From 5c067dc44785a761a0243d8cd634e3ac17d548ad Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Mon, 12 Sep 2016 20:55:20 +0000
Subject: [PATCH] good chance I didn't break anything
---
src/parser.c | 114 +++++++++++++++++++++++++++++++++++++-------------------
1 files changed, 75 insertions(+), 39 deletions(-)
diff --git a/src/parser.c b/src/parser.c
index b5c399f..3551983 100644
--- a/src/parser.c
+++ b/src/parser.c
@@ -2,7 +2,9 @@
#include <string.h>
#include <stdlib.h>
+#include "blas.h"
#include "parser.h"
+#include "assert.h"
#include "activations.h"
#include "crop_layer.h"
#include "cost_layer.h"
@@ -16,6 +18,7 @@
#include "gru_layer.h"
#include "crnn_layer.h"
#include "maxpool_layer.h"
+#include "reorg_layer.h"
#include "softmax_layer.h"
#include "dropout_layer.h"
#include "detection_layer.h"
@@ -43,6 +46,7 @@
int is_gru(section *s);
int is_crnn(section *s);
int is_maxpool(section *s);
+int is_reorg(section *s);
int is_avgpool(section *s);
int is_dropout(section *s);
int is_softmax(section *s);
@@ -115,13 +119,6 @@
deconvolutional_layer layer = make_deconvolutional_layer(batch,h,w,c,n,size,stride,activation);
- char *weights = option_find_str(options, "weights", 0);
- char *biases = option_find_str(options, "biases", 0);
- parse_data(weights, layer.filters, c*n*size*size);
- parse_data(biases, layer.biases, n);
- #ifdef GPU
- if(weights || biases) push_deconvolutional_layer(layer);
- #endif
return layer;
}
@@ -151,7 +148,10 @@
int n = option_find_int(options, "filters",1);
int size = option_find_int(options, "size",1);
int stride = option_find_int(options, "stride",1);
- int pad = option_find_int(options, "pad",0);
+ int pad = option_find_int_quiet(options, "pad",0);
+ int padding = option_find_int_quiet(options, "padding",0);
+ if(pad) padding = size/2;
+
char *activation_s = option_find_str(options, "activation", "logistic");
ACTIVATION activation = get_activation(activation_s);
@@ -165,17 +165,10 @@
int binary = option_find_int_quiet(options, "binary", 0);
int xnor = option_find_int_quiet(options, "xnor", 0);
- convolutional_layer layer = make_convolutional_layer(batch,h,w,c,n,size,stride,pad,activation, batch_normalize, binary, xnor);
+ convolutional_layer layer = make_convolutional_layer(batch,h,w,c,n,size,stride,padding,activation, batch_normalize, binary, xnor);
layer.flipped = option_find_int_quiet(options, "flipped", 0);
layer.dot = option_find_float_quiet(options, "dot", 0);
- char *weights = option_find_str(options, "weights", 0);
- char *biases = option_find_str(options, "biases", 0);
- parse_data(weights, layer.filters, c*n*size*size);
- parse_data(biases, layer.biases, n);
- #ifdef GPU
- if(weights || biases) push_convolutional_layer(layer);
- #endif
return layer;
}
@@ -229,13 +222,6 @@
connected_layer layer = make_connected_layer(params.batch, params.inputs, output, activation, batch_normalize);
- char *weights = option_find_str(options, "weights", 0);
- char *biases = option_find_str(options, "biases", 0);
- parse_data(biases, layer.biases, output);
- parse_data(weights, layer.weights, params.inputs*output);
- #ifdef GPU
- if(weights || biases) push_connected_layer(layer);
- #endif
return layer;
}
@@ -252,9 +238,16 @@
int coords = option_find_int(options, "coords", 4);
int classes = option_find_int(options, "classes", 20);
int num = option_find_int(options, "num", 1);
+
+ params.w = option_find_int(options, "side", params.w);
+ params.h = option_find_int(options, "side", params.h);
+
layer l = make_region_layer(params.batch, params.w, params.h, num, classes, coords);
assert(l.outputs == params.inputs);
+ l.log = option_find_int_quiet(options, "log", 0);
+ l.sqrt = option_find_int_quiet(options, "sqrt", 0);
+
l.softmax = option_find_int(options, "softmax", 0);
