| | |
| | | #include <stdio.h> |
| | | #include <time.h> |
| | | #include "network.h" |
| | | #include "image.h" |
| | | #include "data.h" |
| | | #include "utils.h" |
| | | |
| | | #include "crop_layer.h" |
| | | #include "connected_layer.h" |
| | | #include "convolutional_layer.h" |
| | | #include "deconvolutional_layer.h" |
| | | #include "detection_layer.h" |
| | | #include "maxpool_layer.h" |
| | | #include "cost_layer.h" |
| | | #include "softmax_layer.h" |
| | | #include "dropout_layer.h" |
| | | #include "route_layer.h" |
| | | |
| | | char *get_layer_string(LAYER_TYPE a) |
| | | { |
| | | switch(a){ |
| | | case CONVOLUTIONAL: |
| | | return "convolutional"; |
| | | case DECONVOLUTIONAL: |
| | | return "deconvolutional"; |
| | | case CONNECTED: |
| | | return "connected"; |
| | | case MAXPOOL: |
| | | return "maxpool"; |
| | | case SOFTMAX: |
| | | return "softmax"; |
| | | case DETECTION: |
| | | return "detection"; |
| | | case DROPOUT: |
| | | return "dropout"; |
| | | case CROP: |
| | | return "crop"; |
| | | case COST: |
| | | return "cost"; |
| | | case ROUTE: |
| | | return "route"; |
| | | default: |
| | | break; |
| | | } |
| | | return "none"; |
| | | } |
| | | |
| | | network make_network(int n) |
| | | { |
| | | network net; |
| | | network net = {0}; |
| | | net.n = n; |
| | | net.layers = calloc(net.n, sizeof(void *)); |
| | | net.types = calloc(net.n, sizeof(LAYER_TYPE)); |
| | | net.layers = calloc(net.n, sizeof(layer)); |
| | | #ifdef GPU |
| | | net.input_gpu = calloc(1, sizeof(float *)); |
| | | net.truth_gpu = calloc(1, sizeof(float *)); |
| | | #endif |
| | | return net; |
| | | } |
| | | |
| | | void forward_network(network net, double *input) |
| | | void forward_network(network net, network_state state) |
| | | { |
| | | int i; |
| | | for(i = 0; i < net.n; ++i){ |
| | | if(net.types[i] == CONVOLUTIONAL){ |
| | | convolutional_layer layer = *(convolutional_layer *)net.layers[i]; |
| | | forward_convolutional_layer(layer, input); |
| | | input = layer.output; |
| | | layer l = net.layers[i]; |
| | | if(l.type == CONVOLUTIONAL){ |
| | | forward_convolutional_layer(l, state); |
| | | } else if(l.type == DECONVOLUTIONAL){ |
| | | forward_deconvolutional_layer(l, state); |
| | | } else if(l.type == DETECTION){ |
| | | forward_detection_layer(l, state); |
| | | } else if(l.type == CONNECTED){ |
| | | forward_connected_layer(l, state); |
| | | } else if(l.type == CROP){ |
| | | forward_crop_layer(l, state); |
| | | } else if(l.type == COST){ |
| | | forward_cost_layer(l, state); |
| | | } else if(l.type == SOFTMAX){ |
| | | forward_softmax_layer(l, state); |
| | | } else if(l.type == MAXPOOL){ |
| | | forward_maxpool_layer(l, state); |
| | | } else if(l.type == DROPOUT){ |
| | | forward_dropout_layer(l, state); |
| | | } else if(l.type == ROUTE){ |
| | | forward_route_layer(l, net); |
| | | } |
| | | else if(net.types[i] == CONNECTED){ |
| | | connected_layer layer = *(connected_layer *)net.layers[i]; |
| | | forward_connected_layer(layer, input); |
| | | input = layer.output; |
| | | } |
| | | else if(net.types[i] == SOFTMAX){ |
| | | softmax_layer layer = *(softmax_layer *)net.layers[i]; |
| | | forward_softmax_layer(layer, input); |
| | | input = layer.output; |
| | | } |
| | | else if(net.types[i] == MAXPOOL){ |
| | | maxpool_layer layer = *(maxpool_layer *)net.layers[i]; |
| | | forward_maxpool_layer(layer, input); |
| | | input = layer.output; |
| | | } |
| | | state.input = l.output; |
| | | } |
| | | } |
| | | |
