From 1c05ebf522f0bb5776ba51a46d94aa101220fea1 Mon Sep 17 00:00:00 2001
From: AlexeyAB <alexeyab84@gmail.com>
Date: Thu, 07 Jun 2018 00:39:30 +0000
Subject: [PATCH] Minor fix
---
src/parser.c | 630 ++++++++++++++++++++++++++++++--------------------------
1 files changed, 339 insertions(+), 291 deletions(-)
diff --git a/src/parser.c b/src/parser.c
index 503e7cf..184d1de 100644
--- a/src/parser.c
+++ b/src/parser.c
@@ -2,63 +2,82 @@
#include <string.h>
#include <stdlib.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 "deconvolutional_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 "reorg_old_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"
+#include "upsample_layer.h"
+#include "yolo_layer.h"
+#include <stdint.h>
typedef struct{
char *type;
list *options;
}section;
-int is_network(section *s);
-int is_convolutional(section *s);
-int is_activation(section *s);
-int is_local(section *s);
-int is_deconvolutional(section *s);
-int is_connected(section *s);
-int is_rnn(section *s);
-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);
-int is_normalization(section *s);
-int is_batchnorm(section *s);
-int is_crop(section *s);
-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);
+LAYER_TYPE string_to_layer_type(char * type)
+{
+
+ if (strcmp(type, "[shortcut]")==0) return SHORTCUT;
+ 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, "[yolo]") == 0) return YOLO;
+ if (strcmp(type, "[local]")==0) return LOCAL;
+ if (strcmp(type, "[conv]")==0
+ || strcmp(type, "[convolutional]")==0) return CONVOLUTIONAL;
+ if (strcmp(type, "[activation]")==0) return ACTIVE;
+ if (strcmp(type, "[net]")==0
+ || strcmp(type, "[network]")==0) return NETWORK;
+ if (strcmp(type, "[crnn]")==0) return CRNN;
+ if (strcmp(type, "[gru]")==0) return GRU;
+ if (strcmp(type, "[rnn]")==0) return RNN;
+ if (strcmp(type, "[conn]")==0
+ || 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, "[reorg_old]") == 0) return REORG_OLD;
+ if (strcmp(type, "[avg]")==0
+ || strcmp(type, "[avgpool]")==0) return AVGPOOL;
+ if (strcmp(type, "[dropout]")==0) return DROPOUT;
+ if (strcmp(type, "[lrn]")==0
+ || strcmp(type, "[normalization]")==0) return NORMALIZATION;
+ if (strcmp(type, "[batchnorm]")==0) return BATCHNORM;
+ if (strcmp(type, "[soft]")==0
+ || strcmp(type, "[softmax]")==0) return SOFTMAX;
+ if (strcmp(type, "[route]")==0) return ROUTE;
+ if (strcmp(type, "[upsample]") == 0) return UPSAMPLE;
+ return BLANK;
+}
+
void free_section(section *s)
{
free(s->type);
@@ -99,28 +118,9 @@
int c;
int index;
int time_steps;
+ network net;
} size_params;
-deconvolutional_layer parse_deconvolutional(list *options, size_params params)
-{
- int n = option_find_int(options, "filters",1);
- int size = option_find_int(options, "size",1);
- int stride = option_find_int(options, "stride",1);
- char *activation_s = option_find_str(options, "activation", "logistic");
- ACTIVATION activation = get_activation(activation_s);
-
- int batch,h,w,c;
- h = params.h;
- w = params.w;
- c = params.c;
- batch=params.batch;
- if(!(h && w && c)) error("Layer before deconvolutional layer must output image.");
-
- deconvolutional_layer layer = make_deconvolutional_layer(batch,h,w,c,n,size,stride,activation);
-
- return layer;
-}
-
local_layer parse_local(list *options, size_params params)
{
int n = option_find_int(options, "filters",1);
@@ -147,7 +147,10 @@
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);
@@ -161,9 +164,14 @@
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,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, 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;
}
@@ -226,26 +234,132 @@
int groups = option_find_int_quiet(options, "groups",1);
