From 8f1b4e0962857d402f9d017fcbf387ef0eceb7c4 Mon Sep 17 00:00:00 2001
From: Joseph Redmon <pjreddie@gmail.com>
Date: Thu, 01 Sep 2016 23:48:41 +0000
Subject: [PATCH] updates and things
---
src/parser.c | 108 +++++++++++++++++++++++++++++++++++++++++-------------
1 files changed, 82 insertions(+), 26 deletions(-)
diff --git a/src/parser.c b/src/parser.c
index 1e5be4d..626f510 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"
@@ -16,9 +18,11 @@
#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"
+#include "region_layer.h"
#include "avgpool_layer.h"
#include "local_layer.h"
#include "route_layer.h"
@@ -42,6 +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);
@@ -51,6 +56,7 @@
int is_shortcut(section *s);
int is_cost(section *s);
int is_detection(section *s);
+int is_region(section *s);
int is_route(section *s);
list *read_cfg(char *filename);
@@ -113,13 +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;
}
@@ -149,7 +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);
@@ -163,17 +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;
}
@@ -227,13 +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;
}
@@ -245,6 +233,32 @@
return layer;
}
+layer parse_region(list *options, size_params params)
+{
+ 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);
+ l.rescore = option_find_int_quiet(options, "rescore",0);
+
+ l.coord_scale = option_find_float(options, "coord_scale", 1);
+ l.object_scale = option_find_float(options, "object_scale", 1);
+ l.noobject_scale = option_find_float(options, "noobject_scale", 1);
+ l.class_scale = option_find_float(options, "class_scale", 1);
+ return l;
+}
detection_layer parse_detection(list *options, size_params params)
{
int coords = option_find_int(options, "coords", 1);
@@ -265,6 +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;
}
@@ -274,6 +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;
}
@@ -301,10 +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;
@@ -313,7 +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;
}
@@ -464,6 +496,11 @@
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->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");
@@ -557,6 +594,8 @@
l = parse_crop(options, params);
}else if(is_cost(s)){
l = parse_cost(options, params);
+ }else if(is_region(s)){
+ l = parse_region(options, params);
}else if(is_detection(s)){
l = parse_detection(options, params);
}else if(is_softmax(s)){
@@ -567,6 +606,8 @@
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)){
@@ -603,9 +644,13 @@
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
@@ -620,6 +665,7 @@
if (strcmp(type, "[crop]")==0) return CROP;
if (strcmp(type, "[cost]")==0) return COST;
if (strcmp(type, "[detection]")==0) return DETECTION;
+ if (strcmp(type, "[region]")==0) return REGION;
if (strcmp(type, "[local]")==0) return LOCAL;
if (strcmp(type, "[deconv]")==0
|| strcmp(type, "[deconvolutional]")==0) return DECONVOLUTIONAL;
@@ -635,6 +681,7 @@
|| 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;
@@ -659,6 +706,10 @@
{
return (strcmp(s->type, "[cost]")==0);
}
+int is_region(section *s)
+{
+ return (strcmp(s->type, "[region]")==0);
+}
int is_detection(section *s)
{
return (strcmp(s->type, "[detection]")==0);
@@ -703,6 +754,10 @@
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
@@ -1044,6 +1099,7 @@
fread(l.rolling_variance, sizeof(float), l.n, fp);
}
fread(l.filters, sizeof(float), num, fp);
+ //if(l.c == 3) scal_cpu(num, 1./256, l.filters, 1);
if (l.flipped) {
transpose_matrix(l.filters, l.c*l.size*l.size, l.n);
}
--
Gitblit v1.10.0