l.max_boxes = option_find_int_quiet(options, "max",30);
l.jitter = option_find_float(options, "jitter", .2);
@@ -286,6 +279,7 @@
layer.class_scale = option_find_float(options, "class_scale", 1);
layer.jitter = option_find_float(options, "jitter", .2);
layer.random = option_find_int_quiet(options, "random", 0);
+ layer.reorg = option_find_int_quiet(options, "reorg", 0);
return layer;
}
@@ -295,6 +289,7 @@
COST_TYPE type = get_cost_type(type_s);
float scale = option_find_float_quiet(options, "scale",1);
cost_layer layer = make_cost_layer(params.batch, params.inputs, type, scale);
+ layer.ratio = option_find_float_quiet(options, "ratio",0);
return layer;
}
@@ -322,10 +317,26 @@
return l;
}
+layer parse_reorg(list *options, size_params params)
+{
+ int stride = option_find_int(options, "stride",1);
+
+ int batch,h,w,c;
+ h = params.h;
+ w = params.w;
+ c = params.c;
+ batch=params.batch;
+ if(!(h && w && c)) error("Layer before reorg layer must output image.");
+
+ layer layer = make_reorg_layer(batch,w,h,c,stride);
+ return layer;
+}
+
maxpool_layer parse_maxpool(list *options, size_params params)
{
int stride = option_find_int(options, "stride",1);
int size = option_find_int(options, "size",stride);
+ int padding = option_find_int_quiet(options, "padding", (size-1)/2);
int batch,h,w,c;
h = params.h;
@@ -334,7 +345,7 @@
batch=params.batch;
if(!(h && w && c)) error("Layer before maxpool layer must output image.");
- maxpool_layer layer = make_maxpool_layer(batch,h,w,c,size,stride);
+ maxpool_layer layer = make_maxpool_layer(batch,h,w,c,size,stride,padding);
return layer;
}
@@ -485,6 +496,12 @@
net->max_crop = option_find_int_quiet(options, "max_crop",net->w*2);
net->min_crop = option_find_int_quiet(options, "min_crop",net->w);
+ net->angle = option_find_float_quiet(options, "angle", 0);
+ net->aspect = option_find_float_quiet(options, "aspect", 1);
+ net->saturation = option_find_float_quiet(options, "saturation", 1);
+ net->exposure = option_find_float_quiet(options, "exposure", 1);
+ net->hue = option_find_float_quiet(options, "hue", 0);
+
if(!net->inputs && !(net->h && net->w && net->c)) error("No input parameters supplied");
char *policy_s = option_find_str(options, "policy", "constant");
@@ -534,6 +551,7 @@
node *n = sections->front;
if(!n) error("Config file has no sections");
network net = make_network(sections->size - 1);
+ net.gpu_index = gpu_index;
size_params params;
section *s = (section *)n->val;
@@ -590,6 +608,8 @@
l = parse_batchnorm(options, params);
}else if(is_maxpool(s)){
l = parse_maxpool(options, params);
+ }else if(is_reorg(s)){
+ l = parse_reorg(options, params);
}else if(is_avgpool(s)){
l = parse_avgpool(options, params);
}else if(is_route(s)){
@@ -626,9 +646,13 @@
net.outputs = get_network_output_size(net);
net.output = get_network_output(net);
if(workspace_size){
- //printf("%ld\n", workspace_size);
+ //printf("%ld\n", workspace_size);
#ifdef GPU
- net.workspace = cuda_make_array(0, (workspace_size-1)/sizeof(float)+1);
+ if(gpu_index >= 0){
+ net.workspace = cuda_make_array(0, (workspace_size-1)/sizeof(float)+1);
+ }else {
+ net.workspace = calloc(1, workspace_size);
+ }
#else
net.workspace = calloc(1, workspace_size);
#endif
@@ -659,6 +683,7 @@
|| strcmp(type, "[connected]")==0) return CONNECTED;
if (strcmp(type, "[max]")==0
|| strcmp(type, "[maxpool]")==0) return MAXPOOL;
+ if (strcmp(type, "[reorg]")==0) return REORG;
if (strcmp(type, "[avg]")==0
|| strcmp(type, "[avgpool]")==0) return AVGPOOL;
if (strcmp(type, "[dropout]")==0) return DROPOUT;
@@ -731,6 +756,10 @@
return (strcmp(s->type, "[conn]")==0
|| strcmp(s->type, "[connected]")==0);
}
+int is_reorg(section *s)
+{
+ return (strcmp(s->type, "[reorg]")==0);
+}
int is_maxpool(section *s)
{
return (strcmp(s->type, "[max]")==0
@@ -828,13 +857,13 @@
