Detection is back, baby\!

Joseph Redmon

2015-02-11 0f645836f193e75c4c3b718369e6fab15b5d19c5

 src/network.c

@@ -8,6 +8,7 @@
#include "crop_layer.h"
#include "connected_layer.h"
#include "convolutional_layer.h"
#include "deconvolutional_layer.h"
#include "maxpool_layer.h"
#include "cost_layer.h"
#include "normalization_layer.h"
@@ -20,6 +21,8 @@
    switch(a){
        case CONVOLUTIONAL:
            return "convolutional";
        case DECONVOLUTIONAL:
            return "deconvolutional";
        case CONNECTED:
            return "connected";
        case MAXPOOL:
@@ -42,8 +45,6 @@
    return "none";
}



network make_network(int n, int batch)
{
    network net;
@@ -53,14 +54,14 @@
    net.types = calloc(net.n, sizeof(LAYER_TYPE));
    net.outputs = 0;
    net.output = 0;
    net.seen = 0;
    #ifdef GPU
    net.input_cl = calloc(1, sizeof(cl_mem));
    net.truth_cl = calloc(1, sizeof(cl_mem));
    net.input_gpu = calloc(1, sizeof(float *));
    net.truth_gpu = calloc(1, sizeof(float *));
    #endif
    return net;
}


void forward_network(network net, float *input, float *truth, int train)
{
    int i;
@@ -70,6 +71,11 @@
            forward_convolutional_layer(layer, input);
            input = layer.output;
        }
        else if(net.types[i] == DECONVOLUTIONAL){
            deconvolutional_layer layer = *(deconvolutional_layer *)net.layers[i];
            forward_deconvolutional_layer(layer, input);
            input = layer.output;
        }
        else if(net.types[i] == CONNECTED){
            connected_layer layer = *(connected_layer *)net.layers[i];
            forward_connected_layer(layer, input);
@@ -77,7 +83,7 @@
        }
        else if(net.types[i] == CROP){
            crop_layer layer = *(crop_layer *)net.layers[i];
            forward_crop_layer(layer, input);
            forward_crop_layer(layer, train, input);
            input = layer.output;
        }
        else if(net.types[i] == COST){
@@ -107,9 +113,12 @@
        }
        else if(net.types[i] == FREEWEIGHT){
            if(!train) continue;
            freeweight_layer layer = *(freeweight_layer *)net.layers[i];
            forward_freeweight_layer(layer, input);
            //freeweight_layer layer = *(freeweight_layer *)net.layers[i];
            //forward_freeweight_layer(layer, input);
        }
        //char buff[256];
        //sprintf(buff, "layer %d", i);
        //cuda_compare(get_network_output_gpu_layer(net, i), input, get_network_output_size_layer(net, i)*net.batch, buff);
    }
}

@@ -121,18 +130,12 @@
            convolutional_layer layer = *(convolutional_layer *)net.layers[i];
            update_convolutional_layer(layer);
        }
        else if(net.types[i] == MAXPOOL){
            //maxpool_layer layer = *(maxpool_layer *)net.layers[i];
        }
        else if(net.types[i] == SOFTMAX){
            //maxpool_layer layer = *(maxpool_layer *)net.layers[i];
        }
        else if(net.types[i] == NORMALIZATION){
            //maxpool_layer layer = *(maxpool_layer *)net.layers[i];
        else if(net.types[i] == DECONVOLUTIONAL){
            deconvolutional_layer layer = *(deconvolutional_layer *)net.layers[i];
            update_deconvolutional_layer(layer);
        }
        else if(net.types[i] == CONNECTED){
            connected_layer layer = *(connected_layer *)net.layers[i];
            //secret_update_connected_layer((connected_layer *)net.layers[i]);
            update_connected_layer(layer);
        }
    }
@@ -143,6 +146,9 @@
    if(net.types[i] == CONVOLUTIONAL){
        convolutional_layer layer = *(convolutional_layer *)net.layers[i];
        return layer.output;
    } else if(net.types[i] == DECONVOLUTIONAL){
        deconvolutional_layer layer = *(deconvolutional_layer *)net.layers[i];
        return layer.output;
    } else if(net.types[i] == MAXPOOL){
        maxpool_layer layer = *(maxpool_layer *)net.layers[i];
        return layer.output;
@@ -178,6 +184,9 @@
    if(net.types[i] == CONVOLUTIONAL){
        convolutional_layer layer = *(convolutional_layer *)net.layers[i];
        return layer.delta;
    } else if(net.types[i] == DECONVOLUTIONAL){
        deconvolutional_layer layer = *(deconvolutional_layer *)net.layers[i];
        return layer.delta;
    } else if(net.types[i] == MAXPOOL){
        maxpool_layer layer = *(maxpool_layer *)net.layers[i];
        return layer.delta;
@@ -247,9 +256,13 @@
            prev_input = get_network_output_layer(net, i-1);
            prev_delta = get_network_delta_layer(net, i-1);
        }

