| | |
| | | #include "convolutional_layer.h" |
| | | #include "utils.h" |
| | | #include "batchnorm_layer.h" |
| | | #include "im2col.h" |
| | | #include "col2im.h" |
| | | #include "blas.h" |
| | |
| | | return float_to_image(w,h,c,l.delta); |
| | | } |
| | | |
| | | void backward_scale_cpu(float *x_norm, float *delta, int batch, int n, int size, float *scale_updates) |
| | | { |
| | | int i,b,f; |
| | | for(f = 0; f < n; ++f){ |
| | | float sum = 0; |
| | | for(b = 0; b < batch; ++b){ |
| | | for(i = 0; i < size; ++i){ |
| | | int index = i + size*(f + n*b); |
| | | sum += delta[index] * x_norm[index]; |
| | | } |
| | | } |
| | | scale_updates[f] += sum; |
| | | } |
| | | } |
| | | |
| | | void mean_delta_cpu(float *delta, float *variance, int batch, int filters, int spatial, float *mean_delta) |
| | | { |
| | | |
| | | int i,j,k; |
| | | for(i = 0; i < filters; ++i){ |
| | | mean_delta[i] = 0; |
| | | for (j = 0; j < batch; ++j) { |
| | | for (k = 0; k < spatial; ++k) { |
| | | int index = j*filters*spatial + i*spatial + k; |
| | | mean_delta[i] += delta[index]; |
| | | } |
| | | } |
| | | mean_delta[i] *= (-1./sqrt(variance[i] + .00001f)); |
| | | } |
| | | } |
| | | void variance_delta_cpu(float *x, float *delta, float *mean, float *variance, int batch, int filters, int spatial, float *variance_delta) |
| | | { |
| | | |
| | | int i,j,k; |
| | | for(i = 0; i < filters; ++i){ |
| | | variance_delta[i] = 0; |
| | | for(j = 0; j < batch; ++j){ |
| | | for(k = 0; k < spatial; ++k){ |
| | | int index = j*filters*spatial + i*spatial + k; |
| | | variance_delta[i] += delta[index]*(x[index] - mean[i]); |
| | | } |
| | | } |
| | | variance_delta[i] *= -.5 * pow(variance[i] + .00001f, (float)(-3./2.)); |
| | | } |
| | | } |
| | | void normalize_delta_cpu(float *x, float *mean, float *variance, float *mean_delta, float *variance_delta, int batch, int filters, int spatial, float *delta) |
| | | { |
| | | int f, j, k; |
| | | for(j = 0; j < batch; ++j){ |
| | | for(f = 0; f < filters; ++f){ |
| | | for(k = 0; k < spatial; ++k){ |
| | | int index = j*filters*spatial + f*spatial + k; |
| | | delta[index] = delta[index] * 1./(sqrt(variance[f]) + .00001f) + variance_delta[f] * 2. * (x[index] - mean[f]) / (spatial * batch) + mean_delta[f]/(spatial*batch); |
| | | } |
| | | } |
| | | } |
| | | } |
| | | |
| | | convolutional_layer make_convolutional_layer(int batch, int h, int w, int c, int n, int size, int stride, int pad, ACTIVATION activation, int batch_normalize, int binary) |
| | | convolutional_layer make_convolutional_layer(int batch, int h, int w, int c, int n, int size, int stride, int pad, ACTIVATION activation, int batch_normalize, int binary, int xnor) |
| | | { |
| | | int i; |
| | | convolutional_layer l = {0}; |
| | |
| | | if(binary){ |
| | | l.binary_filters_gpu = cuda_make_array(l.filters, c*n*size*size); |
| | | } |
| | | if(xnor){ |
| | | l.binary_filters_gpu = cuda_make_array(l.filters, c*n*size*size); |
| | | l.binary_input_gpu = cuda_make_array(0, l.inputs*l.batch); |
| | | } |
| | | l.xnor = xnor; |
| | | |
| | | if(batch_normalize){ |
| | | l.mean_gpu = cuda_make_array(l.mean, n); |
| | |
| | | |
| | | void test_convolutional_layer() |
| | | { |
| | | convolutional_layer l = make_convolutional_layer(1, 5, 5, 3, 2, 5, 2, 1, LEAKY, 1, 0); |
| | | convolutional_layer l = make_convolutional_layer(1, 5, 5, 3, 2, 5, 2, 1, LEAKY, 1, 0, 0); |
| | | l.batch_normalize = 1; |
| | | float data[] = {1,1,1,1,1, |
| | | 1,1,1,1,1, |
| | |
| | | } |
| | | |
| | | if(l.batch_normalize){ |
| | | if(state.train){ |
| | | mean_cpu(l.output, l.batch, l.n, l.out_h*l.out_w, l.mean); |
| | | variance_cpu(l.output, l.mean, l.batch, l.n, l.out_h*l.out_w, l.variance); |
| | | normalize_cpu(l.output, l.mean, l.variance, l.batch, l.n, l.out_h*l.out_w); |
| | | } else { |
| | | normalize_cpu(l.output, l.rolling_mean, l.rolling_variance, l.batch, l.n, l.out_h*l.out_w); |
| | | } |
| | | scale_bias(l.output, l.scales, l.batch, l.n, out_h*out_w); |
| | | forward_batchnorm_layer(l, state); |
| | | } |
| | | add_bias(l.output, l.biases, l.batch, l.n, out_h*out_w); |
| | | |