int main(int argc, char** argv)
{
ccv_enable_default_cache();
assert(argc == 2);
FILE *r = fopen(argv[1], "r");
char* file = (char*)malloc(1024);
ccv_array_t* categorizeds = ccv_array_new(sizeof(ccv_categorized_t), 64, 0);
size_t len = 1024;
ssize_t read;
while ((read = getline(&file, &len, r)) != -1)
{
while(read > 1 && isspace(file[read - 1]))
read--;
file[read] = 0;
ccv_file_info_t input;
input.filename = (char*)ccmalloc(1024);
strncpy(input.filename, file, 1024);
ccv_categorized_t categorized = ccv_categorized(0, 0, &input);
ccv_array_push(categorizeds, &categorized);
}
fclose(r);
free(file);
/* MattNet parameters */
ccv_convnet_layer_param_t params[13] = {
// first layer (convolutional => max pool => rnorm)
{
.type = CCV_CONVNET_CONVOLUTIONAL,
.bias = 0,
.glorot = sqrtf(2),
.input = {
.matrix = {
.rows = 225,
.cols = 225,
.channels = 3,
.partition = 1,
},
},
.output = {
.convolutional = {
.count = 96,
.strides = 2,
.border = 1,
.rows = 7,
.cols = 7,
.channels = 3,
.partition = 2,
},
},
},
{
.type = CCV_CONVNET_LOCAL_RESPONSE_NORM,
ccv_nnc_graph_exec_symbol_t ccv_nnc_symbolic_graph_while(ccv_nnc_symbolic_graph_t* const graph, ccv_nnc_symbolic_graph_t* const while_graph, const char* const name)
{
assert(while_graph->p == 0);
assert(while_graph->p_idx == 0);
ccv_nnc_cmd_t cmd = ccv_nnc_cmd(CCV_NNC_GRAPH_FORWARD, 0, CMD_GENERIC(), 0);
// Added one more symbol.
ccv_nnc_graph_exec_symbol_t symbol = ccv_nnc_graph_exec_symbol_new(graph, cmd, 0, 0, 0, 0, name);
// Assigning graph_ref to it.
if (!graph->sub_graphs)
graph->sub_graphs = ccv_array_new(sizeof(ccv_nnc_symbolic_graph_t*), 1, 0);
ccv_array_push(graph->sub_graphs, &while_graph);
ccv_nnc_graph_exec_symbol_info_t* symbol_info = (ccv_nnc_graph_exec_symbol_info_t*)ccv_array_get(graph->exec_symbol_info, symbol.d);
// Note the extra allocation (the ccv_array_t only holds a pointer to ccv_nnc_symbolic_graph_t*).
// In this way, we can get the while graph and don't have to worry about it will be an invalid pointer once
// the array expands (another while graph allocated).
symbol_info->graph_ref = graph->sub_graphs->rnum;
while_graph->p_idx = graph->sub_graphs->rnum;
while_graph->exec_idx = symbol.d + 1;
while_graph->p = graph;
return symbol;
}
int main(int argc, char** argv)
{
static struct option image_net_options[] = {
/* help */
{"help", 0, 0, 0},
/* required parameters */
{"train-list", 1, 0, 0},
{"test-list", 1, 0, 0},
{"working-dir", 1, 0, 0},
/* optional parameters */
{"base-dir", 1, 0, 0},
{"max-epoch", 1, 0, 0},
{"iterations", 1, 0, 0},
{0, 0, 0, 0}
};
char* train_list = 0;
char* test_list = 0;
char* working_dir = 0;
char* base_dir = 0;
ccv_convnet_train_param_t train_params = {
.max_epoch = 100,
.mini_batch = 64,
.sgd_frequency = 1, // do sgd every sgd_frequency batches (mini_batch * device_count * sgd_frequency)
.iterations = 50000,
.device_count = 4,
.peer_access = 1,
.symmetric = 1,
.image_manipulation = 0.2,
.color_gain = 0.001,
.input = {
.min_dim = 257,
.max_dim = 257,
},
};
int i, c;
while (getopt_long_only(argc, argv, "", image_net_options, &c) != -1)
{
switch (c)
{
case 0:
exit_with_help();
case 1:
train_list = optarg;
break;
case 2:
test_list = optarg;
break;
case 3:
working_dir = optarg;
break;
case 4:
base_dir = optarg;
break;
case 5:
train_params.max_epoch = atoi(optarg);
break;
case 6:
train_params.iterations = atoi(optarg);
break;
}
}
if (!train_list || !test_list || !working_dir)
exit_with_help();
ccv_enable_default_cache();
FILE *r0 = fopen(train_list, "r");
assert(r0 && "train-list doesn't exists");
FILE* r1 = fopen(test_list, "r");
assert(r1 && "test-list doesn't exists");
char* file = (char*)malloc(1024);
int dirlen = (base_dir != 0) ? strlen(base_dir) + 1 : 0;
ccv_array_t* categorizeds = ccv_array_new(sizeof(ccv_categorized_t), 64, 0);
while (fscanf(r0, "%d %s", &c, file) != EOF)
{
char* filename = (char*)ccmalloc(1024);
if (base_dir != 0)
{
strncpy(filename, base_dir, 1024);
filename[dirlen - 1] = '/';
}
strncpy(filename + dirlen, file, 1024 - dirlen);
ccv_file_info_t file_info = {
.filename = filename,
};
// imageNet's category class starts from 1, thus, minus 1 to get 0-index
ccv_categorized_t categorized = ccv_categorized(c - 1, 0, &file_info);
ccv_array_push(categorizeds, &categorized);
}
fclose(r0);
ccv_array_t* tests = ccv_array_new(sizeof(ccv_categorized_t), 64, 0);
while (fscanf(r1, "%d %s", &c, file) != EOF)
{
char* filename = (char*)ccmalloc(1024);
if (base_dir != 0)
{
strncpy(filename, base_dir, 1024);
filename[dirlen - 1] = '/';
}
strncpy(filename + dirlen, file, 1024 - dirlen);
ccv_file_info_t file_info = {
.filename = filename,
};
// imageNet's category class starts from 1, thus, minus 1 to get 0-index
ccv_categorized_t categorized = ccv_categorized(c - 1, 0, &file_info);
ccv_array_push(tests, &categorized);
}
fclose(r1);
free(file);
// #define model_params vgg_d_params
#define model_params matt_c_params
int depth = sizeof(model_params) / sizeof(ccv_convnet_layer_param_t);
ccv_convnet_t* convnet = ccv_convnet_new(1, ccv_size(257, 257), model_params, depth);
if (ccv_convnet_verify(convnet, 1000) == 0)
{
ccv_convnet_layer_train_param_t layer_params[depth];
memset(layer_params, 0, sizeof(layer_params));
for (i = 0; i < depth; i++)
{
layer_params[i].w.decay = 0.0005;
layer_params[i].w.learn_rate = 0.01;
layer_params[i].w.momentum = 0.9;
layer_params[i].bias.decay = 0;
layer_params[i].bias.learn_rate = 0.01;
layer_params[i].bias.momentum = 0.9;
}
// set the two full connect layers to last with dropout rate at 0.5
for (i = depth - 3; i < depth - 1; i++)
layer_params[i].dor = 0.5;
train_params.layer_params = layer_params;
ccv_set_cli_output_levels(ccv_cli_output_level_and_above(CCV_CLI_INFO));
ccv_convnet_supervised_train(convnet, categorizeds, tests, working_dir, train_params);
} else {
PRINT(CCV_CLI_ERROR, "Invalid convnet configuration\n");
}
ccv_convnet_free(convnet);
ccv_disable_cache();
return 0;
}
static void _ccv_set_union_mser(ccv_dense_matrix_t* a, ccv_dense_matrix_t* h, ccv_dense_matrix_t* b, ccv_array_t* seq, ccv_mser_param_t params)
{
assert(params.direction == CCV_BRIGHT_TO_DARK || params.direction == CCV_DARK_TO_BRIGHT);
int v, i, j;
ccv_mser_node_t* node = (ccv_mser_node_t*)ccmalloc(sizeof(ccv_mser_node_t) * a->rows * a->cols);
ccv_mser_node_t** rnode = (ccv_mser_node_t**)ccmalloc(sizeof(ccv_mser_node_t*) * a->rows * a->cols);
if (params.range <= 0)
params.range = 255;
// put it in a block so that the memory allocated can be released in the end
int* buck = (int*)alloca(sizeof(int) * (params.range + 2));
memset(buck, 0, sizeof(int) * (params.range + 2));
ccv_mser_node_t* pnode = node;
// this for_block is the only computation that can be shared between dark to bright and bright to dark
// two MSER alternatives, and it only occupies 10% of overall time, we won't share this computation
// at all (also, we need to reinitialize node for the two passes anyway).