| | | void update_network(network net, double step) |
| | | void update_network(network net) |
| | | { |
| | | int i; |
| | | int update_batch = net.batch*net.subdivisions; |
| | | for(i = 0; i < net.n; ++i){ |
| | | if(net.types[i] == CONVOLUTIONAL){ |
| | | convolutional_layer layer = *(convolutional_layer *)net.layers[i]; |
| | | update_convolutional_layer(layer, step, 0.9, .01); |
| | | } |
| | | 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] == CONNECTED){ |
| | | connected_layer layer = *(connected_layer *)net.layers[i]; |
| | | update_connected_layer(layer, step, .9, 0); |
| | | layer l = net.layers[i]; |
| | | if(l.type == CONVOLUTIONAL){ |
| | | update_convolutional_layer(l, update_batch, net.learning_rate, net.momentum, net.decay); |
| | | } else if(l.type == DECONVOLUTIONAL){ |
| | | update_deconvolutional_layer(l, net.learning_rate, net.momentum, net.decay); |
| | | } else if(l.type == CONNECTED){ |
| | | update_connected_layer(l, update_batch, net.learning_rate, net.momentum, net.decay); |
| | | } |
| | | } |
| | | } |
| | | |
| | | double *get_network_output_layer(network net, int i) |
| | | float *get_network_output(network net) |
| | | { |
| | | if(net.types[i] == CONVOLUTIONAL){ |
| | | convolutional_layer layer = *(convolutional_layer *)net.layers[i]; |
| | | return layer.output; |
| | | } else if(net.types[i] == MAXPOOL){ |
| | | maxpool_layer layer = *(maxpool_layer *)net.layers[i]; |
| | | return layer.output; |
| | | } else if(net.types[i] == SOFTMAX){ |
| | | softmax_layer layer = *(softmax_layer *)net.layers[i]; |
| | | return layer.output; |
| | | } else if(net.types[i] == CONNECTED){ |
| | | connected_layer layer = *(connected_layer *)net.layers[i]; |
| | | return layer.output; |
| | | } |
| | | return 0; |
| | | } |
| | | double *get_network_output(network net) |
| | | { |
| | | return get_network_output_layer(net, net.n-1); |
| | | int i; |
| | | for(i = net.n-1; i > 0; --i) if(net.layers[i].type != COST) break; |
| | | return net.layers[i].output; |
| | | } |
| | | |
| | | double *get_network_delta_layer(network net, int i) |
| | | float get_network_cost(network net) |
| | | { |
| | | if(net.types[i] == CONVOLUTIONAL){ |
| | | convolutional_layer layer = *(convolutional_layer *)net.layers[i]; |
| | | return layer.delta; |
| | | } else if(net.types[i] == MAXPOOL){ |
| | | maxpool_layer layer = *(maxpool_layer *)net.layers[i]; |
| | | return layer.delta; |
| | | } else if(net.types[i] == SOFTMAX){ |
| | | softmax_layer layer = *(softmax_layer *)net.layers[i]; |
| | | return layer.delta; |
| | | } else if(net.types[i] == CONNECTED){ |
| | | connected_layer layer = *(connected_layer *)net.layers[i]; |
| | | return layer.delta; |
| | | if(net.layers[net.n-1].type == COST){ |
| | | return net.layers[net.n-1].output[0]; |
| | | } |
| | | if(net.layers[net.n-1].type == DETECTION){ |
| | | return net.layers[net.n-1].cost[0]; |
| | | } |
| | | return 0; |
| | | } |
| | | |
| | | double *get_network_delta(network net) |
| | | int get_predicted_class_network(network net) |
| | | { |
| | | return get_network_delta_layer(net, net.n-1); |
| | | float *out = get_network_output(net); |
| | | int k = get_network_output_size(net); |
| | | return max_index(out, k); |
| | | } |
| | | |
| | | void learn_network(network net, double *input) |
| | | void backward_network(network net, network_state state) |
| | | { |
| | | int i; |
| | | double *prev_input; |
| | | double *prev_delta; |
| | | float *original_input = state.input; |
