Play along w/ alphago

Joseph Redmon

2016-03-15 a392bbd0c957a00e3782c96e7ced84a29ff9dd88

 src/network.c

@@ -8,8 +8,11 @@

#include "crop_layer.h"
#include "connected_layer.h"
#include "rnn_layer.h"
#include "crnn_layer.h"
#include "local_layer.h"
#include "convolutional_layer.h"
#include "activation_layer.h"
#include "deconvolutional_layer.h"
#include "detection_layer.h"
#include "normalization_layer.h"
@@ -19,6 +22,7 @@
#include "softmax_layer.h"
#include "dropout_layer.h"
#include "route_layer.h"
#include "shortcut_layer.h"

int get_current_batch(network net)
{
@@ -72,12 +76,18 @@
    switch(a){
        case CONVOLUTIONAL:
            return "convolutional";
        case ACTIVE:
            return "activation";
        case LOCAL:
            return "local";
        case DECONVOLUTIONAL:
            return "deconvolutional";
        case CONNECTED:
            return "connected";
        case RNN:
            return "rnn";
        case CRNN:
            return "crnn";
        case MAXPOOL:
            return "maxpool";
        case AVGPOOL:
@@ -94,6 +104,8 @@
            return "cost";
        case ROUTE:
            return "route";
        case SHORTCUT:
            return "shortcut";
        case NORMALIZATION:
            return "normalization";
        default:
@@ -119,6 +131,7 @@
{
    int i;
    for(i = 0; i < net.n; ++i){
        state.index = i;
        layer l = net.layers[i];
        if(l.delta){
            scal_cpu(l.outputs * l.batch, 0, l.delta, 1);
@@ -127,6 +140,8 @@
            forward_convolutional_layer(l, state);
        } else if(l.type == DECONVOLUTIONAL){
            forward_deconvolutional_layer(l, state);
        } else if(l.type == ACTIVE){
            forward_activation_layer(l, state);
        } else if(l.type == LOCAL){
            forward_local_layer(l, state);
        } else if(l.type == NORMALIZATION){
@@ -135,6 +150,10 @@
            forward_detection_layer(l, state);
        } else if(l.type == CONNECTED){
            forward_connected_layer(l, state);
        } else if(l.type == RNN){
            forward_rnn_layer(l, state);
        } else if(l.type == CRNN){
            forward_crnn_layer(l, state);
        } else if(l.type == CROP){
            forward_crop_layer(l, state);
        } else if(l.type == COST){
@@ -149,6 +168,8 @@
            forward_dropout_layer(l, state);
        } else if(l.type == ROUTE){
            forward_route_layer(l, net);
        } else if(l.type == SHORTCUT){
            forward_shortcut_layer(l, state);
        }
        state.input = l.output;
    }
@@ -167,6 +188,10 @@
            update_deconvolutional_layer(l, rate, net.momentum, net.decay);
        } else if(l.type == CONNECTED){
            update_connected_layer(l, update_batch, rate, net.momentum, net.decay);
        } else if(l.type == RNN){
            update_rnn_layer(l, update_batch, rate, net.momentum, net.decay);
        } else if(l.type == CRNN){
            update_crnn_layer(l, update_batch, rate, net.momentum, net.decay);
        } else if(l.type == LOCAL){
            update_local_layer(l, update_batch, rate, net.momentum, net.decay);
        }
@@ -187,7 +212,7 @@
    int count = 0;
    for(i = 0; i < net.n; ++i){
        if(net.layers[i].type == COST){
            sum += net.layers[i].output[0];
            sum += net.layers[i].cost[0];
            ++count;
        }
        if(net.layers[i].type == DETECTION){
@@ -211,6 +236,7 @@
    float *original_input = state.input;
    float *original_delta = state.delta;
    for(i = net.n-1; i >= 0; --i){
        state.index = i;
        if(i == 0){
            state.input = original_input;
            state.delta = original_delta;
@@ -224,6 +250,8 @@
            backward_convolutional_layer(l, state);
        } else if(l.type == DECONVOLUTIONAL){
            backward_deconvolutional_layer(l, state);
        } else if(l.type == ACTIVE){
            backward_activation_layer(l, state);
        } else if(l.type == NORMALIZATION){
            backward_normalization_layer(l, state);
        } else if(l.type == MAXPOOL){
@@ -238,12 +266,18 @@
            if(i != 0) backward_softmax_layer(l, state);
        } else if(l.type == CONNECTED){
            backward_connected_layer(l, state);
        } else if(l.type == RNN){
            backward_rnn_layer(l, state);
        } else if(l.type == CRNN){
            backward_crnn_layer(l, state);
        } else if(l.type == LOCAL){
            backward_local_layer(l, state);
        } else if(l.type == COST){
            backward_cost_layer(l, state);
        } else if(l.type == ROUTE){
            backward_route_layer(l, net);
        } else if(l.type == SHORTCUT){
            backward_shortcut_layer(l, state);
        }
    }
}
@@ -255,6 +289,8 @@
    if(gpu_index >= 0) return train_network_datum_gpu(net, x, y);
#endif
    network_state state;
    state.index = 0;
    state.net = net;
    state.input = x;
    state.delta = 0;
    state.truth = y;
@@ -307,6 +343,8 @@
{
    int i,j;
    network_state state;
    state.index = 0;
    state.net = net;
    state.train = 1;
    state.delta = 0;
    float sum = 0;
@@ -347,11 +385,12 @@
        layer l = net->layers[i];
        if(l.type == CONVOLUTIONAL){
            resize_convolutional_layer(&l, w, h);
        }else if(l.type == CROP){
            resize_crop_layer(&l, w, h);
        }else if(l.type == MAXPOOL){
            resize_maxpool_layer(&l, w, h);
        }else if(l.type == AVGPOOL){
            resize_avgpool_layer(&l, w, h);
            break;
        }else if(l.type == NORMALIZATION){
            resize_normalization_layer(&l, w, h);
        }else if(l.type == COST){
@@ -363,6 +402,7 @@
        net->layers[i] = l;
        w = l.out_w;
        h = l.out_h;
        if(l.type == AVGPOOL) break;
    }
    //fprintf(stderr, " Done!\n");
    return 0;
@@ -443,6 +483,8 @@
#endif

    network_state state;
    state.net = net;
    state.index = 0;
    state.input = input;
    state.truth = 0;
    state.train = 0;