if (h != 0)
{
unsigned char* aptr = a->data.u8;
unsigned char* hptr = h->data.u8;
#define for_block(_for_get_a, _for_get_h) \
for (i = 0; i < a->rows; i++) \
{ \
for (j = 0; j < a->cols; j++) \
if (!_for_get_h(hptr, j, 0)) \
++buck[_for_get_a(aptr, j, 0)]; \
aptr += a->step; \
hptr += h->step; \
} \
for (i = 1; i <= params.range; i++) \
buck[i] += buck[i - 1]; \
buck[params.range + 1] = buck[params.range]; \
aptr = a->data.u8; \
hptr = h->data.u8; \
for (i = 0; i < a->rows; i++) \
{ \
for (j = 0; j < a->cols; j++) \
{ \
_ccv_mser_init_node(pnode, j, i); \
if (!_for_get_h(hptr, j, 0)) \
rnode[--buck[_for_get_a(aptr, j, 0)]] = pnode; \
else \
pnode->shortcut = 0; /* this means the pnode is not available */ \
++pnode; \
} \
aptr += a->step; \
hptr += h->step; \
}
ccv_matrix_getter_integer_only_a(a->type, ccv_matrix_getter_integer_only, h->type, for_block);
#undef for_block
} else {
unsigned char* aptr = a->data.u8;
#define for_block(_, _for_get) \
for (i = 0; i < a->rows; i++) \
{ \
for (j = 0; j < a->cols; j++) \
++buck[_for_get(aptr, j, 0)]; \
aptr += a->step; \
} \
for (i = 1; i <= params.range; i++) \
buck[i] += buck[i - 1]; \
buck[params.range + 1] = buck[params.range]; \
aptr = a->data.u8; \
for (i = 0; i < a->rows; i++) \
{ \
for (j = 0; j < a->cols; j++) \
{ \
_ccv_mser_init_node(pnode, j, i); \
rnode[--buck[_for_get(aptr, j, 0)]] = pnode; \
++pnode; \
} \
aptr += a->step; \
}
ccv_matrix_getter_integer_only(a->type, for_block);
#undef for_block
}
ccv_array_t* history_list = ccv_array_new(sizeof(ccv_mser_history_t), 64, 0);
for (v = 0; v <= params.range; v++)
{
int range_segment = buck[params.direction == CCV_DARK_TO_BRIGHT ? v : params.range - v];
int range_segment_cap = buck[params.direction == CCV_DARK_TO_BRIGHT ? v + 1 : params.range - v + 1];
for (i = range_segment; i < range_segment_cap; i++)
{
pnode = rnode[i];
// try to merge pnode with its neighbors
static int dx[] = {-1, 0, 1, -1, 1, -1, 0, 1};
static int dy[] = {-1, -1, -1, 0, 0, 1, 1, 1};
ccv_mser_node_t* node0 = _ccv_mser_find_root(pnode);
for (j = 0; j < 8; j++)
{
int x = dx[j] + pnode->point.x;
int y = dy[j] + pnode->point.y;
if (x >= 0 && x < a->cols && y >= 0 && y < a->rows)
{
ccv_mser_node_t* nnode = pnode + dx[j] + dy[j] * a->cols;
if (nnode->shortcut == 0) // this is a void node, skip
continue;
ccv_mser_node_t* node1 = _ccv_mser_find_root(nnode);
if (node0 != node1)
{
// grep the extended root information
ccv_mser_history_t* root0 = (node0->root >= 0) ? (ccv_mser_history_t*)ccv_array_get(history_list, node0->root) : 0;
ccv_mser_history_t* root1 = (node1->root >= 0) ? (ccv_mser_history_t*)ccv_array_get(history_list, node1->root) : 0;
// swap the node if root1 has higher rank, or larger in size, or root0 is non-existent
if ((root0 && root1 && (root1->value > root0->value
|| (root1->value == root0->value && root1->rank > root0->rank)
|| (root1->value == root0->value && root1->rank == root0->rank && root1->size > root0->size)))
|| (root1 && !root0))
{
ccv_mser_node_t* exnode = node0;
node0 = node1;
node1 = exnode;
ccv_mser_history_t* root = root0;
root0 = root1;
root1 = root;
}
if (!root0)
{
ccv_mser_history_t root = {
.rank = 0,
.size = 1,
.value = v,
.shortcut = history_list->rnum,
.parent = history_list->rnum,
.head = node0,
.tail = node1
};
node0->root = history_list->rnum;
ccv_array_push(history_list, &root);
root0 = (ccv_mser_history_t*)ccv_array_get(history_list, history_list->rnum - 1);
assert(node1->root == -1);
} else if (root0->value < v) {
// conceal the old root as history (er), making a new one and pointing to it
root0->shortcut = root0->parent = history_list->rnum;
ccv_mser_history_t root = *root0;
root.value = v;
node0->root = history_list->rnum;
ccv_array_push(history_list, &root);
root0 = (ccv_mser_history_t*)ccv_array_get(history_list, history_list->rnum - 1);
root1 = (node1->root >= 0) ? (ccv_mser_history_t*)ccv_array_get(history_list, node1->root) : 0; // the memory may be reallocated
root0->rank = ccv_max(root0->rank, (root1 ? root1->rank : 0)) + 1;
}
if (root1)
{
if (root1->value < root0->value) // in this case, root1 is sealed as well
root1->parent = node0->root;
// thus, if root1->parent == itself && root1->shortcut != itself
// it is voided, and not sealed
root1->shortcut = node0->root;
}
// merge the two
node1->shortcut = node0;
root0->size += root1 ? root1->size : 1;
/* insert one endless double link list to another, see illustration:
* 0->1->2->3->4->5->0
* a->b->c->d->a
* set 5.next (0.prev.next) point to a
* set 0.prev point to d
* set d.next (a.prev.next) point to 0
* set a.prev point to 5
* the result endless double link list will be:
* 0->1->2->3->4->5->a->b->c->d->0 */
node0->prev->next = node1;
ccv_mser_node_t* prev = node0->prev;
node0->prev = node1->prev;
node1->prev->next = node0; // consider self-referencing
node1->prev = prev;
root0->head = node0;
root0->tail = node0->prev;
}
}
}
int main(int argc, char** argv)
{
static struct option scd_options[] = {
/* help */
{"help", 0, 0, 0},
/* required parameters */
{"positive-list", 1, 0, 0},
{"background-list", 1, 0, 0},
{"negative-count", 1, 0, 0},
{"working-dir", 1, 0, 0},
/* optional parameters */
{0, 0, 0, 0}
};
char* positive_list = 0;
char* background_list = 0;
char* working_dir = 0;
char* base_dir = 0;
int negative_count = 0;
int k;
while (getopt_long_only(argc, argv, "", scd_options, &k) != -1)
{
switch (k)
{
case 0:
exit_with_help();
case 1:
positive_list = optarg;
break;
case 2:
background_list = optarg;
break;
case 3:
negative_count = atoi(optarg);
break;
case 4:
working_dir = optarg;
break;
case 5:
base_dir = optarg;
}
}
assert(positive_list != 0);
assert(background_list != 0);
assert(working_dir != 0);
assert(negative_count > 0);
FILE* r0 = fopen(positive_list, "r");
assert(r0 && "positive-list doesn't exists");
FILE* r1 = fopen(background_list, "r");
assert(r1 && "background-list doesn't exists");
int dirlen = (base_dir != 0) ? strlen(base_dir) + 1 : 0;
ccv_array_t* posfiles = ccv_array_new(sizeof(ccv_file_info_t), 32, 0);
char* file = (char*)malloc(1024);
size_t len = 1024;
ssize_t read;
while ((read = getline(&file, &len, r0)) != -1)
{
while(read > 1 && isspace(file[read - 1]))
read--;
file[read] = 0;
