From ae43c2bc32fbb838bfebeeaf2c2b058ccab5c83c Mon Sep 17 00:00:00 2001 From: Joseph Redmon <pjreddie@burninator.cs.washington.edu> Date: Thu, 23 Jun 2016 05:31:14 +0000 Subject: [PATCH] hi --- src/blas.h | 37 +++++++++++++++++++++++++++++++------ 1 files changed, 31 insertions(+), 6 deletions(-) diff --git a/src/blas.h b/src/blas.h index be7da00..b4cfcf2 100644 --- a/src/blas.h +++ b/src/blas.h @@ -7,19 +7,32 @@ void test_blas(); void const_cpu(int N, float ALPHA, float *X, int INCX); +void constrain_ongpu(int N, float ALPHA, float * X, int INCX); void pow_cpu(int N, float ALPHA, float *X, int INCX, float *Y, int INCY); void mul_cpu(int N, float *X, int INCX, float *Y, int INCY); void axpy_cpu(int N, float ALPHA, float *X, int INCX, float *Y, int INCY); void copy_cpu(int N, float *X, int INCX, float *Y, int INCY); void scal_cpu(int N, float ALPHA, float *X, int INCX); +void fill_cpu(int N, float ALPHA, float * X, int INCX); float dot_cpu(int N, float *X, int INCX, float *Y, int INCY); void test_gpu_blas(); +void shortcut_cpu(int batch, int w1, int h1, int c1, float *add, int w2, int h2, int c2, float *out); void mean_cpu(float *x, int batch, int filters, int spatial, float *mean); void variance_cpu(float *x, float *mean, int batch, int filters, int spatial, float *variance); void normalize_cpu(float *x, float *mean, float *variance, int batch, int filters, int spatial); +void scale_bias(float *output, float *scales, int batch, int n, int size); +void backward_scale_cpu(float *x_norm, float *delta, int batch, int n, int size, float *scale_updates); +void mean_delta_cpu(float *delta, float *variance, int batch, int filters, int spatial, float *mean_delta); +void variance_delta_cpu(float *x, float *delta, float *mean, float *variance, int batch, int filters, int spatial, float *variance_delta); +void normalize_delta_cpu(float *x, float *mean, float *variance, float *mean_delta, float *variance_delta, int batch, int filters, int spatial, float *delta); + +void smooth_l1_cpu(int n, float *pred, float *truth, float *delta, float *error); +void l2_cpu(int n, float *pred, float *truth, float *delta, float *error); +void weighted_sum_cpu(float *a, float *b, float *s, int num, float *c); + #ifdef GPU void axpy_ongpu(int N, float ALPHA, float * X, int INCX, float * Y, int INCY); void axpy_ongpu_offset(int N, float ALPHA, float * X, int OFFX, int INCX, float * Y, int OFFY, int INCY); @@ -36,14 +49,26 @@ void variance_gpu(float *x, float *mean, int batch, int filters, int spatial, float *variance); void normalize_gpu(float *x, float *mean, float *variance, int batch, int filters, int spatial); -void mean_delta_gpu(float *delta, float *variance, int batch, int filters, int spatial, float *mean_delta); -void variance_delta_gpu(float *x, float *delta, float *mean, float *variance, int batch, int filters, int spatial, float *variance_delta); void normalize_delta_gpu(float *x, float *mean, float *variance, float *mean_delta, float *variance_delta, int batch, int filters, int spatial, float *delta); -void fast_mean_delta_gpu(float *delta, float *variance, int batch, int filters, int spatial, float *spatial_mean_delta, float *mean_delta); -void fast_variance_delta_gpu(float *x, float *delta, float *mean, float *variance, int batch, int filters, int spatial, float *spatial_variance_delta, float *variance_delta); +void fast_mean_delta_gpu(float *delta, float *variance, int batch, int filters, int spatial, float *mean_delta); +void fast_variance_delta_gpu(float *x, float *delta, float *mean, float *variance, int batch, int filters, int spatial, float *variance_delta); -void fast_variance_gpu(float *x, float *mean, int batch, int filters, int spatial, float *spatial_variance, float *variance); -void fast_mean_gpu(float *x, int batch, int filters, int spatial, float *spatial_mean, float *mean); +void fast_variance_gpu(float *x, float *mean, int batch, int filters, int spatial, float *variance); +void fast_mean_gpu(float *x, int batch, int filters, int spatial, float *mean); +void shortcut_gpu(int batch, int w1, int h1, int c1, float *add, int w2, int h2, int c2, float *out); +void scale_bias_gpu(float *output, float *biases, int batch, int n, int size); +void backward_scale_gpu(float *x_norm, float *delta, int batch, int n, int size, float *scale_updates); +void scale_bias_gpu(float *output, float *biases, int batch, int n, int size); +void add_bias_gpu(float *output, float *biases, int batch, int n, int size); +void backward_bias_gpu(float *bias_updates, float *delta, int batch, int n, int size); + +void smooth_l1_gpu(int n, float *pred, float *truth, float *delta, float *error); +void l2_gpu(int n, float *pred, float *truth, float *delta, float *error); +void weighted_delta_gpu(float *a, float *b, float *s, float *da, float *db, float *ds, int num, float *dc); +void weighted_sum_gpu(float *a, float *b, float *s, int num, float *c); +void mult_add_into_gpu(int num, float *a, float *b, float *c); + + #endif #endif -- Gitblit v1.10.0