softmax_layer layer = make_softmax_layer(params.batch, params.inputs, groups);
layer.temperature = option_find_float_quiet(options, "temperature", 1);
+ char *tree_file = option_find_str(options, "tree", 0);
+ if (tree_file) layer.softmax_tree = read_tree(tree_file);
return layer;
}
+int *parse_yolo_mask(char *a, int *num)
+{
+ int *mask = 0;
+ if (a) {
+ int len = strlen(a);
+ int n = 1;
+ int i;
+ for (i = 0; i < len; ++i) {
+ if (a[i] == ',') ++n;
+ }
+ mask = calloc(n, sizeof(int));
+ for (i = 0; i < n; ++i) {
+ int val = atoi(a);
+ mask[i] = val;
+ a = strchr(a, ',') + 1;
+ }
+ *num = n;
+ }
+ return mask;
+}
+
+layer parse_yolo(list *options, size_params params)
+{
+ int classes = option_find_int(options, "classes", 20);
+ int total = option_find_int(options, "num", 1);
+ int num = total;
+
+ char *a = option_find_str(options, "mask", 0);
+ int *mask = parse_yolo_mask(a, &num);
+ int max_boxes = option_find_int_quiet(options, "max", 90);
+ layer l = make_yolo_layer(params.batch, params.w, params.h, num, total, mask, classes, max_boxes);
+ if (l.outputs != params.inputs) {
+ printf("Error: l.outputs == params.inputs \n");
+ printf("filters= in the [convolutional]-layer doesn't correspond to classes= or mask= in [yolo]-layer \n");
+ exit(EXIT_FAILURE);
+ }
+ //assert(l.outputs == params.inputs);
+
+ //l.max_boxes = option_find_int_quiet(options, "max", 90);
+ l.jitter = option_find_float(options, "jitter", .2);
+ l.focal_loss = option_find_int_quiet(options, "focal_loss", 0);
+
+ l.ignore_thresh = option_find_float(options, "ignore_thresh", .5);
+ l.truth_thresh = option_find_float(options, "truth_thresh", 1);
+ l.random = option_find_int_quiet(options, "random", 0);
+
+ char *map_file = option_find_str(options, "map", 0);
+ if (map_file) l.map = read_map(map_file);
+
+ 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 < total*2; ++i) {
+ float bias = atof(a);
+ l.biases[i] = bias;
+ a = strchr(a, ',') + 1;
+ }
+ }
+ return l;
+}
+
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);
- layer l = make_region_layer(params.batch, params.w, params.h, num, classes, coords);
- assert(l.outputs == params.inputs);
+ int max_boxes = option_find_int_quiet(options, "max", 90);
+
+ layer l = make_region_layer(params.batch, params.w, params.h, num, classes, coords, max_boxes);
+ if (l.outputs != params.inputs) {
+ printf("Error: l.outputs == params.inputs \n");
+ printf("filters= in the [convolutional]-layer doesn't correspond to classes= or num= in [region]-layer \n");
+ exit(EXIT_FAILURE);
+ }
+ //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.focal_loss = option_find_int_quiet(options, "focal_loss", 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.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.mask_scale = option_find_float(options, "mask_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 < num*2; ++i){
+ float bias = atof(a);
+ l.biases[i] = bias;
+ a = strchr(a, ',')+1;
+ }
+ }
return l;
}
detection_layer parse_detection(list *options, size_params params)
@@ -278,6 +392,7 @@
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;
}
@@ -308,6 +423,7 @@
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;
@@ -316,14 +432,32 @@
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;
}
+layer parse_reorg_old(list *options, size_params params)
+{
+ printf("\n reorg_old \n");
+ 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;
+ 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_old_layer(batch, w, h, c, stride, reverse);
+ 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;
@@ -332,7 +466,7 @@
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;
}
@@ -410,6 +544,15 @@
return l;
}
+layer parse_upsample(list *options, size_params params, network net)
