good chance I didn't break anything

Joseph Redmon

2016-09-12 5c067dc44785a761a0243d8cd634e3ac17d548ad

 src/network.c

@@ -16,9 +16,11 @@
#include "activation_layer.h"
#include "deconvolutional_layer.h"
#include "detection_layer.h"
#include "region_layer.h"
#include "normalization_layer.h"
#include "batchnorm_layer.h"
#include "maxpool_layer.h"
#include "reorg_layer.h"
#include "avgpool_layer.h"
#include "cost_layer.h"
#include "softmax_layer.h"
@@ -64,6 +66,7 @@
        case EXP:
            return net.learning_rate * pow(net.gamma, batch_num);
        case POLY:
            if (batch_num < net.burn_in) return net.learning_rate * pow((float)batch_num / net.burn_in, net.power);
            return net.learning_rate * pow(1 - (float)batch_num / net.max_batches, net.power);
        case RANDOM:
            return net.learning_rate * pow(rand_uniform(0,1), net.power);
@@ -96,12 +99,16 @@
            return "crnn";
        case MAXPOOL:
            return "maxpool";
        case REORG:
            return "reorg";
        case AVGPOOL:
            return "avgpool";
        case SOFTMAX:
            return "softmax";
        case DETECTION:
            return "detection";
        case REGION:
            return "region";
        case DROPOUT:
            return "dropout";
        case CROP:
@@ -159,6 +166,8 @@
            forward_batchnorm_layer(l, state);
        } else if(l.type == DETECTION){
            forward_detection_layer(l, state);
        } else if(l.type == REGION){
            forward_region_layer(l, state);
        } else if(l.type == CONNECTED){
            forward_connected_layer(l, state);
        } else if(l.type == RNN){
@@ -175,6 +184,8 @@
            forward_softmax_layer(l, state);
        } else if(l.type == MAXPOOL){
            forward_maxpool_layer(l, state);
        } else if(l.type == REORG){
            forward_reorg_layer(l, state);
        } else if(l.type == AVGPOOL){
            forward_avgpool_layer(l, state);
        } else if(l.type == DROPOUT){
@@ -216,7 +227,7 @@
float *get_network_output(network net)
{
    #ifdef GPU
        return get_network_output_gpu(net);
        if (gpu_index >= 0) return get_network_output_gpu(net);
    #endif 
    int i;
    for(i = net.n-1; i > 0; --i) if(net.layers[i].type != COST) break;
@@ -229,11 +240,7 @@
    float sum = 0;
    int count = 0;
    for(i = 0; i < net.n; ++i){
        if(net.layers[i].type == COST){
            sum += net.layers[i].cost[0];
            ++count;
        }
        if(net.layers[i].type == DETECTION){
        if(net.layers[i].cost){
            sum += net.layers[i].cost[0];
            ++count;
        }
@@ -277,12 +284,16 @@
            backward_batchnorm_layer(l, state);
        } else if(l.type == MAXPOOL){
            if(i != 0) backward_maxpool_layer(l, state);
        } else if(l.type == REORG){
            backward_reorg_layer(l, state);
        } else if(l.type == AVGPOOL){
            backward_avgpool_layer(l, state);
        } else if(l.type == DROPOUT){
            backward_dropout_layer(l, state);
        } else if(l.type == DETECTION){
            backward_detection_layer(l, state);
        } else if(l.type == REGION){
            backward_region_layer(l, state);
        } else if(l.type == SOFTMAX){
            if(i != 0) backward_softmax_layer(l, state);
        } else if(l.type == CONNECTED){
@@ -307,11 +318,11 @@

float train_network_datum(network net, float *x, float *y)
{
    *net.seen += net.batch;
#ifdef GPU
    if(gpu_index >= 0) return train_network_datum_gpu(net, x, y);
#endif
    network_state state;
    *net.seen += net.batch;
    state.index = 0;
    state.net = net;
    state.input = x;
@@ -362,6 +373,7 @@
    return (float)sum/(n*batch);
}


float train_network_batch(network net, data d, int n)
{
    int i,j;
@@ -392,6 +404,11 @@
    int i;
    for(i = 0; i < net->n; ++i){
        net->layers[i].batch = b;
        #ifdef CUDNN
        if(net->layers[i].type == CONVOLUTIONAL){
            cudnn_convolutional_setup(net->layers + i);
        }
        #endif
    }
}

@@ -403,7 +420,7 @@
    net->h = h;
    int inputs = 0;
    size_t workspace_size = 0;
    //fprintf(stderr, "Resizing to %d x %d...", w, h);
    //fprintf(stderr, "Resizing to %d x %d...\n", w, h);
    //fflush(stderr);
    for (i = 0; i < net->n; ++i){
        layer l = net->layers[i];
@@ -413,6 +430,8 @@
            resize_crop_layer(&l, w, h);
        }else if(l.type == MAXPOOL){
            resize_maxpool_layer(&l, w, h);
        }else if(l.type == REORG){
            resize_reorg_layer(&l, w, h);
        }else if(l.type == AVGPOOL){
            resize_avgpool_layer(&l, w, h);
        }else if(l.type == NORMALIZATION){
@@ -430,11 +449,16 @@
        if(l.type == AVGPOOL) break;
    }
#ifdef GPU
    if(gpu_index >= 0){
        cuda_free(net->workspace);
        net->workspace = cuda_make_array(0, (workspace_size-1)/sizeof(float)+1);
#else
    }else {
        free(net->workspace);
        net->workspace = calloc(1, workspace_size);
    }
#else
    free(net->workspace);
    net->workspace = calloc(1, workspace_size);
#endif
    //fprintf(stderr, " Done!\n");
    return 0;
@@ -650,10 +674,10 @@
        free_layer(net.layers[i]);
    }
    free(net.layers);
    #ifdef GPU
#ifdef GPU
    if(*net.input_gpu) cuda_free(*net.input_gpu);
    if(*net.truth_gpu) cuda_free(*net.truth_gpu);
    if(net.input_gpu) free(net.input_gpu);
    if(net.truth_gpu) free(net.truth_gpu);
    #endif
#endif
}