| | | for(i = net.n-1; i >= 0; --i){ |
| | | if(i == 0){ |
| | | prev_input = input; |
| | | prev_delta = 0; |
| | | state.input = original_input; |
| | | state.delta = 0; |
| | | }else{ |
| | | prev_input = get_network_output_layer(net, i-1); |
| | | prev_delta = get_network_delta_layer(net, i-1); |
| | | layer prev = net.layers[i-1]; |
| | | state.input = prev.output; |
| | | state.delta = prev.delta; |
| | | } |
| | | if(net.types[i] == CONVOLUTIONAL){ |
| | | convolutional_layer layer = *(convolutional_layer *)net.layers[i]; |
| | | learn_convolutional_layer(layer, prev_input); |
| | | if(i != 0) backward_convolutional_layer(layer, prev_input, prev_delta); |
| | | } |
| | | else if(net.types[i] == MAXPOOL){ |
| | | maxpool_layer layer = *(maxpool_layer *)net.layers[i]; |
| | | if(i != 0) backward_maxpool_layer(layer, prev_input, prev_delta); |
| | | } |
| | | else if(net.types[i] == SOFTMAX){ |
| | | softmax_layer layer = *(softmax_layer *)net.layers[i]; |
| | | if(i != 0) backward_softmax_layer(layer, prev_input, prev_delta); |
| | | } |
| | | else if(net.types[i] == CONNECTED){ |
| | | connected_layer layer = *(connected_layer *)net.layers[i]; |
| | | learn_connected_layer(layer, prev_input); |
| | | if(i != 0) backward_connected_layer(layer, prev_input, prev_delta); |
| | | layer l = net.layers[i]; |
| | | if(l.type == CONVOLUTIONAL){ |
| | | backward_convolutional_layer(l, state); |
| | | } else if(l.type == DECONVOLUTIONAL){ |
| | | backward_deconvolutional_layer(l, state); |
| | | } else if(l.type == MAXPOOL){ |
| | | if(i != 0) backward_maxpool_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 == SOFTMAX){ |
| | | if(i != 0) backward_softmax_layer(l, state); |
| | | } else if(l.type == CONNECTED){ |
| | | backward_connected_layer(l, state); |
| | | } else if(l.type == COST){ |
| | | backward_cost_layer(l, state); |
| | | } else if(l.type == ROUTE){ |
| | | backward_route_layer(l, net); |
| | | } |
| | | } |
| | | } |
| | | |
| | | void train_network_batch(network net, batch b) |
| | | float train_network_datum(network net, float *x, float *y) |
| | | { |
| | | #ifdef GPU |
| | | if(gpu_index >= 0) return train_network_datum_gpu(net, x, y); |
| | | #endif |
| | | network_state state; |
| | | state.input = x; |
| | | state.truth = y; |
| | | state.train = 1; |
| | | forward_network(net, state); |
| | | backward_network(net, state); |
| | | float error = get_network_cost(net); |
| | | if((net.seen/net.batch)%net.subdivisions == 0) update_network(net); |
| | | return error; |
| | | } |
| | | |
| | | float train_network_sgd(network net, data d, int n) |
| | | { |
| | | int batch = net.batch; |
| | | float *X = calloc(batch*d.X.cols, sizeof(float)); |
| | | float *y = calloc(batch*d.y.cols, sizeof(float)); |
| | | |
| | | int i; |
| | | float sum = 0; |
| | | for(i = 0; i < n; ++i){ |
| | | net.seen += batch; |
| | | get_random_batch(d, batch, X, y); |
| | | float err = train_network_datum(net, X, y); |
| | | sum += err; |
| | | } |
| | | free(X); |
| | | free(y); |
| | | return (float)sum/(n*batch); |
| | | } |
| | | |
| | | float train_network(network net, data d) |
| | | { |
| | | int batch = net.batch; |
| | | int n = d.X.rows / batch; |
| | | float *X = calloc(batch*d.X.cols, sizeof(float)); |
| | | float *y = calloc(batch*d.y.cols, sizeof(float)); |
| | | |
| | | int i; |
| | | float sum = 0; |
| | | for(i = 0; i < n; ++i){ |
| | | get_next_batch(d, batch, i*batch, X, y); |
| | | net.seen += batch; |
| | | float err = train_network_datum(net, X, y); |
