From 028696bf15efeca3acb3db8c42a96f7b9e0f55ff Mon Sep 17 00:00:00 2001
From: iovodov <b@ovdv.ru>
Date: Thu, 03 May 2018 13:33:46 +0000
Subject: [PATCH] Output improvements for detector results: When printing detector results, output was done in random order, obfuscating results for interpreting. Now: 1. Text output includes coordinates of rects in (left,right,top,bottom in pixels) along with label and score 2. Text output is sorted by rect lefts to simplify finding appropriate rects on image 3. If several class probs are > thresh for some detection, the most probable is written first and coordinates for others are not repeated 4. Rects are imprinted in image in order by their best class prob, so most probable rects are always on top and not overlayed by less probable ones 5. Most probable label for rect is always written first Also: 6. Message about low GPU memory include required amount
---
src/maxpool_layer.c | 138 +++++++++++++++++++++++++++++++++++++--------
1 files changed, 112 insertions(+), 26 deletions(-)
diff --git a/src/maxpool_layer.c b/src/maxpool_layer.c
index f58a22f..031d116 100644
--- a/src/maxpool_layer.c
+++ b/src/maxpool_layer.c
@@ -1,41 +1,127 @@
#include "maxpool_layer.h"
+#include "cuda.h"
#include <stdio.h>
-image get_maxpool_image(maxpool_layer layer)
+image get_maxpool_image(maxpool_layer l)
{
- int h = (layer.h-1)/layer.stride + 1;
- int w = (layer.w-1)/layer.stride + 1;
- int c = layer.c;
- return double_to_image(h,w,c,layer.output);
+ int h = l.out_h;
+ int w = l.out_w;
+ int c = l.c;
+ return float_to_image(w,h,c,l.output);
}
-maxpool_layer *make_maxpool_layer(int h, int w, int c, int stride)
+image get_maxpool_delta(maxpool_layer l)
{
- printf("Maxpool Layer: %d x %d x %d image, %d stride\n", h,w,c,stride);
- maxpool_layer *layer = calloc(1, sizeof(maxpool_layer));
- layer->h = h;
- layer->w = w;
- layer->c = c;
- layer->stride = stride;
- layer->output = calloc(((h-1)/stride+1) * ((w-1)/stride+1) * c, sizeof(double));
- layer->delta = calloc(((h-1)/stride+1) * ((w-1)/stride+1) * c, sizeof(double));
- return layer;
+ int h = l.out_h;
+ int w = l.out_w;
+ int c = l.c;
+ return float_to_image(w,h,c,l.delta);
}
-void forward_maxpool_layer(const maxpool_layer layer, double *in)
+maxpool_layer make_maxpool_layer(int batch, int h, int w, int c, int size, int stride, int padding)
{
- image input = double_to_image(layer.h, layer.w, layer.c, in);
- image output = get_maxpool_image(layer);
- int i,j,k;
- for(i = 0; i < output.h*output.w*output.c; ++i) output.data[i] = -DBL_MAX;
- for(k = 0; k < input.c; ++k){
- for(i = 0; i < input.h; ++i){
- for(j = 0; j < input.w; ++j){
- double val = get_pixel(input, i, j, k);
- double cur = get_pixel(output, i/layer.stride, j/layer.stride, k);
- if(val > cur) set_pixel(output, i/layer.stride, j/layer.stride, k, val);
+ maxpool_layer l = {0};
+ l.type = MAXPOOL;
+ l.batch = batch;
+ l.h = h;
+ l.w = w;
+ l.c = c;
+ l.pad = padding;
+ l.out_w = (w + 2*padding)/stride;
+ l.out_h = (h + 2*padding)/stride;
+ l.out_c = c;
+ l.outputs = l.out_h * l.out_w * l.out_c;
+ l.inputs = h*w*c;
+ l.size = size;
+ l.stride = stride;
+ int output_size = l.out_h * l.out_w * l.out_c * batch;
+ l.indexes = calloc(output_size, sizeof(int));
+ l.output = calloc(output_size, sizeof(float));
+ l.delta = calloc(output_size, sizeof(float));
+ l.forward = forward_maxpool_layer;
+ l.backward = backward_maxpool_layer;
+ #ifdef GPU
+ l.forward_gpu = forward_maxpool_layer_gpu;
+ l.backward_gpu = backward_maxpool_layer_gpu;
+ l.indexes_gpu = cuda_make_int_array(output_size);
+ l.output_gpu = cuda_make_array(l.output, output_size);
+ l.delta_gpu = cuda_make_array(l.delta, output_size);
+ #endif
+ fprintf(stderr, "max %d x %d / %d %4d x%4d x%4d -> %4d x%4d x%4d\n", size, size, stride, w, h, c, l.out_w, l.out_h, l.out_c);
+ return l;
+}
+
+void resize_maxpool_layer(maxpool_layer *l, int w, int h)
+{
+ l->h = h;
+ l->w = w;
+ l->inputs = h*w*l->c;
+
+ l->out_w = (w + 2*l->pad)/l->stride;
+ l->out_h = (h + 2*l->pad)/l->stride;
+ l->outputs = l->out_w * l->out_h * l->c;
+ int output_size = l->outputs * l->batch;
+
+ l->indexes = realloc(l->indexes, output_size * sizeof(int));
+ l->output = realloc(l->output, output_size * sizeof(float));
+ l->delta = realloc(l->delta, output_size * sizeof(float));
+
+ #ifdef GPU
+ cuda_free((float *)l->indexes_gpu);
+ cuda_free(l->output_gpu);
+ cuda_free(l->delta_gpu);
+ l->indexes_gpu = cuda_make_int_array(output_size);
+ l->output_gpu = cuda_make_array(l->output, output_size);
+ l->delta_gpu = cuda_make_array(l->delta, output_size);
+ #endif
+}
+
+void forward_maxpool_layer(const maxpool_layer l, network_state state)
+{
+ int b,i,j,k,m,n;
+ int w_offset = -l.pad;
+ int h_offset = -l.pad;
+
+ int h = l.out_h;
+ int w = l.out_w;
+ int c = l.c;
+
+ for(b = 0; b < l.batch; ++b){
+ for(k = 0; k < c; ++k){
+ for(i = 0; i < h; ++i){
+ for(j = 0; j < w; ++j){
+ int out_index = j + w*(i + h*(k + c*b));
+ float max = -FLT_MAX;
+ int max_i = -1;
+ for(n = 0; n < l.size; ++n){
+ for(m = 0; m < l.size; ++m){
+ int cur_h = h_offset + i*l.stride + n;
+ int cur_w = w_offset + j*l.stride + m;
+ int index = cur_w + l.w*(cur_h + l.h*(k + b*l.c));
+ int valid = (cur_h >= 0 && cur_h < l.h &&
+ cur_w >= 0 && cur_w < l.w);
+ float val = (valid != 0) ? state.input[index] : -FLT_MAX;
+ max_i = (val > max) ? index : max_i;
+ max = (val > max) ? val : max;
+ }
+ }
+ l.output[out_index] = max;
+ l.indexes[out_index] = max_i;
+ }
}
}
}
}
+void backward_maxpool_layer(const maxpool_layer l, network_state state)
+{
+ int i;
+ int h = l.out_h;
+ int w = l.out_w;
+ int c = l.c;
+ for(i = 0; i < h*w*c*l.batch; ++i){
+ int index = l.indexes[i];
+ state.delta[index] += l.delta[i];
+ }
+}
+
--
Gitblit v1.10.0