| | |
| | | #include "maxpool_layer.h" |
| | | #include "softmax_layer.h" |
| | | |
| | | network make_network(int n) |
| | | network make_network(int n, int batch) |
| | | { |
| | | network net; |
| | | net.n = n; |
| | | net.batch = batch; |
| | | net.layers = calloc(net.n, sizeof(void *)); |
| | | net.types = calloc(net.n, sizeof(LAYER_TYPE)); |
| | | net.outputs = 0; |
| | |
| | | return net; |
| | | } |
| | | |
| | | void print_convolutional_cfg(FILE *fp, convolutional_layer *l, int first) |
| | | { |
| | | int i; |
| | | fprintf(fp, "[convolutional]\n"); |
| | | if(first) fprintf(fp, "batch=%d\n" |
| | | "height=%d\n" |
| | | "width=%d\n" |
| | | "channels=%d\n", |
| | | l->batch,l->h, l->w, l->c); |
| | | fprintf(fp, "filters=%d\n" |
| | | "size=%d\n" |
| | | "stride=%d\n" |
| | | "activation=%s\n", |
| | | l->n, l->size, l->stride, |
| | | get_activation_string(l->activation)); |
| | | fprintf(fp, "data="); |
| | | for(i = 0; i < l->n; ++i) fprintf(fp, "%g,", l->biases[i]); |
| | | for(i = 0; i < l->n*l->c*l->size*l->size; ++i) fprintf(fp, "%g,", l->filters[i]); |
| | | fprintf(fp, "\n\n"); |
| | | } |
| | | void print_connected_cfg(FILE *fp, connected_layer *l, int first) |
| | | { |
| | | int i; |
| | | fprintf(fp, "[connected]\n"); |
| | | if(first) fprintf(fp, "batch=%d\ninput=%d\n", l->batch, l->inputs); |
| | | fprintf(fp, "output=%d\n" |
| | | "activation=%s\n", |
| | | l->outputs, |
| | | get_activation_string(l->activation)); |
| | | fprintf(fp, "data="); |
| | | for(i = 0; i < l->outputs; ++i) fprintf(fp, "%g,", l->biases[i]); |
| | | for(i = 0; i < l->inputs*l->outputs; ++i) fprintf(fp, "%g,", l->weights[i]); |
| | | fprintf(fp, "\n\n"); |
| | | } |
| | | |
| | | void print_maxpool_cfg(FILE *fp, maxpool_layer *l, int first) |
| | | { |
| | | fprintf(fp, "[maxpool]\n"); |
| | | if(first) fprintf(fp, "batch=%d\n" |
| | | "height=%d\n" |
| | | "width=%d\n" |
| | | "channels=%d\n", |
| | | l->batch,l->h, l->w, l->c); |
| | | fprintf(fp, "stride=%d\n\n", l->stride); |
| | | } |
| | | |
| | | void print_softmax_cfg(FILE *fp, softmax_layer *l, int first) |
| | | { |
| | | fprintf(fp, "[softmax]\n"); |
| | | if(first) fprintf(fp, "batch=%d\ninput=%d\n", l->batch, l->inputs); |
| | | fprintf(fp, "\n"); |
| | | } |
| | | |
| | | void save_network(network net, char *filename) |
| | | { |
| | | FILE *fp = fopen(filename, "w"); |
| | | if(!fp) file_error(filename); |
| | | int i; |
| | | for(i = 0; i < net.n; ++i) |
| | | { |
| | | if(net.types[i] == CONVOLUTIONAL) |
| | | print_convolutional_cfg(fp, (convolutional_layer *)net.layers[i], i==0); |
| | | else if(net.types[i] == CONNECTED) |
| | | print_connected_cfg(fp, (connected_layer *)net.layers[i], i==0); |
| | | else if(net.types[i] == MAXPOOL) |
| | | print_maxpool_cfg(fp, (maxpool_layer *)net.layers[i], i==0); |
| | | else if(net.types[i] == SOFTMAX) |
| | | print_softmax_cfg(fp, (softmax_layer *)net.layers[i], i==0); |
| | | } |
| | | fclose(fp); |
| | | } |
| | | |
| | | void forward_network(network net, float *input) |
| | | { |
| | | int i; |
| | |
| | | } |
| | | else if(net.types[i] == CONNECTED){ |
| | | connected_layer layer = *(connected_layer *)net.layers[i]; |
| | | update_connected_layer(layer, step, momentum, 0); |
| | | update_connected_layer(layer, step, momentum, decay); |
| | | } |
| | | } |
| | | } |
| | |
| | | float *out = get_network_output(net); |
| | | int i, k = get_network_output_size(net); |
| | | for(i = 0; i < k; ++i){ |
| | | //printf("%f, ", out[i]); |
| | | delta[i] = truth[i] - out[i]; |
| | | sum += delta[i]*delta[i]; |
| | | } |
| | | //printf("\n"); |
| | | return sum; |
| | | } |
| | | |
| | |
| | | |
| | | float train_network_datum(network net, float *x, float *y, float step, float momentum, float decay) |