ccv_file_info_t file_info;
file_info.filename = (char*)ccmalloc(1024);
if (base_dir != 0)
{
strncpy(file_info.filename, base_dir, 1024);
file_info.filename[dirlen - 1] = '/';
}
strncpy(file_info.filename + dirlen, file, 1024 - dirlen);
ccv_array_push(posfiles, &file_info);
}
fclose(r0);
ccv_array_t* hard_mine = (ccv_array_t*)ccv_array_new(sizeof(ccv_file_info_t), 32, 0);
while ((read = getline(&file, &len, r1)) != -1)
{
while(read > 1 && isspace(file[read - 1]))
read--;
file[read] = 0;
ccv_file_info_t file_info;
file_info.filename = (char*)ccmalloc(1024);
if (base_dir != 0)
{
strncpy(file_info.filename, base_dir, 1024);
file_info.filename[dirlen - 1] = '/';
}
strncpy(file_info.filename + dirlen, file, 1024 - dirlen);
ccv_array_push(hard_mine, &file_info);
}
fclose(r1);
free(file);
ccv_scd_train_param_t params = {
.boosting = 10,
.size = ccv_size(48, 48),
.feature = {
.base = ccv_size(8, 8),
.range_through = 4,
.step_through = 4,
},
.stop_criteria = {
.hit_rate = 0.995,
.false_positive_rate = 0.5,
.accu_false_positive_rate = 1e-7,
.auc_crit = 1e-5,
.maximum_feature = 2048,
.prune_stage = 3,
.prune_feature = 4,
},
.weight_trimming = 0.98,
int main(int argc, char** argv)
{
static struct option icf_options[] = {
/* help */
{"help", 0, 0, 0},
/* required parameters */
{"positive-list", 1, 0, 0},
{"background-list", 1, 0, 0},
{"validate-list", 1, 0, 0},
{"working-dir", 1, 0, 0},
{"negative-count", 1, 0, 0},
{"positive-count", 1, 0, 0},
{"acceptance", 1, 0, 0},
{"size", 1, 0, 0},
{"feature-size", 1, 0, 0},
{"weak-classifier-count", 1, 0, 0},
/* optional parameters */
{"base-dir", 1, 0, 0},
{"grayscale", 1, 0, 0},
{"margin", 1, 0, 0},
{"deform-shift", 1, 0, 0},
{"deform-angle", 1, 0, 0},
{"deform-scale", 1, 0, 0},
{"min-dimension", 1, 0, 0},
{"bootstrap", 1, 0, 0},
{0, 0, 0, 0}
};
char* positive_list = 0;
char* background_list = 0;
char* validate_list = 0;
char* working_dir = 0;
char* base_dir = 0;
int negative_count = 0;
int positive_count = 0;
ccv_icf_new_param_t params = {
.grayscale = 0,
.margin = ccv_margin(0, 0, 0, 0),
.size = ccv_size(0, 0),
.deform_shift = 1,
.deform_angle = 0,
.deform_scale = 0.075,
.feature_size = 0,
.weak_classifier = 0,
.min_dimension = 2,
.bootstrap = 3,
.detector = ccv_icf_default_params,
};
params.detector.step_through = 4; // for faster negatives bootstrap time
int i, k;
char* token;
char* saveptr;
while (getopt_long_only(argc, argv, "", icf_options, &k) != -1)
{
switch (k)
{
case 0:
exit_with_help();
case 1:
positive_list = optarg;
break;
case 2:
background_list = optarg;
break;
case 3:
validate_list = optarg;
break;
case 4:
working_dir = optarg;
break;
case 5:
negative_count = atoi(optarg);
break;
case 6:
positive_count = atoi(optarg);
break;
case 7:
params.acceptance = atof(optarg);
break;
case 8:
token = strtok_r(optarg, "x", &saveptr);
params.size.width = atoi(token);
token = strtok_r(0, "x", &saveptr);
params.size.height = atoi(token);
break;
case 9:
params.feature_size = atoi(optarg);
break;
case 10:
params.weak_classifier = atoi(optarg);
break;
case 11:
base_dir = optarg;
break;
case 12:
params.grayscale = !!atoi(optarg);
break;
case 13:
token = strtok_r(optarg, ",", &saveptr);
params.margin.left = atoi(token);
token = strtok_r(0, ",", &saveptr);
params.margin.top = atoi(token);
token = strtok_r(0, ",", &saveptr);
params.margin.right = atoi(token);
token = strtok_r(0, ",", &saveptr);
params.margin.bottom = atoi(token);
break;
case 14:
params.deform_shift = atof(optarg);
break;
case 15:
params.deform_angle = atof(optarg);
break;
case 16:
params.deform_scale = atof(optarg);
break;
case 17:
params.min_dimension = atoi(optarg);
break;
case 18:
params.bootstrap = atoi(optarg);
break;
}
}
assert(positive_list != 0);
assert(background_list != 0);
assert(validate_list != 0);
assert(working_dir != 0);
assert(positive_count > 0);
assert(negative_count > 0);
assert(params.size.width > 0);
assert(params.size.height > 0);
ccv_enable_cache(512 * 1024 * 1024);
FILE* r0 = fopen(positive_list, "r");
assert(r0 && "positive-list doesn't exists");
FILE* r1 = fopen(background_list, "r");
assert(r1 && "background-list doesn't exists");
FILE* r2 = fopen(validate_list, "r");
assert(r2 && "validate-list doesn't exists");
char* file = (char*)malloc(1024);
ccv_decimal_pose_t pose;
int dirlen = (base_dir != 0) ? strlen(base_dir) + 1 : 0;
ccv_array_t* posfiles = ccv_array_new(sizeof(ccv_file_info_t), 32, 0);
// roll pitch yaw
while (fscanf(r0, "%s %f %f %f %f %f %f %f", file, &pose.x, &pose.y, &pose.a, &pose.b, &pose.roll, &pose.pitch, &pose.yaw) != EOF)
{
ccv_file_info_t file_info;
file_info.filename = (char*)ccmalloc(1024);
if (base_dir != 0)
{
strncpy(file_info.filename, base_dir, 1024);
file_info.filename[dirlen - 1] = '/';
}
strncpy(file_info.filename + dirlen, file, 1024 - dirlen);
file_info.pose = pose;
ccv_array_push(posfiles, &file_info);
}
fclose(r0);
size_t len = 1024;
ssize_t read;
ccv_array_t* bgfiles = (ccv_array_t*)ccv_array_new(sizeof(ccv_file_info_t), 32, 0);
while ((read = getline(&file, &len, r1)) != -1)
{
while(read > 1 && isspace(file[read - 1]))
read--;
file[read] = 0;
ccv_file_info_t file_info;
file_info.filename = (char*)ccmalloc(1024);
if (base_dir != 0)
{
strncpy(file_info.filename, base_dir, 1024);
file_info.filename[dirlen - 1] = '/';
}
strncpy(file_info.filename + dirlen, file, 1024 - dirlen);
ccv_array_push(bgfiles, &file_info);
}
fclose(r1);
ccv_array_t* validatefiles = ccv_array_new(sizeof(ccv_file_info_t), 32, 0);
// roll pitch yaw
while (fscanf(r2, "%s %f %f %f %f %f %f %f", file, &pose.x, &pose.y, &pose.a, &pose.b, &pose.roll, &pose.pitch, &pose.yaw) != EOF)
{
ccv_file_info_t file_info;
file_info.filename = (char*)ccmalloc(1024);
if (base_dir != 0)
{
strncpy(file_info.filename, base_dir, 1024);
file_info.filename[dirlen - 1] = '/';
}
strncpy(file_info.filename + dirlen, file, 1024 - dirlen);
file_info.pose = pose;
ccv_array_push(validatefiles, &file_info);
}
fclose(r2);
free(file);
ccv_icf_classifier_cascade_t* classifier = ccv_icf_classifier_cascade_new(posfiles, positive_count, bgfiles, negative_count, validatefiles, working_dir, params);
char filename[1024];
snprintf(filename, 1024, "%s/final-cascade", working_dir);
