecture.h
@@ -43,15 +43,15 @@ constexpr IndexType PSQTBuckets                  = 16;
 constexpr IndexType LayerStacks                  = 16;
 
 struct NetworkArchitecture {
-    static constexpr int FC_0_OUTPUTS = 15;
+    static constexpr int FC_0_OUTPUTS = 16;
     static constexpr int FC_1_OUTPUTS = 32;
 
-    Layers::AffineTransformSparseInput<TransformedFeatureDimensions, FC_0_OUTPUTS + 1> fc_0;
-    Layers::SqrClippedReLU<FC_0_OUTPUTS + 1>                                           ac_sqr_0;
-    Layers::ClippedReLU<FC_0_OUTPUTS + 1>                                              ac_0;
-    Layers::AffineTransform<FC_0_OUTPUTS * 2, FC_1_OUTPUTS>                            fc_1;
-    Layers::ClippedReLU<FC_1_OUTPUTS>                                                  ac_1;
-    Layers::AffineTransform<FC_1_OUTPUTS, 1>                                           fc_2;
+    Layers::AffineTransformSparseInput<TransformedFeatureDimensions, FC_0_OUTPUTS> fc_0;
+    Layers::SqrClippedReLU<FC_0_OUTPUTS>                                           ac_sqr_0;
+    Layers::ClippedReLU<FC_0_OUTPUTS>                                              ac_0;
+    Layers::AffineTransform<FC_0_OUTPUTS * 2, FC_1_OUTPUTS>                        fc_1;
+    Layers::ClippedReLU<FC_1_OUTPUTS>                                              ac_1;
+    Layers::AffineTransform<FC_1_OUTPUTS, 1>                                       fc_2;
 
     // Hash value embedded in the evaluation file
     static constexpr std::uint32_t get_hash_value() {
@@ -106,17 +106,15 @@ struct NetworkArchitecture {
 
         fc_0.propagate(transformedFeatures, buffer.fc_0_out);
         ac_sqr_0.propagate(buffer.fc_0_out, buffer.ac_sqr_0_out);
-        ac_0.propagate(buffer.fc_0_out, buffer.ac_0_out);
-        std::memcpy(buffer.ac_sqr_0_out + FC_0_OUTPUTS, buffer.ac_0_out,
-                    FC_0_OUTPUTS * sizeof(decltype(ac_0)::OutputType));
+        ac_0.propagate(buffer.fc_0_out, buffer.ac_sqr_0_out + FC_0_OUTPUTS);
         fc_1.propagate(buffer.ac_sqr_0_out, buffer.fc_1_out);
         ac_1.propagate(buffer.fc_1_out, buffer.ac_1_out);
         fc_2.propagate(buffer.ac_1_out, buffer.fc_2_out);
 
-        // buffer.fc_0_out[FC_0_OUTPUTS] is such that 1.0 is equal to 127*(1<<WeightScaleBits) in
-        // quantized form but we want 1.0 to be equal to 600*OutputScale
-        std::int32_t fwdOut =
-          (buffer.fc_0_out[FC_0_OUTPUTS]) * (600 * OutputScale) / (127 * (1 << WeightScaleBits));
+        // buffer.fc_0_out[FC_0_OUTPUTS - 1] is such that 1.0 is equal to 127*(1<<WeightScaleBits)
+        // in quantized form but we want 1.0 to be equal to 600*OutputScale
+        std::int32_t fwdOut = (buffer.fc_0_out[FC_0_OUTPUTS - 1]) * (600 * OutputScale)
+                            / (127 * (1 << WeightScaleBits));
         std::int32_t outputValue = buffer.fc_2_out[0] + fwdOut;
 
         return outputValue;