| | |
| | | |
| | | image get_maxpool_image(maxpool_layer l) |
| | | { |
| | | int h = (l.h-1)/l.stride + 1; |
| | | int w = (l.w-1)/l.stride + 1; |
| | | int h = l.out_h; |
| | | int w = l.out_w; |
| | | int c = l.c; |
| | | return float_to_image(w,h,c,l.output); |
| | | } |
| | | |
| | | image get_maxpool_delta(maxpool_layer l) |
| | | { |
| | | int h = (l.h-1)/l.stride + 1; |
| | | int w = (l.w-1)/l.stride + 1; |
| | | int h = l.out_h; |
| | | int w = l.out_w; |
| | | int c = l.c; |
| | | return float_to_image(w,h,c,l.delta); |
| | | } |
| | |
| | | l.h = h; |
| | | l.w = w; |
| | | l.c = c; |
| | | l.out_h = h; |
| | | l.out_w = w; |
| | | l.out_w = (w-1)/stride + 1; |
| | | l.out_h = (h-1)/stride + 1; |
| | | l.out_c = c; |
| | | l.outputs = l.out_h * l.out_w * l.out_c; |
| | | l.inputs = l.outputs; |
| | | l.inputs = h*w*c; |
| | | l.size = size; |
| | | l.stride = stride; |
| | | int output_size = ((h-1)/stride+1) * ((w-1)/stride+1) * c * batch; |
| | | int output_size = l.out_h * l.out_w * l.out_c * batch; |
| | | l.indexes = calloc(output_size, sizeof(int)); |
| | | l.output = calloc(output_size, sizeof(float)); |
| | | l.delta = calloc(output_size, sizeof(float)); |
| | |
| | | return l; |
| | | } |
| | | |
| | | void resize_maxpool_layer(maxpool_layer *l, int h, int w) |
| | | void resize_maxpool_layer(maxpool_layer *l, int w, int h) |
| | | { |
| | | int stride = l->stride; |
| | | l->h = h; |
| | | l->w = w; |
| | | int output_size = ((h-1)/l->stride+1) * ((w-1)/l->stride+1) * l->c * l->batch; |
| | | |
| | | l->out_w = (w-1)/stride + 1; |
| | | l->out_h = (h-1)/stride + 1; |
| | | l->outputs = l->out_w * l->out_h * l->c; |
| | | int output_size = l->outputs * l->batch; |
| | | |
| | | l->indexes = realloc(l->indexes, output_size * sizeof(int)); |
| | | l->output = realloc(l->output, output_size * sizeof(float)); |
| | | l->delta = realloc(l->delta, output_size * sizeof(float)); |
| | | |
| | |
| | | cuda_free(l->delta_gpu); |
| | | l->indexes_gpu = cuda_make_int_array(output_size); |
| | | l->output_gpu = cuda_make_array(l->output, output_size); |
| | | l->delta_gpu = cuda_make_array(l->delta, output_size); |
| | | l->delta_gpu = cuda_make_array(l->delta, output_size); |
| | | #endif |
| | | } |
| | | |
| | |
| | | int h = (l.h-1)/l.stride + 1; |
| | | int w = (l.w-1)/l.stride + 1; |
| | | int c = l.c; |
| | | memset(state.delta, 0, l.batch*l.h*l.w*l.c*sizeof(float)); |
| | | for(i = 0; i < h*w*c*l.batch; ++i){ |
| | | int index = l.indexes[i]; |
| | | state.delta[index] += l.delta[i]; |