| | | sum += err; |
| | | } |
| | | free(X); |
| | | free(y); |
| | | return (float)sum/(n*batch); |
| | | } |
| | | |
| | | float train_network_batch(network net, data d, int n) |
| | | { |
| | | int i,j; |
| | | int k = get_network_output_size(net); |
| | | int correct = 0; |
| | | for(i = 0; i < b.n; ++i){ |
| | | show_image(b.images[i], "Input"); |
| | | forward_network(net, b.images[i].data); |
| | | image o = get_network_image(net); |
| | | if(o.h) show_image_collapsed(o, "Output"); |
| | | double *output = get_network_output(net); |
| | | double *delta = get_network_delta(net); |
| | | int max_k = 0; |
| | | double max = 0; |
| | | for(j = 0; j < k; ++j){ |
| | | delta[j] = b.truth[i][j]-output[j]; |
| | | if(output[j] > max) { |
| | | max = output[j]; |
| | | max_k = j; |
| | | } |
| | | network_state state; |
| | | state.train = 1; |
| | | float sum = 0; |
| | | int batch = 2; |
| | | for(i = 0; i < n; ++i){ |
| | | for(j = 0; j < batch; ++j){ |
| | | int index = rand()%d.X.rows; |
| | | state.input = d.X.vals[index]; |
| | | state.truth = d.y.vals[index]; |
| | | forward_network(net, state); |
| | | backward_network(net, state); |
| | | sum += get_network_cost(net); |
| | | } |
| | | if(b.truth[i][max_k]) ++correct; |
| | | printf("%f\n", (double)correct/(i+1)); |
| | | learn_network(net, b.images[i].data); |
| | | update_network(net, .001); |
| | | if(i%100 == 0){ |
| | | visualize_network(net); |
| | | cvWaitKey(100); |
| | | } |
| | | update_network(net); |
| | | } |
| | | visualize_network(net); |
| | | print_network(net); |
| | | cvWaitKey(100); |
| | | printf("Accuracy: %f\n", (double)correct/b.n); |
| | | return (float)sum/(n*batch); |
| | | } |
| | | |
| | | int get_network_output_size_layer(network net, int i) |
| | | void set_batch_network(network *net, int b) |
| | | { |
| | | if(net.types[i] == CONVOLUTIONAL){ |
| | | convolutional_layer layer = *(convolutional_layer *)net.layers[i]; |
| | | image output = get_convolutional_image(layer); |
| | | return output.h*output.w*output.c; |
| | | net->batch = b; |
| | | int i; |
| | | for(i = 0; i < net->n; ++i){ |
| | | net->layers[i].batch = b; |
| | | } |
| | | else if(net.types[i] == MAXPOOL){ |
| | | maxpool_layer layer = *(maxpool_layer *)net.layers[i]; |
| | | image output = get_maxpool_image(layer); |
| | | return output.h*output.w*output.c; |
| | | } |
| | | else if(net.types[i] == CONNECTED){ |
| | | connected_layer layer = *(connected_layer *)net.layers[i]; |
| | | return layer.outputs; |
| | | } |
| | | else if(net.types[i] == SOFTMAX){ |
| | | softmax_layer layer = *(softmax_layer *)net.layers[i]; |
| | | return layer.inputs; |
| | | } |
| | | |
| | | /* |
| | | int resize_network(network net, int h, int w, int c) |
| | | { |
| | | fprintf(stderr, "Might be broken, careful!!"); |
| | | 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); |
| | | 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); |
| | | 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{ |
| | | error("Cannot resize this type of layer"); |
| | | } |
| | | } |
| | | return 0; |
| | | } |
| | | */ |
| | | |
| | | int get_network_output_size(network net) |
| | | { |
| | | int i = net.n-1; |
| | | return get_network_output_size_layer(net, i); |
| | | int i; |
| | | for(i = net.n-1; i > 0; --i) if(net.layers[i].type != COST) break; |
| | | return net.layers[i].outputs; |
| | | } |
| | | |
| | | int get_network_input_size(network net) |
| | | { |
| | | return net.layers[0].inputs; |
