From 8f1b4e0962857d402f9d017fcbf387ef0eceb7c4 Mon Sep 17 00:00:00 2001 From: Joseph Redmon <pjreddie@gmail.com> Date: Thu, 01 Sep 2016 23:48:41 +0000 Subject: [PATCH] updates and things --- src/blas.h | 32 ++++++++++++++++++++++++++++++-- 1 files changed, 30 insertions(+), 2 deletions(-) diff --git a/src/blas.h b/src/blas.h index 023024a..95374c9 100644 --- a/src/blas.h +++ b/src/blas.h @@ -1,5 +1,6 @@ #ifndef BLAS_H #define BLAS_H +void reorg(float *x, int size, int layers, int batch, int forward); void pm(int M, int N, float *A); float *random_matrix(int rows, int cols); void time_random_matrix(int TA, int TB, int m, int k, int n); @@ -7,26 +8,39 @@ 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(float *out, int w, int h, int c, int batch, int sample, float *add, int stride, int c2); +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); void copy_ongpu(int N, float * X, int INCX, float * Y, int INCY); void copy_ongpu_offset(int N, float * X, int OFFX, int INCX, float * Y, int OFFY, int INCY); void scal_ongpu(int N, float ALPHA, float * X, int INCX); +void supp_ongpu(int N, float ALPHA, float * X, int INCX); void mask_ongpu(int N, float * X, float mask_num, float * mask); void const_ongpu(int N, float ALPHA, float *X, int INCX); void pow_ongpu(int N, float ALPHA, float *X, int INCX, float *Y, int INCY); @@ -44,6 +58,20 @@ 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(float *out, int w, int h, int c, int batch, int sample, float *add, int stride, int c2); +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); + +void reorg_ongpu(float *x, int w, int h, int c, int batch, int stride, int forward, float *out); + #endif #endif -- Gitblit v1.10.0