| | | { |
| | | forward_network(net, x); |
| | | int class = get_predicted_class_network(net); |
| | | float error = backward_network(net, x, y); |
| | | update_network(net, step, momentum, decay); |
| | | //return (y[class]?1:0); |
| | | return error; |
| | | forward_network(net, x); |
| | | //int class = get_predicted_class_network(net); |
| | | float error = backward_network(net, x, y); |
| | | update_network(net, step, momentum, decay); |
| | | //return (y[class]?1:0); |
| | | return error; |
| | | } |
| | | |
| | | float train_network_sgd(network net, data d, int n, float step, float momentum,float decay) |
| | | { |
| | | int i; |
| | | float error = 0; |
| | | int correct = 0; |
| | | int pos = 0; |
| | | for(i = 0; i < n; ++i){ |
| | | int index = rand()%d.X.rows; |
| | | error += train_network_datum(net, d.X.vals[index], d.y.vals[index], step, momentum, decay); |
| | | float err = train_network_datum(net, d.X.vals[index], d.y.vals[index], step, momentum, decay); |
| | | float *y = d.y.vals[index]; |
| | | int class = get_predicted_class_network(net); |
| | | correct += (y[class]?1:0); |
| | | if(y[1]){ |
| | | error += err; |
| | | ++pos; |
| | | } |
| | | |
| | | |
| | | //printf("%d %f %f\n", i,net.output[0], d.y.vals[index][0]); |
| | | //if((i+1)%10 == 0){ |
| | | // printf("%d: %f\n", (i+1), (float)correct/(i+1)); |
| | | //} |
| | | } |
| | | return error/n; |
| | | //printf("Accuracy: %f\n",(float) correct/n); |
| | | return error/pos; |
| | | } |
| | | float train_network_batch(network net, data d, int n, float step, float momentum,float decay) |
| | | { |
| | |
| | | } |
| | | visualize_network(net); |
| | | cvWaitKey(100); |
| | | printf("Accuracy: %f\n", (float)correct/d.X.rows); |
| | | fprintf(stderr, "Accuracy: %f\n", (float)correct/d.X.rows); |
| | | } |
| | | |
| | | int get_network_output_size_layer(network net, int i) |
| | |
| | | return 0; |
| | | } |
| | | |
| | | /* |
| | | int resize_network(network net, int h, int w, int c) |
| | | { |
| | | int i; |
| | | for (i = 0; i < net.n; ++i){ |
| | | if(net.types[i] == CONVOLUTIONAL){ |
| | | convolutional_layer *layer = (convolutional_layer *)net.layers[i]; |
| | | layer->h = h; |
| | | layer->w = w; |
| | | layer->c = c; |
| | | image output = get_convolutional_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]; |
| | | layer->h = h; |
| | | layer->w = w; |
| | | layer->c = c; |
| | | image output = get_maxpool_image(*layer); |
| | | h = output.h; |
| | | w = output.w; |
| | | c = output.c; |
| | | } |
| | | } |
| | | return 0; |
| | | } |
| | | */ |
| | | |
| | | int resize_network(network net, int h, int w, int c) |
| | | { |
| | | int i; |
| | | 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); |
| | | image output = get_convolutional_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); |
| | | image output = get_maxpool_image(*layer); |
| | | h = output.h; |
| | | w = output.w; |
| | | c = output.c; |
| | | } |
| | | else{ |
| | | error("Cannot resize this type of layer"); |
| | | } |
| | | } |
| | | return 0; |
| | | } |
| | | |
| | | int get_network_output_size(network net) |
| | | { |
| | | int i = net.n-1; |
| | |
| | | |
| | | void visualize_network(network net) |
| | | { |
| | | image *prev = 0; |
| | | int i; |
| | | char buff[256]; |
| | | for(i = 0; i < net.n; ++i){ |
| | | sprintf(buff, "Layer %d", i); |
| | | if(net.types[i] == CONVOLUTIONAL){ |
| | | convolutional_layer layer = *(convolutional_layer *)net.layers[i]; |
| | | visualize_convolutional_layer(layer, buff); |
| | | prev = visualize_convolutional_layer(layer, buff, prev); |
| | | } |
| | | } |
| | | } |
| | |
| | | return acc; |
| | | } |
| | | |
| | | |