From 67794a52a1ca19275f186dbc21cb45c1a45d6b92 Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Wed, 16 Mar 2016 11:44:44 +0000
Subject: [PATCH] more go

---
 src/convolutional_layer.c |  152 +++++++++++++++++++++++++++++++++++++++++++++++++-
 1 files changed, 148 insertions(+), 4 deletions(-)

diff --git a/src/convolutional_layer.c b/src/convolutional_layer.c
index e97b00d..cdc8bd3 100644
--- a/src/convolutional_layer.c
+++ b/src/convolutional_layer.c
@@ -7,6 +7,52 @@
 #include <stdio.h>
 #include <time.h>
 
+void swap_binary(convolutional_layer *l)
+{
+    float *swap = l->filters;
+    l->filters = l->binary_filters;
+    l->binary_filters = swap;
+
+    #ifdef GPU
+    swap = l->filters_gpu;
+    l->filters_gpu = l->binary_filters_gpu;
+    l->binary_filters_gpu = swap;
+    #endif
+}
+
+void binarize_filters2(float *filters, int n, int size, char *binary, float *scales)
+{
+    int i, k, f;
+    for(f = 0; f < n; ++f){
+        float mean = 0;
+        for(i = 0; i < size; ++i){
+            mean += fabs(filters[f*size + i]);
+        }
+        mean = mean / size;
+        scales[f] = mean;
+        for(i = 0; i < size/8; ++i){
+            binary[f*size + i] = (filters[f*size + i] > 0) ? 1 : 0;
+            for(k = 0; k < 8; ++k){
+            }
+        }
+    }
+}
+
+void binarize_filters(float *filters, int n, int size, float *binary)
+{
+    int i, f;
+    for(f = 0; f < n; ++f){
+        float mean = 0;
+        for(i = 0; i < size; ++i){
+            mean += fabs(filters[f*size + i]);
+        }
+        mean = mean / size;
+        for(i = 0; i < size; ++i){
+            binary[f*size + i] = (filters[f*size + i] > 0) ? mean : -mean;
+        }
+    }
+}
+
 int convolutional_out_height(convolutional_layer l)
 {
     int h = l.h;
@@ -41,7 +87,65 @@
     return float_to_image(w,h,c,l.delta);
 }
 
-convolutional_layer make_convolutional_layer(int batch, int h, int w, int c, int n, int size, int stride, int pad, ACTIVATION activation, int batch_normalize)
+void backward_scale_cpu(float *x_norm, float *delta, int batch, int n, int size, float *scale_updates)
+{
+    int i,b,f;
+    for(f = 0; f < n; ++f){
+        float sum = 0;
+        for(b = 0; b < batch; ++b){
+            for(i = 0; i < size; ++i){
+                int index = i + size*(f + n*b);
+                sum += delta[index] * x_norm[index];
+            }
+        }
+        scale_updates[f] += sum;
+    }
+}
+
+void mean_delta_cpu(float *delta, float *variance, int batch, int filters, int spatial, float *mean_delta)
+{
+
+    int i,j,k;
+    for(i = 0; i < filters; ++i){
+        mean_delta[i] = 0;
+        for (j = 0; j < batch; ++j) {
+            for (k = 0; k < spatial; ++k) {
+                int index = j*filters*spatial + i*spatial + k;
+                mean_delta[i] += delta[index];
+            }
+        }
+        mean_delta[i] *= (-1./sqrt(variance[i] + .00001f));
+    }
+}
+void  variance_delta_cpu(float *x, float *delta, float *mean, float *variance, int batch, int filters, int spatial, float *variance_delta)
+{
+
+    int i,j,k;
+    for(i = 0; i < filters; ++i){
+        variance_delta[i] = 0;
+        for(j = 0; j < batch; ++j){
+            for(k = 0; k < spatial; ++k){
+                int index = j*filters*spatial + i*spatial + k;
+                variance_delta[i] += delta[index]*(x[index] - mean[i]);
+            }
+        }
+        variance_delta[i] *= -.5 * pow(variance[i] + .00001f, (float)(-3./2.));
+    }
+}
+void normalize_delta_cpu(float *x, float *mean, float *variance, float *mean_delta, float *variance_delta, int batch, int filters, int spatial, float *delta)
+{
+    int f, j, k;
+    for(j = 0; j < batch; ++j){
+        for(f = 0; f < filters; ++f){
+            for(k = 0; k < spatial; ++k){
+                int index = j*filters*spatial + f*spatial + k;
+                delta[index] = delta[index] * 1./(sqrt(variance[f]) + .00001f) + variance_delta[f] * 2. * (x[index] - mean[f]) / (spatial * batch) + mean_delta[f]/(spatial*batch);
+            }
+        }
+    }
+}
+
+convolutional_layer make_convolutional_layer(int batch, int h, int w, int c, int n, int size, int stride, int pad, ACTIVATION activation, int batch_normalize, int binary)
 {
     int i;
     convolutional_layer l = {0};
@@ -51,6 +155,7 @@
     l.w = w;
     l.c = c;
     l.n = n;
+    l.binary = binary;
     l.batch = batch;
     l.stride = stride;
     l.size = size;
@@ -65,7 +170,7 @@
 
