void load_weights_upto(network *net, char *filename, int cutoff)
{
fprintf(stderr, "Loading weights from %s...", filename);
fflush(stdout);
FILE *fp = fopen(filename, "r");
if(!fp) file_error(filename);
float garbage;
fread(&garbage, sizeof(float), 1, fp);
fread(&garbage, sizeof(float), 1, fp);
fread(&garbage, sizeof(float), 1, fp);
fread(net->seen, sizeof(int), 1, fp);
int i;
for(i = 0; i < net->n && i < cutoff; ++i){
layer l = net->layers[i];
if (l.dontload) continue;
if(l.type == CONVOLUTIONAL){
int num = l.n*l.c*l.size*l.size;
fread(l.biases, sizeof(float), l.n, fp);
if (l.batch_normalize && (!l.dontloadscales)){
fread(l.scales, sizeof(float), l.n, fp);
fread(l.rolling_mean, sizeof(float), l.n, fp);
fread(l.rolling_variance, sizeof(float), l.n, fp);
}
fread(l.filters, sizeof(float), num, fp);
#ifdef GPU
if(gpu_index >= 0){
push_convolutional_layer(l);
}
#endif
}
if(l.type == DECONVOLUTIONAL){
int num = l.n*l.c*l.size*l.size;
fread(l.biases, sizeof(float), l.n, fp);
fread(l.filters, sizeof(float), num, fp);
#ifdef GPU
if(gpu_index >= 0){
push_deconvolutional_layer(l);
}
#endif
}
if(l.type == CONNECTED){
fread(l.biases, sizeof(float), l.outputs, fp);
fread(l.weights, sizeof(float), l.outputs*l.inputs, fp);
#ifdef GPU
if(gpu_index >= 0){
push_connected_layer(l);
}
#endif
}
}
fprintf(stderr, "Done!\n");
fclose(fp);
}
void load_weights_upto(network *net, char *filename, int cutoff)
{
fprintf(stderr, "Loading weights from %s...", filename);
fflush(stdout);
FILE *fp = fopen(filename, "r");
if(!fp) file_error(filename);
fread(&net->learning_rate, sizeof(float), 1, fp);
fread(&net->momentum, sizeof(float), 1, fp);
fread(&net->decay, sizeof(float), 1, fp);
fread(&net->seen, sizeof(int), 1, fp);
int i;
for(i = 0; i < net->n && i < cutoff; ++i){
layer l = net->layers[i];
if(l.type == CONVOLUTIONAL){
int num = l.n*l.c*l.size*l.size;
fread(l.biases, sizeof(float), l.n, fp);
fread(l.filters, sizeof(float), num, fp);
#ifdef GPU
if(gpu_index >= 0){
push_convolutional_layer(l);
}
#endif
}
if(l.type == DECONVOLUTIONAL){
int num = l.n*l.c*l.size*l.size;
fread(l.biases, sizeof(float), l.n, fp);
fread(l.filters, sizeof(float), num, fp);
#ifdef GPU
if(gpu_index >= 0){
push_deconvolutional_layer(l);
}
#endif
}
if(l.type == CONNECTED){
fread(l.biases, sizeof(float), l.outputs, fp);
fread(l.weights, sizeof(float), l.outputs*l.inputs, fp);
#ifdef GPU
if(gpu_index >= 0){
push_connected_layer(l);
}
#endif
}
}
fprintf(stderr, "Done!\n");
fclose(fp);
}
connected_layer parse_connected(list *options, size_params params)
{
int output = option_find_int(options, "output",1);
char *activation_s = option_find_str(options, "activation", "logistic");
ACTIVATION activation = get_activation(activation_s);
connected_layer layer = make_connected_layer(params.batch, params.inputs, output, activation);
char *weights = option_find_str(options, "weights", 0);
char *biases = option_find_str(options, "biases", 0);
parse_data(biases, layer.biases, output);
parse_data(weights, layer.weights, params.inputs*output);
#ifdef GPU
if(weights || biases) push_connected_layer(layer);
#endif
return layer;
}
void load_connected_weights(layer l, FILE *fp, int transpose)
{
fread(l.biases, sizeof(float), l.outputs, fp);
fread(l.weights, sizeof(float), l.outputs*l.inputs, fp);
if(transpose){