for (j = 0; j < l.n; ++j){
int index = j*l.c*l.size*l.size;
- fwrite(l.filters+index, sizeof(float), l.c*l.size*l.size, fp);
+ fwrite(l.weights+index, sizeof(float), l.c*l.size*l.size, fp);
for (k = 0; k < l.c*l.size*l.size; ++k) fwrite(&zero, sizeof(float), 1, fp);
}
for (j = 0; j < l.n; ++j){
int index = j*l.c*l.size*l.size;
for (k = 0; k < l.c*l.size*l.size; ++k) fwrite(&zero, sizeof(float), 1, fp);
- fwrite(l.filters+index, sizeof(float), l.c*l.size*l.size, fp);
+ fwrite(l.weights+index, sizeof(float), l.c*l.size*l.size, fp);
}
}
}
@@ -848,7 +877,7 @@
pull_convolutional_layer(l);
}
#endif
- binarize_filters(l.filters, l.n, l.c*l.size*l.size, l.binary_filters);
+ binarize_weights(l.weights, l.n, l.c*l.size*l.size, l.binary_weights);
int size = l.c*l.size*l.size;
int i, j, k;
fwrite(l.biases, sizeof(float), l.n, fp);
@@ -858,7 +887,7 @@
fwrite(l.rolling_variance, sizeof(float), l.n, fp);
}
for(i = 0; i < l.n; ++i){
- float mean = l.binary_filters[i*size];
+ float mean = l.binary_weights[i*size];
if(mean < 0) mean = -mean;
fwrite(&mean, sizeof(float), 1, fp);
for(j = 0; j < size/8; ++j){
@@ -866,7 +895,7 @@
unsigned char c = 0;
for(k = 0; k < 8; ++k){
if (j*8 + k >= size) break;
- if (l.binary_filters[index + k] > 0) c = (c | 1<<k);
+ if (l.binary_weights[index + k] > 0) c = (c | 1<<k);
}
fwrite(&c, sizeof(char), 1, fp);
}
@@ -891,7 +920,7 @@
fwrite(l.rolling_mean, sizeof(float), l.n, fp);
fwrite(l.rolling_variance, sizeof(float), l.n, fp);
}
- fwrite(l.filters, sizeof(float), num, fp);
+ fwrite(l.weights, sizeof(float), num, fp);
}
void save_batchnorm_weights(layer l, FILE *fp)
@@ -924,6 +953,9 @@
void save_weights_upto(network net, char *filename, int cutoff)
{
+#ifdef GPU
+ cuda_set_device(net.gpu_index);
+#endif
fprintf(stderr, "Saving weights to %s\n", filename);
FILE *fp = fopen(filename, "w");
if(!fp) file_error(filename);
@@ -969,7 +1001,7 @@
int locations = l.out_w*l.out_h;
int size = l.size*l.size*l.c*l.n*locations;
fwrite(l.biases, sizeof(float), l.outputs, fp);
- fwrite(l.filters, sizeof(float), size, fp);
+ fwrite(l.weights, sizeof(float), size, fp);
}
}
fclose(fp);
@@ -1047,7 +1079,7 @@
fread(&c, sizeof(char), 1, fp);
for(k = 0; k < 8; ++k){
if (j*8 + k >= size) break;
- l.filters[index + k] = (c & 1<<k) ? mean : -mean;
+ l.weights[index + k] = (c & 1<<k) ? mean : -mean;
}
}
}
@@ -1071,11 +1103,12 @@
fread(l.rolling_mean, sizeof(float), l.n, fp);
fread(l.rolling_variance, sizeof(float), l.n, fp);
}
- fread(l.filters, sizeof(float), num, fp);
+ fread(l.weights, sizeof(float), num, fp);
+ //if(l.c == 3) scal_cpu(num, 1./256, l.weights, 1);
if (l.flipped) {
- transpose_matrix(l.filters, l.c*l.size*l.size, l.n);
+ transpose_matrix(l.weights, l.c*l.size*l.size, l.n);
}
- //if (l.binary) binarize_filters(l.filters, l.n, l.c*l.size*l.size, l.filters);
+ //if (l.binary) binarize_weights(l.weights, l.n, l.c*l.size*l.size, l.weights);
#ifdef GPU
if(gpu_index >= 0){
push_convolutional_layer(l);
@@ -1086,6 +1119,9 @@
void load_weights_upto(network *net, char *filename, int cutoff)
{
+#ifdef GPU
+ cuda_set_device(net->gpu_index);
+#endif
fprintf(stderr, "Loading weights from %s...", filename);
fflush(stdout);
FILE *fp = fopen(filename, "rb");
@@ -1110,7 +1146,7 @@
if(l.type == DECONVOLUTIONAL){
int num = l.n*l.c*l.size*l.size;
fread(l.biases, sizeof(float), l.n, fp);
- fread(l.filters, sizeof(float), num, fp);
+ fread(l.weights, sizeof(float), num, fp);
#ifdef GPU
if(gpu_index >= 0){
push_deconvolutional_layer(l);
@@ -1145,7 +1181,7 @@
int locations = l.out_w*l.out_h;
int size = l.size*l.size*l.c*l.n*locations;
fread(l.biases, sizeof(float), l.outputs, fp);
- fread(l.filters, sizeof(float), size, fp);
+ fread(l.weights, sizeof(float), size, fp);
#ifdef GPU
if(gpu_index >= 0){
push_local_layer(l);
--
Gitblit v1.10.0