ccv_icf_write_classifier_cascade(classifier, filename);
for (i = 0; i < posfiles->rnum; i++)
{
ccv_file_info_t* file_info = (ccv_file_info_t*)ccv_array_get(posfiles, i);
free(file_info->filename);
}
ccv_array_free(posfiles);
for (i = 0; i < bgfiles->rnum; i++)
{
ccv_file_info_t* file_info = (ccv_file_info_t*)ccv_array_get(bgfiles, i);
free(file_info->filename);
}
ccv_array_free(bgfiles);
for (i = 0; i < validatefiles->rnum; i++)
{
ccv_file_info_t* file_info = (ccv_file_info_t*)ccv_array_get(validatefiles, i);
free(file_info->filename);
}
ccv_array_free(validatefiles);
ccv_disable_cache();
return 0;
}
ccv_nnc_tensor_symbol_t ccv_nnc_find_tensor_symbol_from_graph(const ccv_nnc_symbolic_graph_t* const graph, const ccv_nnc_tensor_symbol_t symbol)
{
if (symbol.graph == graph)
return symbol;
const ccv_nnc_symbolic_graph_t* curr_graph = symbol.graph;
ccv_nnc_tensor_symbol_info_t* const symbol_info = (ccv_nnc_tensor_symbol_info_t*)ccv_array_get(symbol.graph->tensor_symbol_info, symbol.d);
assert(symbol.d >= 0 && symbol.d < curr_graph->tensor_symbol_info->rnum);
while (curr_graph && curr_graph != graph)
curr_graph = curr_graph->p;
if (curr_graph)
{
curr_graph = symbol.graph;
ccv_nnc_tensor_symbol_info_t* curr_symbol_info = symbol_info;
ccv_nnc_tensor_symbol_t curr_symbol = symbol;
while (curr_graph != graph)
{
ccv_nnc_symbolic_graph_t* const p = curr_graph->p;
// I need to find the symbol, it must exist.
assert(curr_symbol_info->p_ref);
// Move on.
curr_symbol.d = curr_symbol_info->p_ref - 1;
curr_symbol.graph = p;
assert(curr_symbol.d >= 0 && curr_symbol.d < p->tensor_symbol_info->rnum);
curr_symbol_info = (ccv_nnc_tensor_symbol_info_t*)ccv_array_get(p->tensor_symbol_info, curr_symbol.d);
curr_graph = p;
}
return curr_symbol;
}
// Otherwise, if the symbol is in the parent graph, this is a bit more expensive because I need to keep a trace stack.
curr_graph = graph;
ccv_array_t* trace = ccv_array_new(sizeof(int), 0, 0);
while (curr_graph && curr_graph != symbol.graph)
{
const int p_idx = curr_graph->p_idx - 1;
ccv_array_push(trace, &p_idx);
curr_graph = curr_graph->p;
}
// If it is not in both the parent graph and the sub-graph, the input is invalid.
assert(curr_graph);
curr_graph = symbol.graph;
ccv_nnc_tensor_symbol_info_t* curr_symbol_info = symbol_info;
ccv_nnc_tensor_symbol_t curr_symbol = symbol;
// The graph is a sub graph of the symbol passed in.
int i;
for (i = trace->rnum - 1; i >= 0; i--)
{
const int p_idx = *(int*)ccv_array_get(trace, i);
assert(p_idx >= 0);
assert(curr_graph->sub_graphs);
assert(curr_symbol_info->s_ref);
assert(p_idx >= 0 && p_idx < curr_symbol_info->s_ref->rnum);
const int s_idx = *(int*)ccv_array_get(curr_symbol_info->s_ref, p_idx);
ccv_nnc_symbolic_graph_t* const s = *(ccv_nnc_symbolic_graph_t**)ccv_array_get(curr_graph->sub_graphs, p_idx);
// I need to find the symbol, it must exist.
assert(s_idx);
curr_symbol.d = s_idx - 1;
curr_symbol.graph = s;
assert(curr_symbol.d >= 0 && curr_symbol.d < s->tensor_symbol_info->rnum);
curr_symbol_info = (ccv_nnc_tensor_symbol_info_t*)ccv_array_get(s->tensor_symbol_info, curr_symbol.d);
// Move on.
curr_graph = s;
}
ccv_array_free(trace);
return curr_symbol;
}
static ccv_nnc_graph_t* ccv_nnc_simple_graph(ccv_convnet_t* convnet, ccv_nnc_tensor_t* input, ccv_nnc_tensor_t* output, ccv_nnc_graph_exec_t* source, ccv_nnc_graph_exec_t* dest, ccv_array_t* tensors)
{
int i;
// We only create the graph compute to the last fc layer.
ccv_nnc_graph_t* vgg = ccv_nnc_graph_new();
ccv_nnc_graph_exec_t previous_exec;
for (i = 0; i < convnet->count; i++)
{
ccv_convnet_layer_t* layer = convnet->layers + i;
int rows, cols, partition;
ccv_convnet_make_output(layer, layer->input.matrix.rows, layer->input.matrix.cols, &rows, &cols, &partition);
ccv_nnc_tensor_t* tensor = output;
if (i < convnet->count - 1)
{
if (layer->type == CCV_CONVNET_FULL_CONNECT)
tensor = ccv_nnc_tensor_new(0, ONE_CPU_TENSOR(rows * cols * partition), 0);
else
tensor = ccv_nnc_tensor_new(0, ONE_CPU_TENSOR(rows, cols, (layer->type == CCV_CONVNET_CONVOLUTIONAL ? layer->net.convolutional.count : layer->input.matrix.channels)), 0);
ccv_array_push(tensors, &tensor);
}
ccv_nnc_graph_exec_t exec = {0};
if (layer->type == CCV_CONVNET_CONVOLUTIONAL)
{
ccv_nnc_tensor_t* w = ccv_nnc_tensor_new(0, ONE_CPU_TENSOR(layer->net.convolutional.count, layer->net.convolutional.rows, layer->net.convolutional.cols, layer->net.convolutional.channels), 0);
memcpy(w->data.f32, layer->w, layer->wnum * sizeof(float));
ccv_nnc_tensor_t* bias = ccv_nnc_tensor_new(0, ONE_CPU_TENSOR(layer->net.convolutional.count), 0);
memcpy(bias->data.f32, layer->bias, layer->net.convolutional.count * sizeof(float));
ccv_array_push(tensors, &w);
ccv_array_push(tensors, &bias);
ccv_nnc_cmd_t cmd = CMD_CONVOLUTION_FORWARD(layer->net.convolutional.count, layer->net.convolutional.rows, layer->net.convolutional.cols, layer->net.convolutional.channels);
ccv_nnc_hint_t hint = ccv_nnc_hint_auto(cmd.info, input->info, tensor->info);
cmd = ccv_nnc_cmd_autotune(cmd, 0, hint, 0, TENSOR_LIST(input, w, bias), TENSOR_LIST(tensor), 0);
exec = ccv_nnc_graph_exec_new(vgg, cmd, hint, TENSOR_LIST(input, w, bias), TENSOR_LIST(tensor));
} else if (layer->type == CCV_CONVNET_MAX_POOL) {
ccv_nnc_cmd_t cmd = ccv_nnc_cmd(CCV_NNC_MAX_POOL_FORWARD, 0, CMD_GENERIC(layer->net.pool.size, layer->net.pool.size, layer->input.matrix.channels), 0);
ccv_nnc_hint_t hint = ccv_nnc_hint_auto(cmd.info, input->info, tensor->info);
exec = ccv_nnc_graph_exec_new(vgg, cmd, hint, TENSOR_LIST(input), TENSOR_LIST(tensor));
} else if (layer->type == CCV_CONVNET_FULL_CONNECT) {
ccv_nnc_tensor_t* w = ccv_nnc_tensor_new(0, ONE_CPU_TENSOR(layer->net.full_connect.count, layer->input.node.count), 0);
memcpy(w->data.f32, layer->w, layer->wnum * sizeof(float));
ccv_nnc_tensor_t* bias = ccv_nnc_tensor_new(0, ONE_CPU_TENSOR(layer->net.full_connect.count), 0);
memcpy(bias->data.f32, layer->bias, layer->net.full_connect.count * sizeof(float));
ccv_array_push(tensors, &w);
ccv_array_push(tensors, &bias);
ccv_nnc_cmd_t cmd = ccv_nnc_cmd(CCV_NNC_GEMM_FORWARD, 0, CMD_GEMM(layer->net.full_connect.count), 0);
// If the input is not what I expected (array), reshape it.
