From c7b10ceadb1a78e7480d281444a31ae2a7dc1b05 Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Fri, 06 May 2016 23:25:16 +0000
Subject: [PATCH] so much need to commit
---
src/cost_layer.c | 35 ++++++++++++++++++++++++-----------
1 files changed, 24 insertions(+), 11 deletions(-)
diff --git a/src/cost_layer.c b/src/cost_layer.c
index 7593490..fdba777 100644
--- a/src/cost_layer.c
+++ b/src/cost_layer.c
@@ -11,7 +11,8 @@
{
if (strcmp(s, "sse")==0) return SSE;
if (strcmp(s, "masked")==0) return MASKED;
- fprintf(stderr, "Couldn't find activation function %s, going with SSE\n", s);
+ if (strcmp(s, "smooth")==0) return SMOOTH;
+ fprintf(stderr, "Couldn't find cost type %s, going with SSE\n", s);
return SSE;
}
@@ -22,6 +23,8 @@
return "sse";
case MASKED:
return "masked";
+ case SMOOTH:
+ return "smooth";
}
return "sse";
}
@@ -38,9 +41,11 @@
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));
#ifdef GPU
- l.delta_gpu = cuda_make_array(l.delta, inputs*batch);
+ l.delta_gpu = cuda_make_array(l.output, inputs*batch);
+ l.output_gpu = cuda_make_array(l.delta, inputs*batch);
#endif
return l;
}
@@ -50,9 +55,12 @@
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
}
@@ -65,10 +73,12 @@
if(state.truth[i] == SECRET_NUM) state.input[i] = SECRET_NUM;
}
}
- 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);
- *(l.output) = dot_cpu(l.batch*l.inputs, l.delta, 1, l.delta, 1);
- //printf("cost: %f\n", *l.output);
+ if(l.cost_type == SMOOTH){
+ smooth_l1_cpu(l.batch*l.inputs, state.input, state.truth, l.delta, l.output);
+ } else {
+ l2_cpu(l.batch*l.inputs, state.input, state.truth, l.delta, l.output);
+ }
+ l.cost[0] = sum_array(l.output, l.batch*l.inputs);
}
void backward_cost_layer(const cost_layer l, network_state state)
@@ -95,11 +105,14 @@
mask_ongpu(l.batch*l.inputs, state.input, SECRET_NUM, state.truth);
}
- 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);
+ if(l.cost_type == SMOOTH){
+ smooth_l1_gpu(l.batch*l.inputs, state.input, state.truth, l.delta_gpu, l.output_gpu);
+ } else {
+ 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);
+ 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