From 4528f9b4b49dc701d3de7b38fa59c17c41702679 Mon Sep 17 00:00:00 2001
From: AlexeyAB <alexeyab84@gmail.com>
Date: Tue, 08 Aug 2017 15:23:57 +0000
Subject: [PATCH] Fixed - use individual track_id for each class of object
---
src/parser.c | 122 ++++++++++++++++++++++++++++++----------
1 files changed, 92 insertions(+), 30 deletions(-)
diff --git a/src/parser.c b/src/parser.c
index e04c6c2..3f39a13 100644
--- a/src/parser.c
+++ b/src/parser.c
@@ -2,32 +2,32 @@
#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"
-#include "convolutional_layer.h"
#include "activation_layer.h"
-#include "normalization_layer.h"
-#include "batchnorm_layer.h"
-#include "connected_layer.h"
-#include "rnn_layer.h"
-#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 "activations.h"
+#include "assert.h"
#include "avgpool_layer.h"
+#include "batchnorm_layer.h"
+#include "blas.h"
+#include "connected_layer.h"
+#include "convolutional_layer.h"
+#include "cost_layer.h"
+#include "crnn_layer.h"
+#include "crop_layer.h"
+#include "detection_layer.h"
+#include "dropout_layer.h"
+#include "gru_layer.h"
+#include "list.h"
#include "local_layer.h"
+#include "maxpool_layer.h"
+#include "normalization_layer.h"
+#include "option_list.h"
+#include "parser.h"
+#include "region_layer.h"
+#include "reorg_layer.h"
+#include "rnn_layer.h"
#include "route_layer.h"
#include "shortcut_layer.h"
-#include "list.h"
-#include "option_list.h"
+#include "softmax_layer.h"
#include "utils.h"
typedef struct{
@@ -111,6 +111,7 @@
int c;
int index;
int time_steps;
+ network net;
} size_params;
local_layer parse_local(list *options, size_params params)
@@ -156,9 +157,14 @@
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,padding,activation, batch_normalize, binary, xnor);
+ convolutional_layer layer = make_convolutional_layer(batch,h,w,c,n,size,stride,padding,activation, batch_normalize, binary, xnor, params.net.adam);
layer.flipped = option_find_int_quiet(options, "flipped", 0);
layer.dot = option_find_float_quiet(options, "dot", 0);
+ if(params.net.adam){
+ layer.B1 = params.net.B1;
+ layer.B2 = params.net.B2;
+ layer.eps = params.net.eps;
+ }
return layer;
}
@@ -232,9 +238,6 @@
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);
@@ -246,10 +249,36 @@
l.jitter = option_find_float(options, "jitter", .2);
l.rescore = option_find_int_quiet(options, "rescore",0);
+ l.thresh = option_find_float(options, "thresh", .5);
+ l.classfix = option_find_int_quiet(options, "classfix", 0);
+ l.absolute = option_find_int_quiet(options, "absolute", 0);
+ l.random = option_find_int_quiet(options, "random", 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);
+ l.bias_match = option_find_int_quiet(options, "bias_match",0);
+
+ char *tree_file = option_find_str(options, "tree", 0);
+ if (tree_file) l.softmax_tree = read_tree(tree_file);
+ char *map_file = option_find_str(options, "map", 0);
+ if (map_file) l.map = read_map(map_file);
+
+ char *a = option_find_str(options, "anchors", 0);
+ if(a){
+ int len = strlen(a);
+ int n = 1;
+ int i;
+ for(i = 0; i < len; ++i){
+ if (a[i] == ',') ++n;
+ }
+ for(i = 0; i < n; ++i){
+ float bias = atof(a);
+ l.biases[i] = bias;
+ a = strchr(a, ',')+1;
+ }
+ }
return l;
}
detection_layer parse_detection(list *options, size_params params)
@@ -313,6 +342,7 @@
layer parse_reorg(list *options, size_params params)
{
int stride = option_find_int(options, "stride",1);
+ int reverse = option_find_int_quiet(options, "reverse",0);
int batch,h,w,c;
h = params.h;
@@ -321,7 +351,7 @@
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);
+ layer layer = make_reorg_layer(batch,w,h,c,stride,reverse);
return layer;
}
@@ -482,6 +512,13 @@
net->batch *= net->time_steps;
net->subdivisions = subdivs;
+ net->adam = option_find_int_quiet(options, "adam", 0);
+ if(net->adam){
+ net->B1 = option_find_float(options, "B1", .9);
+ net->B2 = option_find_float(options, "B2", .999);
+ net->eps = option_find_float(options, "eps", .000001);
+ }
+
net->h = option_find_int_quiet(options, "height",0);
net->w = option_find_int_quiet(options, "width",0);
net->c = option_find_int_quiet(options, "channels",0);
@@ -564,14 +601,16 @@
params.inputs = net.inputs;
params.batch = net.batch;
params.time_steps = net.time_steps;
+ params.net = net;
size_t workspace_size = 0;
n = n->next;
int count = 0;
free_section(s);
+ fprintf(stderr, "layer filters size input output\n");
while(n){
params.index = count;
- fprintf(stderr, "%d: ", count);
+ fprintf(stderr, "%5d ", count);
s = (section *)n->val;
options = s->options;
layer l = {0};
@@ -745,6 +784,10 @@
fwrite(l.rolling_variance, sizeof(float), l.n, fp);
}
fwrite(l.weights, sizeof(float), num, fp);
+ if(l.adam){
+ fwrite(l.m, sizeof(float), num, fp);
+ fwrite(l.v, sizeof(float), num, fp);
+ }
}
void save_batchnorm_weights(layer l, FILE *fp)
@@ -779,11 +822,11 @@
{
#ifdef GPU
if(net.gpu_index >= 0){
- cuda_set_device(net.gpu_index);
+ cuda_set_device(net.gpu_index);
}
#endif
fprintf(stderr, "Saving weights to %s\n", filename);
- FILE *fp = fopen(filename, "w");
+ FILE *fp = fopen(filename, "wb");
if(!fp) file_error(filename);
int major = 0;
@@ -928,8 +971,27 @@
fread(l.scales, sizeof(float), l.n, fp);
fread(l.rolling_mean, sizeof(float), l.n, fp);
fread(l.rolling_variance, sizeof(float), l.n, fp);
+ if(0){
+ int i;
+ for(i = 0; i < l.n; ++i){
+ printf("%g, ", l.rolling_mean[i]);
+ }
+ printf("\n");
+ for(i = 0; i < l.n; ++i){
+ printf("%g, ", l.rolling_variance[i]);
+ }
+ printf("\n");
+ }
+ if(0){
+ fill_cpu(l.n, 0, l.rolling_mean, 1);
+ fill_cpu(l.n, 0, l.rolling_variance, 1);
+ }
}
fread(l.weights, sizeof(float), num, fp);
+ if(l.adam){
+ fread(l.m, sizeof(float), num, fp);
+ fread(l.v, sizeof(float), num, fp);
+ }
//if(l.c == 3) scal_cpu(num, 1./256, l.weights, 1);
if (l.flipped) {
transpose_matrix(l.weights, l.c*l.size*l.size, l.n);
@@ -947,7 +1009,7 @@
{
#ifdef GPU
if(net->gpu_index >= 0){
- cuda_set_device(net->gpu_index);
+ cuda_set_device(net->gpu_index);
}
#endif
fprintf(stderr, "Loading weights from %s...", filename);
--
Gitblit v1.10.0