| | | } |
| | | |
| | | detection_layer get_network_detection_layer(network net) |
| | | { |
| | | int i; |
| | | for(i = 0; i < net.n; ++i){ |
| | | if(net.layers[i].type == DETECTION){ |
| | | return net.layers[i]; |
| | | } |
| | | } |
| | | fprintf(stderr, "Detection layer not found!!\n"); |
| | | detection_layer l = {0}; |
| | | return l; |
| | | } |
| | | |
| | | image get_network_image_layer(network net, int i) |
| | | { |
| | | if(net.types[i] == CONVOLUTIONAL){ |
| | | convolutional_layer layer = *(convolutional_layer *)net.layers[i]; |
| | | return get_convolutional_image(layer); |
| | | layer l = net.layers[i]; |
| | | if (l.out_w && l.out_h && l.out_c){ |
| | | return float_to_image(l.out_w, l.out_h, l.out_c, l.output); |
| | | } |
| | | else if(net.types[i] == MAXPOOL){ |
| | | maxpool_layer layer = *(maxpool_layer *)net.layers[i]; |
| | | return get_maxpool_image(layer); |
| | | } |
| | | return make_empty_image(0,0,0); |
| | | image def = {0}; |
| | | return def; |
| | | } |
| | | |
| | | image get_network_image(network net) |
| | |
| | | image m = get_network_image_layer(net, i); |
| | | if(m.h != 0) return m; |
| | | } |
| | | return make_empty_image(0,0,0); |
| | | image def = {0}; |
| | | return def; |
| | | } |
| | | |
| | | 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_filters(layer, buff); |
| | | layer l = net.layers[i]; |
| | | if(l.type == CONVOLUTIONAL){ |
| | | prev = visualize_convolutional_layer(l, buff, prev); |
| | | } |
| | | } |
| | | } |
| | | |
| | | void top_predictions(network net, int k, int *index) |
| | | { |
| | | int size = get_network_output_size(net); |
| | | float *out = get_network_output(net); |
| | | top_k(out, size, k, index); |
| | | } |
| | | |
| | | |
| | | float *network_predict(network net, float *input) |
| | | { |
| | | #ifdef GPU |
| | | if(gpu_index >= 0) return network_predict_gpu(net, input); |
| | | #endif |
| | | |
| | | network_state state; |
| | | state.input = input; |
| | | state.truth = 0; |
| | | state.train = 0; |
| | | state.delta = 0; |
| | | forward_network(net, state); |
| | | float *out = get_network_output(net); |
| | | return out; |
| | | } |
| | | |
| | | matrix network_predict_data_multi(network net, data test, int n) |
| | | { |
| | | int i,j,b,m; |
| | | int k = get_network_output_size(net); |
| | | matrix pred = make_matrix(test.X.rows, k); |
| | | float *X = calloc(net.batch*test.X.rows, sizeof(float)); |
| | | for(i = 0; i < test.X.rows; i += net.batch){ |
| | | for(b = 0; b < net.batch; ++b){ |
| | | if(i+b == test.X.rows) break; |
| | | memcpy(X+b*test.X.cols, test.X.vals[i+b], test.X.cols*sizeof(float)); |
| | | } |
| | | for(m = 0; m < n; ++m){ |
| | | float *out = network_predict(net, X); |
| | | for(b = 0; b < net.batch; ++b){ |
| | | if(i+b == test.X.rows) break; |
| | | for(j = 0; j < k; ++j){ |
| | | pred.vals[i+b][j] += out[j+b*k]/n; |
| | | } |
| | | } |
| | | } |
| | | } |
| | | free(X); |
| | | return pred; |
| | | } |
| | | |
| | | matrix network_predict_data(network net, data test) |
| | | { |
| | | int i,j,b; |
| | | int k = get_network_output_size(net); |
| | | matrix pred = make_matrix(test.X.rows, k); |
| | | float *X = calloc(net.batch*test.X.cols, sizeof(float)); |
| | | for(i = 0; i < test.X.rows; i += net.batch){ |
| | | for(b = 0; b < net.batch; ++b){ |
| | | if(i+b == test.X.rows) break; |
| | | memcpy(X+b*test.X.cols, test.X.vals[i+b], test.X.cols*sizeof(float)); |
| | | } |
| | | float *out = network_predict(net, X); |