+{
+
+ int stride = option_find_int(options, "stride", 2);
+ layer l = make_upsample_layer(params.batch, params.w, params.h, params.c, stride);
+ l.scale = option_find_float_quiet(options, "scale", 1);
+ return l;
+}
+
route_layer parse_route(list *options, size_params params, network net)
{
char *l = option_find(options, "layers");
@@ -476,18 +619,37 @@
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);
net->inputs = option_find_int_quiet(options, "inputs", net->h * net->w * net->c);
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->flip = option_find_int_quiet(options, "flip", 1);
+
+ net->small_object = option_find_int_quiet(options, "small_object", 0);
+ 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);
+ net->power = option_find_float_quiet(options, "power", 4);
if(!net->inputs && !(net->h && net->w && net->c)) error("No input parameters supplied");
char *policy_s = option_find_str(options, "policy", "constant");
net->policy = get_policy(policy_s);
net->burn_in = option_find_int_quiet(options, "burn_in", 0);
+#ifdef CUDNN_HALF
+ net->burn_in = 0;
+#endif
if(net->policy == STEP){
net->step = option_find_int(options, "step", 1);
net->scale = option_find_float(options, "scale", 1);
@@ -521,17 +683,29 @@
net->gamma = option_find_float(options, "gamma", 1);
net->step = option_find_int(options, "step", 1);
} else if (net->policy == POLY || net->policy == RANDOM){
- net->power = option_find_float(options, "power", 1);
+ //net->power = option_find_float(options, "power", 1);
}
net->max_batches = option_find_int(options, "max_batches", 0);
}
+int is_network(section *s)
+{
+ return (strcmp(s->type, "[net]")==0
+ || strcmp(s->type, "[network]")==0);
+}
+
network parse_network_cfg(char *filename)
{
+ return parse_network_cfg_custom(filename, 0);
+}
+
+network parse_network_cfg_custom(char *filename, int batch)
+{
list *sections = read_cfg(filename);
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;
@@ -543,60 +717,70 @@
params.w = net.w;
params.c = net.c;
params.inputs = net.inputs;
+ if (batch > 0) net.batch = batch;
params.batch = net.batch;
params.time_steps = net.time_steps;
+ params.net = net;
+ float bflops = 0;
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, "%4d ", count);
s = (section *)n->val;
options = s->options;
layer l = {0};
- if(is_convolutional(s)){
+ LAYER_TYPE lt = string_to_layer_type(s->type);
+ if(lt == CONVOLUTIONAL){
l = parse_convolutional(options, params);
- }else if(is_local(s)){
+ }else if(lt == LOCAL){
l = parse_local(options, params);
- }else if(is_activation(s)){
+ }else if(lt == ACTIVE){
l = parse_activation(options, params);
- }else if(is_deconvolutional(s)){
- l = parse_deconvolutional(options, params);
- }else if(is_rnn(s)){
+ }else if(lt == RNN){
l = parse_rnn(options, params);
- }else if(is_gru(s)){
+ }else if(lt == GRU){
l = parse_gru(options, params);
- }else if(is_crnn(s)){
+ }else if(lt == CRNN){
l = parse_crnn(options, params);
- }else if(is_connected(s)){
+ }else if(lt == CONNECTED){
l = parse_connected(options, params);
- }else if(is_crop(s)){
+ }else if(lt == CROP){
l = parse_crop(options, params);
- }else if(is_cost(s)){
+ }else if(lt == COST){
l = parse_cost(options, params);
- }else if(is_region(s)){
+ }else if(lt == REGION){
l = parse_region(options, params);
- }else if(is_detection(s)){
+ }else if (lt == YOLO) {
+ l = parse_yolo(options, params);
+ }else if(lt == DETECTION){
l = parse_detection(options, params);
- }else if(is_softmax(s)){
+ }else if(lt == SOFTMAX){
l = parse_softmax(options, params);
- }else if(is_normalization(s)){
+ net.hierarchy = l.softmax_tree;
+ }else if(lt == NORMALIZATION){
l = parse_normalization(options, params);
- }else if(is_batchnorm(s)){