transpose_matrix(l.weights, l.inputs, l.outputs);
}
//printf("Biases: %f mean %f variance\n", mean_array(l.biases, l.outputs), variance_array(l.biases, l.outputs));
//printf("Weights: %f mean %f variance\n", mean_array(l.weights, l.outputs*l.inputs), variance_array(l.weights, l.outputs*l.inputs));
if (l.batch_normalize && (!l.dontloadscales)){
fread(l.scales, sizeof(float), l.outputs, fp);
fread(l.rolling_mean, sizeof(float), l.outputs, fp);
fread(l.rolling_variance, sizeof(float), l.outputs, fp);
//printf("Scales: %f mean %f variance\n", mean_array(l.scales, l.outputs), variance_array(l.scales, l.outputs));
//printf("rolling_mean: %f mean %f variance\n", mean_array(l.rolling_mean, l.outputs), variance_array(l.rolling_mean, l.outputs));
//printf("rolling_variance: %f mean %f variance\n", mean_array(l.rolling_variance, l.outputs), variance_array(l.rolling_variance, l.outputs));
}
#ifdef GPU
if(gpu_index >= 0){
push_connected_layer(l);
}
#endif
}
void push_rnn_layer(layer l)
{
push_connected_layer(*(l.input_layer));
push_connected_layer(*(l.self_layer));
push_connected_layer(*(l.output_layer));
}
void client_update(network net, char *address)
{
int fd = socket_setup(0);
struct hostent *hp; /* host information */
struct sockaddr_in server; /* server address */
/* fill in the server's address and data */
bzero((char*)&server, sizeof(server));
server.sin_family = AF_INET;
server.sin_port = htons(SERVER_PORT);
/* look up the address of the server given its name */
hp = gethostbyname(address);
if (!hp) {
perror("no such host");
fprintf(stderr, "could not obtain address of %s\n", "localhost");
}
/* put the host's address into the server address structure */
memcpy((void *)&server.sin_addr, hp->h_addr_list[0], hp->h_length);
if (connect(fd, (struct sockaddr *) &server, sizeof(server)) < 0) {
error("error connecting");
}
/* send a message to the server */
int i;
//printf("Sending\n");
for(i = 0; i < net.n; ++i){
if(net.layers[i].type == CONVOLUTIONAL){
convolutional_layer layer = net.layers[i];
write_all(fd, (char*) layer.bias_updates, layer.n*sizeof(float));
int num = layer.n*layer.c*layer.size*layer.size;
write_all(fd, (char*) layer.filter_updates, num*sizeof(float));
memset(layer.bias_updates, 0, layer.n*sizeof(float));
memset(layer.filter_updates, 0, num*sizeof(float));
}
if(net.layers[i].type == CONNECTED){
connected_layer layer = net.layers[i];
write_all(fd, (char *)layer.bias_updates, layer.outputs*sizeof(float));
write_all(fd, (char *)layer.weight_updates, layer.outputs*layer.inputs*sizeof(float));
memset(layer.bias_updates, 0, layer.outputs*sizeof(float));
memset(layer.weight_updates, 0, layer.inputs*layer.outputs*sizeof(float));
}
}
//printf("Sent\n");
for(i = 0; i < net.n; ++i){
if(net.layers[i].type == CONVOLUTIONAL){
convolutional_layer layer = net.layers[i];
read_all(fd, (char*) layer.biases, layer.n*sizeof(float));
int num = layer.n*layer.c*layer.size*layer.size;
read_all(fd, (char*) layer.filters, num*sizeof(float));
#ifdef GPU
push_convolutional_layer(layer);
#endif
}
if(net.layers[i].type == CONNECTED){
connected_layer layer = net.layers[i];
read_all(fd, (char *)layer.biases, layer.outputs*sizeof(float));
read_all(fd, (char *)layer.weights, layer.outputs*layer.inputs*sizeof(float));
#ifdef GPU
push_connected_layer(layer);
#endif
}
}
//printf("Updated\n");
close(fd);
}