     // float scale = 1./sqrt(size*size*c);
     float scale = sqrt(2./(size*size*c));
-    for(i = 0; i < c*n*size*size; ++i) l.filters[i] = 2*scale*rand_uniform() - scale;
+    for(i = 0; i < c*n*size*size; ++i) l.filters[i] = scale*rand_uniform(-1, 1);
     int out_h = convolutional_out_height(l);
     int out_w = convolutional_out_width(l);
     l.out_h = out_h;
@@ -78,6 +183,12 @@
     l.output = calloc(l.batch*out_h * out_w * n, sizeof(float));
     l.delta  = calloc(l.batch*out_h * out_w * n, sizeof(float));
 
+    if(binary){
+        l.binary_filters = calloc(c*n*size*size, sizeof(float));
+        l.cfilters = calloc(c*n*size*size, sizeof(char));
+        l.scales = calloc(n, sizeof(float));
+    }
+
     if(batch_normalize){
         l.scales = calloc(n, sizeof(float));
         l.scale_updates = calloc(n, sizeof(float));
@@ -106,6 +217,10 @@
     l.delta_gpu = cuda_make_array(l.delta, l.batch*out_h*out_w*n);
     l.output_gpu = cuda_make_array(l.output, l.batch*out_h*out_w*n);
 
+    if(binary){
+        l.binary_filters_gpu = cuda_make_array(l.filters, c*n*size*size);
+    }
+
     if(batch_normalize){
         l.mean_gpu = cuda_make_array(l.mean, n);
         l.variance_gpu = cuda_make_array(l.variance, n);
@@ -141,7 +256,7 @@
 
 void test_convolutional_layer()
 {
-    convolutional_layer l = make_convolutional_layer(1, 5, 5, 3, 2, 5, 2, 1, LEAKY, 1);
+    convolutional_layer l = make_convolutional_layer(1, 5, 5, 3, 2, 5, 2, 1, LEAKY, 1, 0);
     l.batch_normalize = 1;
     float data[] = {1,1,1,1,1,
         1,1,1,1,1,
@@ -228,13 +343,42 @@
     }
 }
 
-void forward_convolutional_layer(const convolutional_layer l, network_state state)
+void forward_convolutional_layer(convolutional_layer l, network_state state)
 {
     int out_h = convolutional_out_height(l);
     int out_w = convolutional_out_width(l);
     int i;
 
     fill_cpu(l.outputs*l.batch, 0, l.output, 1);
+    /*
+    if(l.binary){
+        binarize_filters(l.filters, l.n, l.c*l.size*l.size, l.binary_filters);
+        binarize_filters2(l.filters, l.n, l.c*l.size*l.size, l.cfilters, l.scales);
+        swap_binary(&l);
+    }
+    */
+
+    if(l.binary){
+        int m = l.n;
+        int k = l.size*l.size*l.c;
+        int n = out_h*out_w;
+
+        char  *a = l.cfilters;
+        float *b = l.col_image;
+        float *c = l.output;
+
+        for(i = 0; i < l.batch; ++i){
+            im2col_cpu(state.input, l.c, l.h, l.w, 
+                    l.size, l.stride, l.pad, b);
+            gemm_bin(m,n,k,1,a,k,b,n,c,n);
+            c += n*m;
+            state.input += l.c*l.h*l.w;
+        }
+        scale_bias(l.output, l.scales, l.batch, l.n, out_h*out_w);
+        add_bias(l.output, l.biases, l.batch, l.n, out_h*out_w);
+        activate_array(l.output, m*n*l.batch, l.activation);
+        return;
+    }
 
     int m = l.n;
     int k = l.size*l.size*l.c;

--
Gitblit v1.10.0