if (input->info.dim[0] != ccv_nnc_tensor_count(input->info))
{
input = ccv_nnc_tensor_new(input->data.u8, ONE_CPU_TENSOR(ccv_nnc_tensor_count(input->info)), 0);
ccv_array_push(tensors, &input);
}
cmd = ccv_nnc_cmd_autotune(cmd, 0, ccv_nnc_no_hint, 0, TENSOR_LIST(input, w, bias), TENSOR_LIST(tensor), 0);
exec = ccv_nnc_graph_exec_new(vgg, cmd, ccv_nnc_no_hint, TENSOR_LIST(input, w, bias), TENSOR_LIST(tensor));
} else {
assert("unreachable");
}
if (i != 0)
ccv_nnc_graph_exec_concat(vgg, previous_exec, exec);
previous_exec = exec;
if (i == 0)
*source = exec;
if (i < convnet->count - 1 &&
(layer->type == CCV_CONVNET_CONVOLUTIONAL || layer->type == CCV_CONVNET_FULL_CONNECT))
{
// Create the ReLU layer.
ccv_nnc_cmd_param_t cmd_params = {};
ccv_nnc_cmd_t cmd = ccv_nnc_cmd(CCV_NNC_RELU_FORWARD, 0, cmd_params, 0);
exec = ccv_nnc_graph_exec_new(vgg, cmd, ccv_nnc_no_hint, TENSOR_LIST(tensor), TENSOR_LIST(tensor));
ccv_nnc_graph_exec_concat(vgg, previous_exec, exec);
previous_exec = exec;
}
if (i == convnet->count - 1)
*dest = exec;
// This is the input of next layer.
input = tensor;
}
return vgg;
}
ccv_array_t* ccv_bbf_detect_objects(ccv_dense_matrix_t* a, ccv_bbf_classifier_cascade_t** _cascade, int count, ccv_bbf_param_t params)
{
int hr = a->rows / ENDORSE(params.size.height);
int wr = a->cols / ENDORSE(params.size.width);
double scale = pow(2., 1. / (params.interval + 1.));
APPROX int next = params.interval + 1;
int scale_upto = (int)(log((double)ccv_min(hr, wr)) / log(scale));
ccv_dense_matrix_t** pyr = (ccv_dense_matrix_t**)alloca(ENDORSE(scale_upto + next * 2) * 4 * sizeof(ccv_dense_matrix_t*));
memset(pyr, 0, (scale_upto + next * 2) * 4 * sizeof(ccv_dense_matrix_t*));
if (ENDORSE(params.size.height != _cascade[0]->size.height || params.size.width != _cascade[0]->size.width))
ccv_resample(a, &pyr[0], 0, a->rows * ENDORSE(_cascade[0]->size.height / params.size.height), a->cols * ENDORSE(_cascade[0]->size.width / params.size.width), CCV_INTER_AREA);
else
pyr[0] = a;
APPROX int i;
int j, k, t, x, y, q;
for (i = 1; ENDORSE(i < ccv_min(params.interval + 1, scale_upto + next * 2)); i++)
ccv_resample(pyr[0], &pyr[i * 4], 0, (int)(pyr[0]->rows / pow(scale, i)), (int)(pyr[0]->cols / pow(scale, i)), CCV_INTER_AREA);
for (i = next; ENDORSE(i < scale_upto + next * 2); i++)
ccv_sample_down(pyr[i * 4 - next * 4], &pyr[i * 4], 0, 0, 0);
if (params.accurate)
for (i = next * 2; ENDORSE(i < scale_upto + next * 2); i++)
{
ccv_sample_down(pyr[i * 4 - next * 4], &pyr[i * 4 + 1], 0, 1, 0);
ccv_sample_down(pyr[i * 4 - next * 4], &pyr[i * 4 + 2], 0, 0, 1);
ccv_sample_down(pyr[i * 4 - next * 4], &pyr[i * 4 + 3], 0, 1, 1);
}
ccv_array_t* idx_seq;
ccv_array_t* seq = ccv_array_new(sizeof(ccv_comp_t), 64, 0);
ccv_array_t* seq2 = ccv_array_new(sizeof(ccv_comp_t), 64, 0);
ccv_array_t* result_seq = ccv_array_new(sizeof(ccv_comp_t), 64, 0);
/* detect in multi scale */
for (t = 0; t < count; t++)
{
ccv_bbf_classifier_cascade_t* cascade = _cascade[t];
APPROX float scale_x = (float) params.size.width / (float) cascade->size.width;
APPROX float scale_y = (float) params.size.height / (float) cascade->size.height;
ccv_array_clear(seq);
for (i = 0; ENDORSE(i < scale_upto); i++)
{
APPROX int dx[] = {0, 1, 0, 1};
APPROX int dy[] = {0, 0, 1, 1};
APPROX int i_rows = pyr[i * 4 + next * 8]->rows - ENDORSE(cascade->size.height >> 2);
APPROX int steps[] = { pyr[i * 4]->step, pyr[i * 4 + next * 4]->step, pyr[i * 4 + next * 8]->step };
APPROX int i_cols = pyr[i * 4 + next * 8]->cols - ENDORSE(cascade->size.width >> 2);
int paddings[] = { pyr[i * 4]->step * 4 - i_cols * 4,
pyr[i * 4 + next * 4]->step * 2 - i_cols * 2,
pyr[i * 4 + next * 8]->step - i_cols };
for (q = 0; q < (params.accurate ? 4 : 1); q++)
{
APPROX unsigned char* u8[] = { pyr[i * 4]->data.u8 + dx[q] * 2 + dy[q] * pyr[i * 4]->step * 2, pyr[i * 4 + next * 4]->data.u8 + dx[q] + dy[q] * pyr[i * 4 + next * 4]->step, pyr[i * 4 + next * 8 + q]->data.u8 };
for (y = 0; ENDORSE(y < i_rows); y++)
{
for (x = 0; ENDORSE(x < i_cols); x++)
{
APPROX float sum;
APPROX int flag = 1;
ccv_bbf_stage_classifier_t* classifier = cascade->stage_classifier;
for (j = 0; j < ENDORSE(cascade->count); ++j, ++classifier)
{
sum = 0;
APPROX float* alpha = classifier->alpha;
ccv_bbf_feature_t* feature = classifier->feature;
for (k = 0; k < ENDORSE(classifier->count); ++k, alpha += 2, ++feature)
sum += alpha[_ccv_run_bbf_feature(feature, ENDORSE(steps), u8)];
if (ENDORSE(sum) < ENDORSE(classifier->threshold))
{
flag = 0;
break;
}
}
if (ENDORSE(flag))
{
ccv_comp_t comp;
comp.rect = ccv_rect((int)((x * 4 + dx[q] * 2) * scale_x + 0.5), (int)((y * 4 + dy[q] * 2) * scale_y + 0.5), (int)(cascade->size.width * scale_x + 0.5), (int)(cascade->size.height * scale_y + 0.5));
comp.neighbors = 1;
comp.classification.id = t;
comp.classification.confidence = sum;
ccv_array_push(seq, &comp);
}
u8[0] += 4;
u8[1] += 2;
u8[2] += 1;
}
u8[0] += paddings[0];
u8[1] += paddings[1];
u8[2] += paddings[2];
}
}
scale_x *= scale;
scale_y *= scale;
}
/* the following code from OpenCV's haar feature implementation */
if(params.min_neighbors == 0)
{
for (i = 0; ENDORSE(i < seq->rnum); i++)
{
ccv_comp_t* comp = (ccv_comp_t*)ENDORSE(ccv_array_get(seq, i));
ccv_array_push(result_seq, comp);
}
} else {
idx_seq = 0;
ccv_array_clear(seq2);
// group retrieved rectangles in order to filter out noise
int ncomp = ccv_array_group(seq, &idx_seq, _ccv_is_equal_same_class, 0);
ccv_comp_t* comps = (ccv_comp_t*)ccmalloc((ncomp + 1) * sizeof(ccv_comp_t));
memset(comps, 0, (ncomp + 1) * sizeof(ccv_comp_t));
// count number of neighbors