+ }else if(lt == BATCHNORM){
l = parse_batchnorm(options, params);
- }else if(is_maxpool(s)){
+ }else if(lt == MAXPOOL){
l = parse_maxpool(options, params);
- }else if(is_reorg(s)){
- l = parse_reorg(options, params);
- }else if(is_avgpool(s)){
+ }else if(lt == REORG){
+ l = parse_reorg(options, params); }
+ else if (lt == REORG_OLD) {
+ l = parse_reorg_old(options, params);
+ }else if(lt == AVGPOOL){
l = parse_avgpool(options, params);
- }else if(is_route(s)){
+ }else if(lt == ROUTE){
l = parse_route(options, params, net);
- }else if(is_shortcut(s)){
+ }else if (lt == UPSAMPLE) {
+ l = parse_upsample(options, params, net);
+ }else if(lt == SHORTCUT){
l = parse_shortcut(options, params, net);
- }else if(is_dropout(s)){
+ }else if(lt == DROPOUT){
l = parse_dropout(options, params);
l.output = net.layers[count-1].output;
l.delta = net.layers[count-1].delta;
@@ -607,6 +791,8 @@
}else{
fprintf(stderr, "Type not recognized: %s\n", s->type);
}
+ l.onlyforward = option_find_int_quiet(options, "onlyforward", 0);
+ l.stopbackward = option_find_int_quiet(options, "stopbackward", 0);
l.dontload = option_find_int_quiet(options, "dontload", 0);
l.dontloadscales = option_find_int_quiet(options, "dontloadscales", 0);
option_unused(options);
@@ -621,15 +807,17 @@
params.c = l.out_c;
params.inputs = l.outputs;
}
+ if (l.bflops > 0) bflops += l.bflops;
}
free_list(sections);
net.outputs = get_network_output_size(net);
net.output = get_network_output(net);
+ printf("Total BFLOPS %5.3f \n", bflops);
if(workspace_size){
//printf("%ld\n", workspace_size);
#ifdef GPU
if(gpu_index >= 0){
- net.workspace = cuda_make_array(0, (workspace_size-1)/sizeof(float)+1);
+ net.workspace = cuda_make_array(0, workspace_size/sizeof(float) + 1);
}else {
net.workspace = calloc(1, workspace_size);
}
@@ -640,141 +828,7 @@
return net;
}
-LAYER_TYPE string_to_layer_type(char * type)
-{
- if (strcmp(type, "[shortcut]")==0) return SHORTCUT;
- 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;
- if (strcmp(type, "[conv]")==0
- || strcmp(type, "[convolutional]")==0) return CONVOLUTIONAL;
- if (strcmp(type, "[activation]")==0) return ACTIVE;
- if (strcmp(type, "[net]")==0
- || strcmp(type, "[network]")==0) return NETWORK;
- if (strcmp(type, "[crnn]")==0) return CRNN;
- if (strcmp(type, "[gru]")==0) return GRU;
- if (strcmp(type, "[rnn]")==0) return RNN;
- if (strcmp(type, "[conn]")==0
- || 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;
- if (strcmp(type, "[lrn]")==0
- || strcmp(type, "[normalization]")==0) return NORMALIZATION;
- if (strcmp(type, "[batchnorm]")==0) return BATCHNORM;
- if (strcmp(type, "[soft]")==0
- || strcmp(type, "[softmax]")==0) return SOFTMAX;
- if (strcmp(type, "[route]")==0) return ROUTE;
- return BLANK;
-}
-
-int is_shortcut(section *s)
-{
- return (strcmp(s->type, "[shortcut]")==0);
-}
-int is_crop(section *s)
-{
- return (strcmp(s->type, "[crop]")==0);
-}
-int is_cost(section *s)
-{
- 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);
-}
-int is_local(section *s)
-{
- return (strcmp(s->type, "[local]")==0);
-}
-int is_deconvolutional(section *s)
-{
- return (strcmp(s->type, "[deconv]")==0
- || strcmp(s->type, "[deconvolutional]")==0);
-}
-int is_convolutional(section *s)
-{
- return (strcmp(s->type, "[conv]")==0
- || strcmp(s->type, "[convolutional]")==0);
-}
-int is_activation(section *s)
-{
- return (strcmp(s->type, "[activation]")==0);
-}
-int is_network(section *s)
-{
- return (strcmp(s->type, "[net]")==0
- || strcmp(s->type, "[network]")==0);
-}
-int is_crnn(section *s)
-{
- return (strcmp(s->type, "[crnn]")==0);
-}
-int is_gru(section *s)
-{
- return (strcmp(s->type, "[gru]")==0);
-}
-int is_rnn(section *s)
-{
- return (strcmp(s->type, "[rnn]")==0);
-}
