From 9c2c220c88aff4d0bcbdd5b03b10c6d1a7db56d3 Mon Sep 17 00:00:00 2001
From: Edmond Yoo <hj3yoo@uwaterloo.ca>
Date: Sun, 16 Sep 2018 03:14:14 +0000
Subject: [PATCH] Moving files from MTGCardDetector #2
---
src/parser.c | 297 ++++++++++++++++++++++++++++++++++++++++++++++++++--------
1 files changed, 254 insertions(+), 43 deletions(-)
diff --git a/src/parser.c b/src/parser.c
index a27d245..c716ea9 100644
--- a/src/parser.c
+++ b/src/parser.c
@@ -2,33 +2,37 @@
#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 "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;
@@ -45,6 +49,7 @@
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;
@@ -59,6 +64,7 @@
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;
@@ -68,6 +74,7 @@
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;
}
@@ -111,6 +118,7 @@
int c;
int index;
int time_steps;
+ network net;
} size_params;
local_layer parse_local(list *options, size_params params)
@@ -156,9 +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,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;
}
@@ -221,33 +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);
+ int max_boxes = option_find_int_quiet(options, "max", 90);
- 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);
+ 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)
@@ -311,6 +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;
@@ -319,7 +432,24 @@
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;
}
@@ -327,7 +457,7 @@
{
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 padding = option_find_int_quiet(options, "padding", size-1);
int batch,h,w,c;
h = params.h;
@@ -381,7 +511,7 @@
layer parse_shortcut(list *options, size_params params, network net)
{
- char *l = option_find(options, "from");
+ char *l = option_find(options, "from");
int index = atoi(l);
if(index < 0) index = params.index + index;
@@ -414,9 +544,18 @@
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");
+ char *l = option_find(options, "layers");
int len = strlen(l);
if(!l) error("Route Layer must specify input layers");
int n = 1;
@@ -480,30 +619,43 @@
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);
} else if (net->policy == STEPS){
- char *l = option_find(options, "steps");
- char *p = option_find(options, "scales");
+ char *l = option_find(options, "steps");
+ char *p = option_find(options, "scales");
if(!l || !p) error("STEPS policy must have steps and scales in cfg file");
int len = strlen(l);
@@ -531,7 +683,7 @@
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);
}
@@ -544,6 +696,11 @@
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");
@@ -560,16 +717,20 @@
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};
@@ -594,10 +755,13 @@
l = parse_cost(options, params);
}else if(lt == REGION){
l = parse_region(options, params);
+ }else if (lt == YOLO) {
+ l = parse_yolo(options, params);
}else if(lt == DETECTION){
l = parse_detection(options, params);
}else if(lt == SOFTMAX){
l = parse_softmax(options, params);
+ net.hierarchy = l.softmax_tree;
}else if(lt == NORMALIZATION){
l = parse_normalization(options, params);
}else if(lt == BATCHNORM){
@@ -605,11 +769,15 @@
}else if(lt == MAXPOOL){
l = parse_maxpool(options, params);
}else if(lt == REORG){
- l = parse_reorg(options, params);
+ 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(lt == ROUTE){
l = parse_route(options, params, net);
+ }else if (lt == UPSAMPLE) {
+ l = parse_upsample(options, params, net);
}else if(lt == SHORTCUT){
l = parse_shortcut(options, params, net);
}else if(lt == DROPOUT){
@@ -623,6 +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);
@@ -637,15 +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);
}
@@ -653,9 +825,16 @@
net.workspace = calloc(1, workspace_size);
#endif
}
+ LAYER_TYPE lt = net.layers[net.n - 1].type;
+ if ((net.w % 32 != 0 || net.h % 32 != 0) && (lt == YOLO || lt == REGION || lt == DETECTION)) {
+ printf("\n Warning: width=%d and height=%d in cfg-file must be divisible by 32 for default networks Yolo v1/v2/v3!!! \n\n",
+ net.w, net.h);
+ }
return net;
}
+
+
list *read_cfg(char *filename)
{
FILE *file = fopen(filename, "r");
@@ -742,6 +921,10 @@
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)
@@ -776,11 +959,11 @@
{
#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;
@@ -925,8 +1108,27 @@
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);
@@ -944,7 +1146,7 @@
{
#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);
@@ -958,7 +1160,16 @@
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;
--
Gitblit v1.10.0