for(i = 0; ENDORSE(i < seq->rnum); i++)
{
ccv_comp_t r1 = *(ccv_comp_t*)ENDORSE(ccv_array_get(seq, i));
int idx = *(int*)ENDORSE(ccv_array_get(idx_seq, i));
if (ENDORSE(comps[idx].neighbors) == 0)
comps[idx].classification.confidence = r1.classification.confidence;
++comps[idx].neighbors;
comps[idx].rect.x += r1.rect.x;
comps[idx].rect.y += r1.rect.y;
comps[idx].rect.width += r1.rect.width;
comps[idx].rect.height += r1.rect.height;
comps[idx].classification.id = r1.classification.id;
comps[idx].classification.confidence = ccv_max(comps[idx].classification.confidence, r1.classification.confidence);
}
// calculate average bounding box
for(i = 0; ENDORSE(i < ncomp); i++)
{
int n = ENDORSE(comps[i].neighbors);
if(n >= params.min_neighbors)
{
ccv_comp_t comp;
comp.rect.x = (comps[i].rect.x * 2 + n) / (2 * n);
comp.rect.y = (comps[i].rect.y * 2 + n) / (2 * n);
comp.rect.width = (comps[i].rect.width * 2 + n) / (2 * n);
comp.rect.height = (comps[i].rect.height * 2 + n) / (2 * n);
comp.neighbors = comps[i].neighbors;
comp.classification.id = comps[i].classification.id;
comp.classification.confidence = comps[i].classification.confidence;
ccv_array_push(seq2, &comp);
}
}
// filter out small face rectangles inside large face rectangles
for(i = 0; ENDORSE(i < seq2->rnum); i++)
{
ccv_comp_t r1 = *(ccv_comp_t*)ENDORSE(ccv_array_get(seq2, i));
APPROX int flag = 1;
for(j = 0; ENDORSE(j < seq2->rnum); j++)
{
ccv_comp_t r2 = *(ccv_comp_t*)ENDORSE(ccv_array_get(seq2, j));
APPROX int distance = (int)(r2.rect.width * 0.25 + 0.5);
if(ENDORSE(i != j &&
r1.classification.id == r2.classification.id &&
r1.rect.x >= r2.rect.x - distance &&
r1.rect.y >= r2.rect.y - distance &&
r1.rect.x + r1.rect.width <= r2.rect.x + r2.rect.width + distance &&
r1.rect.y + r1.rect.height <= r2.rect.y + r2.rect.height + distance &&
(r2.neighbors > ccv_max(3, r1.neighbors) || r1.neighbors < 3)))
{
flag = 0;
break;
}
}
if(ENDORSE(flag))
ccv_array_push(result_seq, &r1);
}
ccv_array_free(idx_seq);
ccfree(comps);
}
}
ccv_array_free(seq);
ccv_array_free(seq2);
ccv_array_t* result_seq2;
/* the following code from OpenCV's haar feature implementation */
if (params.flags & CCV_BBF_NO_NESTED)
{
result_seq2 = ccv_array_new(sizeof(ccv_comp_t), 64, 0);
idx_seq = 0;
// group retrieved rectangles in order to filter out noise
int ncomp = ccv_array_group(result_seq, &idx_seq, _ccv_is_equal, 0);
ccv_comp_t* comps = (ccv_comp_t*)ccmalloc((ncomp + 1) * sizeof(ccv_comp_t));
memset(comps, 0, (ncomp + 1) * sizeof(ccv_comp_t));
// count number of neighbors
for(i = 0; ENDORSE(i < result_seq->rnum); i++)
{
ccv_comp_t r1 = *(ccv_comp_t*)ENDORSE(ccv_array_get(result_seq, i));
int idx = *(int*)ENDORSE(ccv_array_get(idx_seq, i));
if (ENDORSE(comps[idx].neighbors == 0 || comps[idx].classification.confidence < r1.classification.confidence))
{
comps[idx].classification.confidence = r1.classification.confidence;
comps[idx].neighbors = 1;
comps[idx].rect = r1.rect;
comps[idx].classification.id = r1.classification.id;
}
}
// calculate average bounding box
for(i = 0; ENDORSE(i < ncomp); i++)
if(ENDORSE(comps[i].neighbors))
ccv_array_push(result_seq2, &comps[i]);
ccv_array_free(result_seq);
ccfree(comps);
} else {
result_seq2 = result_seq;
}
for (i = 1; ENDORSE(i < scale_upto + next * 2); i++)
ccv_matrix_free(pyr[i * 4]);
if (params.accurate)
for (i = next * 2; ENDORSE(i < scale_upto + next * 2); i++)
{
ccv_matrix_free(pyr[i * 4 + 1]);
ccv_matrix_free(pyr[i * 4 + 2]);
ccv_matrix_free(pyr[i * 4 + 3]);
}
if (ENDORSE(params.size.height != _cascade[0]->size.height || params.size.width != _cascade[0]->size.width))
ccv_matrix_free(pyr[0]);
return result_seq2;
}
int main(int argc, char** argv)
{
static struct option swt_options[] = {
/* help */
{"help", 0, 0, 0},
/* optional parameters */
{"size", 1, 0, 0},
{"low-thresh", 1, 0, 0},
{"high-thresh", 1, 0, 0},
{"max-height", 1, 0, 0},
{"min-height", 1, 0, 0},
{"min-area", 1, 0, 0},
{"aspect-ratio", 1, 0, 0},
{"std-ratio", 1, 0, 0},
{"thickness-ratio", 1, 0, 0},
{"height-ratio", 1, 0, 0},
{"intensity-thresh", 1, 0, 0},
{"letter-occlude-thresh", 1, 0, 0},
{"distance-ratio", 1, 0, 0},
{"intersect-ratio", 1, 0, 0},
{"letter-thresh", 1, 0, 0},
{"elongate-ratio", 1, 0, 0},
{"breakdown-ratio", 1, 0, 0},
{"breakdown", 1, 0, 0},
{"iterations", 1, 0, 0},
{"base-dir", 1, 0, 0},
{0, 0, 0, 0}
};
if (argc <= 1)
exit_with_help();
ccv_swt_param_t params = {
.interval = 1,
.same_word_thresh = { 0.2, 0.8 },
.min_neighbors = 1,
.scale_invariant = 0,
.size = 3,
.low_thresh = 78,
.high_thresh = 214,
.max_height = 300,
.min_height = 10,
.min_area = 75,
.letter_occlude_thresh = 2,
.aspect_ratio = 10,
.std_ratio = 0.5,
.thickness_ratio = 1.5,
.height_ratio = 2.0,
.intensity_thresh = 45,
.distance_ratio = 3.0,
.intersect_ratio = 2.0,
.letter_thresh = 3,
.elongate_ratio = 1.3,
.breakdown = 1,
.breakdown_ratio = 1.0,
};
ccv_swt_range_t size_range = {
.min_value = 1,
.max_value = 3,
.step = 2,
.enable = 1,
};
ccv_swt_range_t low_thresh_range = {
.min_value = 50,
.max_value = 150,
.step = 1,
.enable = 1,
};
ccv_swt_range_t high_thresh_range = {
.min_value = 200,
.max_value = 350,
.step = 1,
.enable = 1,
};
ccv_swt_range_t max_height_range = {
.min_value = 500,
.max_value = 500,
.step = 1,
.enable = 1,
};
ccv_swt_range_t min_height_range = {
.min_value = 5,
.max_value = 30,
.step = 1,
.enable = 1,
};
ccv_swt_range_t min_area_range = {
.min_value = 10,
.max_value = 100,
.step = 1,
.enable = 1,
};
ccv_swt_range_t letter_occlude_thresh_range = {
.min_value = 0,
.max_value = 5,
.step = 1,
.enable = 1,
};
ccv_swt_range_t aspect_ratio_range = {