| | | for(b = 0; b < net.batch; ++b){ |
| | | if(i+b == test.X.rows) break; |
| | | for(j = 0; j < k; ++j){ |
| | | pred.vals[i+b][j] = out[j+b*k]; |
| | | } |
| | | } |
| | | } |
| | | free(X); |
| | | return pred; |
| | | } |
| | | |
| | | void print_network(network net) |
| | | { |
| | | int i,j; |
| | | for(i = 0; i < net.n; ++i){ |
| | | double *output; |
| | | int n = 0; |
| | | if(net.types[i] == CONVOLUTIONAL){ |
| | | convolutional_layer layer = *(convolutional_layer *)net.layers[i]; |
| | | output = layer.output; |
| | | image m = get_convolutional_image(layer); |
| | | n = m.h*m.w*m.c; |
| | | } |
| | | else if(net.types[i] == MAXPOOL){ |
| | | maxpool_layer layer = *(maxpool_layer *)net.layers[i]; |
| | | output = layer.output; |
| | | image m = get_maxpool_image(layer); |
| | | n = m.h*m.w*m.c; |
| | | } |
| | | else if(net.types[i] == CONNECTED){ |
| | | connected_layer layer = *(connected_layer *)net.layers[i]; |
| | | output = layer.output; |
| | | n = layer.outputs; |
| | | } |
| | | else if(net.types[i] == SOFTMAX){ |
| | | softmax_layer layer = *(softmax_layer *)net.layers[i]; |
| | | output = layer.output; |
| | | n = layer.inputs; |
| | | } |
| | | double mean = mean_array(output, n); |
| | | double vari = variance_array(output, n); |
| | | printf("Layer %d - Mean: %f, Variance: %f\n",i,mean, vari); |
| | | layer l = net.layers[i]; |
| | | float *output = l.output; |
| | | int n = l.outputs; |
| | | float mean = mean_array(output, n); |
| | | float vari = variance_array(output, n); |
| | | fprintf(stderr, "Layer %d - Mean: %f, Variance: %f\n",i,mean, vari); |
| | | if(n > 100) n = 100; |
| | | for(j = 0; j < n; ++j) printf("%f, ", output[j]); |
| | | if(n == 100)printf(".....\n"); |
| | | printf("\n"); |
| | | for(j = 0; j < n; ++j) fprintf(stderr, "%f, ", output[j]); |
| | | if(n == 100)fprintf(stderr,".....\n"); |
| | | fprintf(stderr, "\n"); |
| | | } |
| | | } |
| | | |
| | | void compare_networks(network n1, network n2, data test) |
| | | { |
| | | matrix g1 = network_predict_data(n1, test); |
| | | matrix g2 = network_predict_data(n2, test); |
| | | int i; |
| | | int a,b,c,d; |
| | | a = b = c = d = 0; |
| | | for(i = 0; i < g1.rows; ++i){ |
| | | int truth = max_index(test.y.vals[i], test.y.cols); |
| | | int p1 = max_index(g1.vals[i], g1.cols); |
| | | int p2 = max_index(g2.vals[i], g2.cols); |
| | | if(p1 == truth){ |
| | | if(p2 == truth) ++d; |
| | | else ++c; |
| | | }else{ |
| | | if(p2 == truth) ++b; |
| | | else ++a; |
| | | } |
| | | } |
| | | printf("%5d %5d\n%5d %5d\n", a, b, c, d); |
| | | float num = pow((abs(b - c) - 1.), 2.); |
| | | float den = b + c; |
| | | printf("%f\n", num/den); |
| | | } |
| | | |
| | | float network_accuracy(network net, data d) |
| | | { |
| | | matrix guess = network_predict_data(net, d); |
| | | float acc = matrix_topk_accuracy(d.y, guess,1); |
| | | free_matrix(guess); |
| | | return acc; |
| | | } |
| | | |
| | | float *network_accuracies(network net, data d) |
| | | { |
| | | static float acc[2]; |
| | | matrix guess = network_predict_data(net, d); |
| | | acc[0] = matrix_topk_accuracy(d.y, guess,1); |
| | | acc[1] = matrix_topk_accuracy(d.y, guess,5); |
| | | free_matrix(guess); |
| | | return acc; |
| | | } |
| | | |
| | | |
| | | float network_accuracy_multi(network net, data d, int n) |
| | | { |
| | | matrix guess = network_predict_data_multi(net, d, n); |
| | | float acc = matrix_topk_accuracy(d.y, guess,1); |
| | | free_matrix(guess); |
| | | return acc; |
| | | } |
| | | |
| | | |