Optimized resizing of network for random=1
| | |
| | | |
| | | void resize_convolutional_layer(convolutional_layer *l, int w, int h) |
| | | { |
| | | int old_w = l->w; |
| | | int old_h = l->h; |
| | | l->w = w; |
| | | l->h = h; |
| | | int out_w = convolutional_out_width(*l); |
| | |
| | | } |
| | | |
| | | #ifdef GPU |
| | | cuda_free(l->delta_gpu); |
| | | cuda_free(l->output_gpu); |
| | | if (old_w < w || old_h < h) { |
| | | cuda_free(l->delta_gpu); |
| | | cuda_free(l->output_gpu); |
| | | |
| | | l->delta_gpu = cuda_make_array(l->delta, l->batch*l->outputs); |
| | | l->output_gpu = cuda_make_array(l->output, l->batch*l->outputs); |
| | | l->delta_gpu = cuda_make_array(l->delta, l->batch*l->outputs); |
| | | l->output_gpu = cuda_make_array(l->output, l->batch*l->outputs); |
| | | |
| | | if(l->batch_normalize){ |
| | | cuda_free(l->x_gpu); |
| | | cuda_free(l->x_norm_gpu); |
| | | if (l->batch_normalize) { |
| | | cuda_free(l->x_gpu); |
| | | cuda_free(l->x_norm_gpu); |
| | | |
| | | l->x_gpu = cuda_make_array(l->output, l->batch*l->outputs); |
| | | l->x_norm_gpu = cuda_make_array(l->output, l->batch*l->outputs); |
| | | } |
| | | l->x_gpu = cuda_make_array(l->output, l->batch*l->outputs); |
| | | l->x_norm_gpu = cuda_make_array(l->output, l->batch*l->outputs); |
| | | } |
| | | } |
| | | #ifdef CUDNN |
| | | cudnn_convolutional_setup(l); |
| | | #endif |
| | |
| | | cuda_set_device(net->gpu_index); |
| | | if(gpu_index >= 0){ |
| | | cuda_free(net->workspace); |
| | | if (net->input_gpu) { |
| | | cuda_free(*net->input_gpu); |
| | | *net->input_gpu = 0; |
| | | cuda_free(*net->truth_gpu); |
| | | *net->truth_gpu = 0; |
| | | } |
| | | } |
| | | #endif |
| | | int i; |
| | |
| | | //fflush(stderr); |
| | | for (i = 0; i < net->n; ++i){ |
| | | layer l = net->layers[i]; |
| | | printf(" %d: layer = %d,", i, l.type); |
| | | if(l.type == CONVOLUTIONAL){ |
| | | resize_convolutional_layer(&l, w, h); |
| | | }else if(l.type == CROP){ |
| | |
| | | } |
| | | #ifdef GPU |
| | | if(gpu_index >= 0){ |
| | | if(net->input_gpu) { |
| | | cuda_free(*net->input_gpu); |
| | | *net->input_gpu = 0; |
| | | cuda_free(*net->truth_gpu); |
| | | *net->truth_gpu = 0; |
| | | } |
| | | net->workspace = cuda_make_array(0, (workspace_size-1)/sizeof(float)+1); |
| | | printf(" CUDA allocate done! \n"); |
| | | }else { |
| | | free(net->workspace); |
| | | net->workspace = calloc(1, workspace_size); |