.min_value = 5,
.max_value = 15,
.step = 1,
.enable = 1,
};
ccv_swt_range_t std_ratio_range = {
.min_value = 0.1,
.max_value = 1.0,
.step = 0.01,
.enable = 1,
};
ccv_swt_range_t thickness_ratio_range = {
.min_value = 1.0,
.max_value = 2.0,
.step = 0.1,
.enable = 1,
};
ccv_swt_range_t height_ratio_range = {
.min_value = 1.0,
.max_value = 3.0,
.step = 0.1,
.enable = 1,
};
ccv_swt_range_t intensity_thresh_range = {
.min_value = 1,
.max_value = 50,
.step = 1,
.enable = 1,
};
ccv_swt_range_t distance_ratio_range = {
.min_value = 1.0,
.max_value = 5.0,
.step = 0.1,
.enable = 1,
};
ccv_swt_range_t intersect_ratio_range = {
.min_value = 0.0,
.max_value = 5.0,
.step = 0.1,
.enable = 1,
};
ccv_swt_range_t letter_thresh_range = {
.min_value = 0,
.max_value = 5,
.step = 1,
.enable = 1,
};
ccv_swt_range_t elongate_ratio_range = {
.min_value = 0.1,
.max_value = 2.5,
.step = 0.1,
.enable = 1,
};
ccv_swt_range_t breakdown_ratio_range = {
.min_value = 0.5,
.max_value = 1.5,
.step = 0.01,
.enable = 1,
};
int i, j, k, iterations = 10;
while (getopt_long_only(argc - 1, argv + 1, "", swt_options, &k) != -1)
{
switch (k)
{
case 0:
exit_with_help();
case 1:
decode_range(optarg, &size_range);
break;
case 2:
decode_range(optarg, &low_thresh_range);
break;
case 3:
decode_range(optarg, &high_thresh_range);
break;
case 4:
decode_range(optarg, &max_height_range);
break;
case 5:
decode_range(optarg, &min_height_range);
break;
case 6:
decode_range(optarg, &min_area_range);
break;
case 7:
decode_range(optarg, &aspect_ratio_range);
break;
case 8:
decode_range(optarg, &std_ratio_range);
break;
case 9:
decode_range(optarg, &thickness_ratio_range);
break;
case 10:
decode_range(optarg, &height_ratio_range);
break;
case 11:
decode_range(optarg, &intensity_thresh_range);
break;
case 12:
decode_range(optarg, &letter_occlude_thresh_range);
break;
case 13:
decode_range(optarg, &distance_ratio_range);
break;
case 14:
decode_range(optarg, &intersect_ratio_range);
break;
case 15:
decode_range(optarg, &letter_thresh_range);
break;
case 16:
decode_range(optarg, &elongate_ratio_range);
break;
case 17:
decode_range(optarg, &breakdown_ratio_range);
break;
case 18:
params.breakdown = !!atoi(optarg);
break;
case 19:
iterations = atoi(optarg);
break;
case 20:
chdir(optarg);
break;
}
}
FILE* r = fopen(argv[1], "rt");
if (!r)
exit_with_help();
ccv_enable_cache(1024 * 1024 * 1024);
ccv_array_t* aof = ccv_array_new(sizeof(char*), 64, 0);
ccv_array_t* aow = ccv_array_new(sizeof(ccv_array_t*), 64, 0);
ccv_array_t* cw = 0;
char* file = (char*)malloc(1024);
size_t len = 1024;
ssize_t read;
while ((read = getline(&file, &len, r)) != -1)
{
while(read > 1 && isspace(file[read - 1]))
read--;
file[read] = 0;
double x, y, width, height;
int recognized = sscanf(file, "%lf %lf %lf %lf", &x, &y, &width, &height);
if (recognized == 4)
{
ccv_rect_t rect = {
.x = (int)(x + 0.5),
.y = (int)(y + 0.5),
.width = (int)(width + 0.5),
.height = (int)(height + 0.5)
};
ccv_array_push(cw, &rect);
} else {
char* name = (char*)malloc(ccv_min(1023, strlen(file)) + 1);
strncpy(name, file, ccv_min(1023, strlen(file)) + 1);
ccv_array_push(aof, &name);
cw = ccv_array_new(sizeof(ccv_rect_t), 1, 0);
ccv_array_push(aow, &cw);
}
}
free(file);
printf("loaded %d images for parameter search of:\n", aof->rnum);
if (size_range.enable)
printf(" - canny size from %d to %d, += %lg\n", (int)(size_range.min_value + 0.5), (int)(size_range.max_value + 0.5), size_range.step);
if (std_ratio_range.enable)
printf(" - std threshold ratio from %lg to %lg, += %lg\n", std_ratio_range.min_value, std_ratio_range.max_value, std_ratio_range.step);
if (max_height_range.enable)
printf(" - maximum height from %d to %d, += %lg\n", (int)(max_height_range.min_value + 0.5), (int)(max_height_range.max_value + 0.5), max_height_range.step);
if (min_height_range.enable)
printf(" - minimum height from %d to %d, += %lg\n", (int)(min_height_range.min_value + 0.5), (int)(min_height_range.max_value + 0.5), min_height_range.step);
if (min_area_range.enable)
printf(" - minimum area from %d to %d, += %lg\n", (int)(min_area_range.min_value + 0.5), (int)(min_area_range.max_value + 0.5), min_area_range.step);
if (letter_occlude_thresh_range.enable)
printf(" - letter occlude threshold from %d to %d, += %lg\n", (int)(letter_occlude_thresh_range.min_value + 0.5), (int)(letter_occlude_thresh_range.max_value + 0.5), letter_occlude_thresh_range.step);
if (aspect_ratio_range.enable)
printf(" - aspect ratio threshold from %lg to %lg, += %lg\n", aspect_ratio_range.min_value, aspect_ratio_range.max_value, aspect_ratio_range.step);
if (thickness_ratio_range.enable)
printf(" - thickness ratio threshold from %lg to %lg, += %lg\n", thickness_ratio_range.min_value, thickness_ratio_range.max_value, thickness_ratio_range.step);
if (height_ratio_range.enable)
printf(" - height ratio threshold from %lg to %lg, += %lg\n", height_ratio_range.min_value, height_ratio_range.max_value, height_ratio_range.step);
if (intensity_thresh_range.enable)
printf(" - intensity threshold from %d to %d, += %lg\n", (int)(intensity_thresh_range.min_value + 0.5), (int)(intensity_thresh_range.max_value + 0.5), intensity_thresh_range.step);
if (distance_ratio_range.enable)
printf(" - distance ratio threshold from %lg to %lg, += %lg\n", distance_ratio_range.min_value, distance_ratio_range.max_value, distance_ratio_range.step);
if (intersect_ratio_range.enable)
printf(" - intersect ratio threshold from %lg to %lg, += %lg\n", intersect_ratio_range.min_value, intersect_ratio_range.max_value, intersect_ratio_range.step);