        if(net.types[i] == CONVOLUTIONAL){
            convolutional_layer layer = *(convolutional_layer *)net.layers[i];
            backward_convolutional_layer(layer, prev_input, prev_delta);
        } else if(net.types[i] == DECONVOLUTIONAL){
            deconvolutional_layer layer = *(deconvolutional_layer *)net.layers[i];
            backward_deconvolutional_layer(layer, prev_input, prev_delta);
        }
        else if(net.types[i] == MAXPOOL){
            maxpool_layer layer = *(maxpool_layer *)net.layers[i];
@@ -377,6 +390,9 @@
        if(net->types[i] == CONVOLUTIONAL){
            convolutional_layer *layer = (convolutional_layer *)net->layers[i];
            layer->batch = b;
        }else if(net->types[i] == DECONVOLUTIONAL){
            deconvolutional_layer *layer = (deconvolutional_layer *)net->layers[i];
            layer->batch = b;
        }
        else if(net->types[i] == MAXPOOL){
            maxpool_layer *layer = (maxpool_layer *)net->layers[i];
@@ -415,6 +431,10 @@
        convolutional_layer layer = *(convolutional_layer *)net.layers[i];
        return layer.h*layer.w*layer.c;
    }
    if(net.types[i] == DECONVOLUTIONAL){
        deconvolutional_layer layer = *(deconvolutional_layer *)net.layers[i];
        return layer.h*layer.w*layer.c;
    }
    else if(net.types[i] == MAXPOOL){
        maxpool_layer layer = *(maxpool_layer *)net.layers[i];
        return layer.h*layer.w*layer.c;
@@ -448,6 +468,11 @@
        image output = get_convolutional_image(layer);
        return output.h*output.w*output.c;
    }
    else if(net.types[i] == DECONVOLUTIONAL){
        deconvolutional_layer layer = *(deconvolutional_layer *)net.layers[i];
        image output = get_deconvolutional_image(layer);
        return output.h*output.w*output.c;
    }
    else if(net.types[i] == MAXPOOL){
        maxpool_layer layer = *(maxpool_layer *)net.layers[i];
        image output = get_maxpool_image(layer);
@@ -483,21 +508,31 @@
    for (i = 0; i < net.n; ++i){
        if(net.types[i] == CONVOLUTIONAL){
            convolutional_layer *layer = (convolutional_layer *)net.layers[i];
            resize_convolutional_layer(layer, h, w, c);
            resize_convolutional_layer(layer, h, w);
            image output = get_convolutional_image(*layer);
            h = output.h;
            w = output.w;
            c = output.c;
        } else if(net.types[i] == DECONVOLUTIONAL){
            deconvolutional_layer *layer = (deconvolutional_layer *)net.layers[i];
            resize_deconvolutional_layer(layer, h, w);
            image output = get_deconvolutional_image(*layer);
            h = output.h;
            w = output.w;
            c = output.c;
        }else if(net.types[i] == MAXPOOL){
            maxpool_layer *layer = (maxpool_layer *)net.layers[i];
            resize_maxpool_layer(layer, h, w, c);
            resize_maxpool_layer(layer, h, w);
            image output = get_maxpool_image(*layer);
            h = output.h;
            w = output.w;
            c = output.c;
        }else if(net.types[i] == DROPOUT){
            dropout_layer *layer = (dropout_layer *)net.layers[i];
            resize_dropout_layer(layer, h*w*c);
        }else if(net.types[i] == NORMALIZATION){
            normalization_layer *layer = (normalization_layer *)net.layers[i];
            resize_normalization_layer(layer, h, w, c);
            resize_normalization_layer(layer, h, w);
            image output = get_normalization_image(*layer);
            h = output.h;
            w = output.w;
@@ -527,6 +562,10 @@
        convolutional_layer layer = *(convolutional_layer *)net.layers[i];
        return get_convolutional_image(layer);
    }
    else if(net.types[i] == DECONVOLUTIONAL){
        deconvolutional_layer layer = *(deconvolutional_layer *)net.layers[i];
        return get_deconvolutional_image(layer);
    }
    else if(net.types[i] == MAXPOOL){
        maxpool_layer layer = *(maxpool_layer *)net.layers[i];
        return get_maxpool_image(layer);
@@ -535,6 +574,9 @@
        normalization_layer layer = *(normalization_layer *)net.layers[i];
        return get_normalization_image(layer);
    }
    else if(net.types[i] == DROPOUT){
        return get_network_image_layer(net, i-1);
    }
    else if(net.types[i] == CROP){
        crop_layer layer = *(crop_layer *)net.layers[i];
        return get_crop_image(layer);
@@ -582,7 +624,7 @@
float *network_predict(network net, float *input)
{
    #ifdef GPU
        if(gpu_index >= 0) return network_predict_gpu(net, input);
    if(gpu_index >= 0)  return network_predict_gpu(net, input);
    #endif

    forward_network(net, input, 0, 0);