-int is_connected(section *s)
-{
- 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
- || strcmp(s->type, "[maxpool]")==0);
-}
-int is_avgpool(section *s)
-{
- return (strcmp(s->type, "[avg]")==0
- || strcmp(s->type, "[avgpool]")==0);
-}
-int is_dropout(section *s)
-{
- return (strcmp(s->type, "[dropout]")==0);
-}
-
-int is_normalization(section *s)
-{
- return (strcmp(s->type, "[lrn]")==0
- || strcmp(s->type, "[normalization]")==0);
-}
-
-int is_batchnorm(section *s)
-{
- return (strcmp(s->type, "[batchnorm]")==0);
-}
-
-int is_softmax(section *s)
-{
- return (strcmp(s->type, "[soft]")==0
- || strcmp(s->type, "[softmax]")==0);
-}
-int is_route(section *s)
-{
- return (strcmp(s->type, "[route]")==0);
-}
list *read_cfg(char *filename)
{
@@ -811,45 +865,6 @@
return sections;
}
-void save_weights_double(network net, char *filename)
-{
- fprintf(stderr, "Saving doubled weights to %s\n", filename);
- FILE *fp = fopen(filename, "w");
- if(!fp) file_error(filename);
-
- fwrite(&net.learning_rate, sizeof(float), 1, fp);
- fwrite(&net.momentum, sizeof(float), 1, fp);
- fwrite(&net.decay, sizeof(float), 1, fp);
- fwrite(net.seen, sizeof(int), 1, fp);
-
- int i,j,k;
- for(i = 0; i < net.n; ++i){
- layer l = net.layers[i];
- if(l.type == CONVOLUTIONAL){
-#ifdef GPU
- if(gpu_index >= 0){
- pull_convolutional_layer(l);
- }
-#endif
- float zero = 0;
- fwrite(l.biases, sizeof(float), l.n, fp);
- fwrite(l.biases, sizeof(float), l.n, fp);
-
- 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);
- 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);
- }
- }
- }
- fclose(fp);
-}
-
void save_convolutional_weights_binary(layer l, FILE *fp)
{
#ifdef GPU
@@ -857,7 +872,7 @@
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);
@@ -867,7 +882,7 @@
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){
@@ -875,7 +890,7 @@
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);
}
@@ -900,7 +915,11 @@
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);
+ 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)
@@ -933,8 +952,13 @@
void save_weights_upto(network net, char *filename, int cutoff)
{
+#ifdef GPU
+ if(net.gpu_index >= 0){
+ 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;
@@ -978,7 +1002,7 @@
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);
@@ -1056,7 +1080,7 @@
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;
}
}
}
@@ -1079,12 +1103,32 @@
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.filters, sizeof(float), num, fp);
+ 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.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);
@@ -1095,6 +1139,11 @@
void load_weights_upto(network *net, char *filename, int cutoff)
{
+#ifdef GPU
+ if(net->gpu_index >= 0){
+ cuda_set_device(net->gpu_index);
+ }
+#endif
fprintf(stderr, "Loading weights from %s...", filename);
fflush(stdout);
FILE *fp = fopen(filename, "rb");
@@ -1106,7 +1155,16 @@
fread(&major, sizeof(int), 1, fp);
fread(&minor, sizeof(int), 1, fp);
fread(&revision, sizeof(int), 1, fp);
- fread(net->seen, sizeof(int), 1, fp);
+ if ((major * 10 + minor) >= 2) {
+ printf("\n seen 64 \n");
+ uint64_t iseen = 0;
+ fread(&iseen, sizeof(uint64_t), 1, fp);
+ *net->seen = iseen;
+ }
+ else {
+ printf("\n seen 32 \n");
+ fread(net->seen, sizeof(int), 1, fp);
+ }
int transpose = (major > 1000) || (minor > 1000);
int i;
@@ -1116,16 +1174,6 @@
if(l.type == CONVOLUTIONAL){
load_convolutional_weights(l, fp);
}
- 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);
-#ifdef GPU
- if(gpu_index >= 0){
- push_deconvolutional_layer(l);
- }
-#endif
- }
if(l.type == CONNECTED){
load_connected_weights(l, fp, transpose);
}
@@ -1154,7 +1202,7 @@
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