if (letter_thresh_range.enable)
printf(" - minimum number of letters from %d to %d, += %lg\n", (int)(letter_thresh_range.min_value + 0.5), (int)(letter_thresh_range.max_value + 0.5), letter_thresh_range.step);
if (elongate_ratio_range.enable)
printf(" - elongate ratio threshold from %lg to %lg, += %lg\n", elongate_ratio_range.min_value, elongate_ratio_range.max_value, elongate_ratio_range.step);
if (breakdown_ratio_range.enable)
printf(" - breakdown ratio threshold from %lg to %lg, += %lg\n", breakdown_ratio_range.min_value, breakdown_ratio_range.max_value, breakdown_ratio_range.step);
if (low_thresh_range.enable)
printf(" - canny low threshold from %d to %d, += %lg\n", (int)(low_thresh_range.min_value + 0.5), (int)(low_thresh_range.max_value + 0.5), low_thresh_range.step);
if (high_thresh_range.enable)
printf(" - canny high threshold from %d to %d, += %lg\n", (int)(high_thresh_range.min_value + 0.5), (int)(high_thresh_range.max_value + 0.5), high_thresh_range.step);
double best_f = 0, best_precision = 0, best_recall = 0;
double a = 0.5;
double v;
ccv_swt_param_t best_params = params;
#define optimize(parameter, type, rounding) \
if (parameter##_range.enable) \
{ \
params = best_params; \
int total_iterations = 0; \
for (v = parameter##_range.min_value; v <= parameter##_range.max_value; v += parameter##_range.step) \
++total_iterations; \
double* precision = (double*)ccmalloc(sizeof(double) * total_iterations); \
double* recall = (double*)ccmalloc(sizeof(double) * total_iterations); \
double* total_words = (double*)ccmalloc(sizeof(double) * total_iterations); \
memset(precision, 0, sizeof(double) * total_iterations); \
memset(recall, 0, sizeof(double) * total_iterations); \
memset(total_words, 0, sizeof(double) * total_iterations); \
double total_truth = 0; \
for (j = 0; j < aof->rnum; j++) \
{ \
char* name = *(char**)ccv_array_get(aof, j); \
ccv_dense_matrix_t* image = 0; \
ccv_read(name, &image, CCV_IO_GRAY | CCV_IO_ANY_FILE); \
ccv_array_t* truth = *(ccv_array_t**)ccv_array_get(aow, j); \
total_truth += truth->rnum; \
for (v = parameter##_range.min_value, k = 0; v <= parameter##_range.max_value; v += parameter##_range.step, k++) \
{ \
params.parameter = (type)(v + rounding); \
ccv_array_t* words = ccv_swt_detect_words(image, params); \
double one_precision = 0, one_recall = 0; \
_ccv_evaluate_wolf(words, truth, params, &one_precision, &one_recall); \
assert(one_precision <= words->rnum + 0.1); \
precision[k] += one_precision; \
recall[k] += one_recall; \
total_words[k] += words->rnum; \
ccv_array_free(words); \
FLUSH("perform SWT on %s (%d / %d) for " #parameter " = (%lg <- [%lg, %lg])", name, j + 1, aof->rnum, v, parameter##_range.min_value, parameter##_range.max_value); \
} \
ccv_matrix_free(image); \
} \
for (v = parameter##_range.min_value, j = 0; v <= parameter##_range.max_value; v += parameter##_range.step, j++) \
{ \
params.parameter = (type)(v + rounding); \
double f, total_precision = precision[j], total_recall = recall[j]; \
total_precision /= total_words[j]; \
total_recall /= total_truth; \
f = 1.0 / (a / total_precision + (1.0 - a) / total_recall); \
if (f > best_f) \
{ \
best_params = params; \
best_f = f; \
best_precision = total_precision; \
best_recall = total_recall; \
} \
FLUSH("current harmonic mean : %.2lf%%, precision : %.2lf%%, recall : %.2lf%% ; best harmonic mean : %.2lf%%, precision : %.2lf%%, recall : %.2lf%% ; at " #parameter " = %lg (%lg <- [%lg, %lg])", f * 100, total_precision * 100, total_recall * 100, best_f * 100, best_precision * 100, best_recall * 100, (double)best_params.parameter, v, parameter##_range.min_value, parameter##_range.max_value); \
} \
printf("\n"); \
ccfree(precision); \
ccfree(recall); \
ccfree(total_words); \
}
for (i = 0; i < iterations; i++)
{
optimize(size, int, 0.5);
optimize(std_ratio, double, 0);
optimize(max_height, int, 0.5);
optimize(min_height, int, 0.5);
optimize(min_area, int, 0.5);
optimize(letter_occlude_thresh, int, 0.5);
optimize(aspect_ratio, double, 0);
optimize(thickness_ratio, double, 0);
optimize(height_ratio, double, 0);
optimize(intensity_thresh, int, 0.5);
optimize(distance_ratio, double, 0);
optimize(intersect_ratio, double, 0);
optimize(letter_thresh, int, 0.5);
optimize(elongate_ratio, double, 0);
optimize(breakdown_ratio, double, 0);
optimize(low_thresh, int, 0.5);
optimize(high_thresh, int, 0.5);
printf("At iteration %d(of %d) : best parameters for swt is:\n"
"\tsize = %d\n"
"\tlow_thresh = %d\n"
"\thigh_thresh = %d\n"
"\tmax_height = %d\n"
"\tmin_height = %d\n"
"\tmin_area = %d\n"
"\tletter_occlude_thresh = %d\n"
"\taspect_ratio = %lf\n"
"\tstd_ratio = %lf\n"
"\tthickness_ratio = %lf\n"
"\theight_ratio = %lf\n"
"\tintensity_thresh = %d\n"
"\tdistance_ratio = %lf\n"
"\tintersect_ratio = %lf\n"
"\tletter_thresh = %d\n"
"\telongate_ratio = %lf\n"
"\tbreakdown_ratio = %lf\n",
i + 1, iterations,
best_params.size,
best_params.low_thresh,
best_params.high_thresh,
best_params.max_height,
best_params.min_height,
best_params.min_area,
best_params.letter_occlude_thresh,
best_params.aspect_ratio,
best_params.std_ratio,
best_params.thickness_ratio,
best_params.height_ratio,
best_params.intensity_thresh,
best_params.distance_ratio,
best_params.intersect_ratio,
best_params.letter_thresh,
best_params.elongate_ratio,
best_params.breakdown_ratio);
}
#undef optimize
for (i = 0; i < aof->rnum; i++)
{
char* name = *(char**)ccv_array_get(aof, i);
free(name);
ccv_array_t* cw = *(ccv_array_t**)ccv_array_get(aow, i);
ccv_array_free(cw);
}
ccv_array_free(aof);
ccv_array_free(aow);
ccv_drain_cache();
return 0;
}