From ee25ad42c5e9ecdc5a3aa7125e657ce26cc9535c Mon Sep 17 00:00:00 2001
From: Edmond Yoo <hj3yoo@uwaterloo.ca>
Date: Sun, 16 Sep 2018 02:48:50 +0000
Subject: [PATCH] temp

---
 src/cost_layer.c |   53 ++++++++++++++++++++++++++++++++++++++++-------------
 1 files changed, 40 insertions(+), 13 deletions(-)

diff --git a/src/cost_layer.c b/src/cost_layer.c
index 39ae809..39d2398 100644
--- a/src/cost_layer.c
+++ b/src/cost_layer.c
@@ -31,7 +31,7 @@
 
 cost_layer make_cost_layer(int batch, int inputs, COST_TYPE cost_type, float scale)
 {
-    fprintf(stderr, "Cost Layer: %d inputs\n", inputs);
+    fprintf(stderr, "cost                                           %4d\n",  inputs);
     cost_layer l = {0};
     l.type = COST;
 
@@ -41,9 +41,17 @@
     l.outputs = inputs;
     l.cost_type = cost_type;
     l.delta = calloc(inputs*batch, sizeof(float));
-    l.output = calloc(1, sizeof(float));
+    l.output = calloc(inputs*batch, sizeof(float));
+    l.cost = calloc(1, sizeof(float));
+
+    l.forward = forward_cost_layer;
+    l.backward = backward_cost_layer;
     #ifdef GPU
-    l.delta_gpu = cuda_make_array(l.delta, inputs*batch);
+    l.forward_gpu = forward_cost_layer_gpu;
+    l.backward_gpu = backward_cost_layer_gpu;
+
+    l.delta_gpu = cuda_make_array(l.output, inputs*batch);
+    l.output_gpu = cuda_make_array(l.delta, inputs*batch);
     #endif
     return l;
 }
@@ -53,9 +61,12 @@
     l->inputs = inputs;
     l->outputs = inputs;
     l->delta = realloc(l->delta, inputs*l->batch*sizeof(float));
+    l->output = realloc(l->output, inputs*l->batch*sizeof(float));
 #ifdef GPU
     cuda_free(l->delta_gpu);
+    cuda_free(l->output_gpu);
     l->delta_gpu = cuda_make_array(l->delta, inputs*l->batch);
+    l->output_gpu = cuda_make_array(l->output, inputs*l->batch);
 #endif
 }
 
@@ -69,13 +80,11 @@
         }
     }
     if(l.cost_type == SMOOTH){
-        smooth_l1_cpu(l.batch*l.inputs, state.input, state.truth, l.delta);
+        smooth_l1_cpu(l.batch*l.inputs, state.input, state.truth, l.delta, l.output);
     } else {
-        copy_cpu(l.batch*l.inputs, state.truth, 1, l.delta, 1);
-        axpy_cpu(l.batch*l.inputs, -1, state.input, 1, l.delta, 1);
+        l2_cpu(l.batch*l.inputs, state.input, state.truth, l.delta, l.output);
     }
-    *(l.output) = dot_cpu(l.batch*l.inputs, l.delta, 1, l.delta, 1);
-    //printf("cost: %f\n", *l.output);
+    l.cost[0] = sum_array(l.output, l.batch*l.inputs);
 }
 
 void backward_cost_layer(const cost_layer l, network_state state)
@@ -95,6 +104,15 @@
     cuda_push_array(l.delta_gpu, l.delta, l.batch*l.inputs);
 }
 
+int float_abs_compare (const void * a, const void * b)
+{
+    float fa = *(const float*) a;
+    if(fa < 0) fa = -fa;
+    float fb = *(const float*) b;
+    if(fb < 0) fb = -fb;
+    return (fa > fb) - (fa < fb);
+}
+
 void forward_cost_layer_gpu(cost_layer l, network_state state)
 {
     if (!state.truth) return;
@@ -103,14 +121,23 @@
     }
 
     if(l.cost_type == SMOOTH){
-        smooth_l1_gpu(l.batch*l.inputs, state.input, state.truth, l.delta_gpu);
+        smooth_l1_gpu(l.batch*l.inputs, state.input, state.truth, l.delta_gpu, l.output_gpu);
     } else {
-        copy_ongpu(l.batch*l.inputs, state.truth, 1, l.delta_gpu, 1);
-        axpy_ongpu(l.batch*l.inputs, -1, state.input, 1, l.delta_gpu, 1);
+        l2_gpu(l.batch*l.inputs, state.input, state.truth, l.delta_gpu, l.output_gpu);
     }
 
-    cuda_pull_array(l.delta_gpu, l.delta, l.batch*l.inputs);
-    *(l.output) = dot_cpu(l.batch*l.inputs, l.delta, 1, l.delta, 1);
+    if(l.ratio){
+        cuda_pull_array(l.delta_gpu, l.delta, l.batch*l.inputs);
+        qsort(l.delta, l.batch*l.inputs, sizeof(float), float_abs_compare);
+        int n = (1-l.ratio) * l.batch*l.inputs;
+        float thresh = l.delta[n];
+        thresh = 0;
+        printf("%f\n", thresh);
+        supp_ongpu(l.batch*l.inputs, thresh, l.delta_gpu, 1);
+    }
+
+    cuda_pull_array(l.output_gpu, l.output, l.batch*l.inputs);
+    l.cost[0] = sum_array(l.output, l.batch*l.inputs);
 }
 
 void backward_cost_layer_gpu(const cost_layer l, network_state state)

--
Gitblit v1.10.0