File size: 1,511 Bytes
be903e2 | 1 2 3 4 5 6 7 8 9 10 11 12 13 14 15 16 17 18 19 20 21 22 23 24 25 26 27 28 29 30 31 32 33 34 35 36 37 38 39 40 41 42 43 44 45 46 47 48 49 50 51 52 53 54 55 56 57 58 | // Tencent is pleased to support the open source community by making ncnn available.
//
// Copyright (C) 2023 THL A29 Limited, a Tencent company. All rights reserved.
//
// Licensed under the BSD 3-Clause License (the "License"); you may not use this file except
// in compliance with the License. You may obtain a copy of the License at
//
// https://opensource.org/licenses/BSD-3-Clause
//
// Unless required by applicable law or agreed to in writing, software distributed
// under the License is distributed on an "AS IS" BASIS, WITHOUT WARRANTIES OR
// CONDITIONS OF ANY KIND, either express or implied. See the License for the
// specific language governing permissions and limitations under the License.
#include "celu.h"
#include <math.h>
namespace ncnn {
CELU::CELU()
{
one_blob_only = true;
support_inplace = true;
}
int CELU::load_param(const ParamDict& pd)
{
alpha = pd.get(0, 1.f);
return 0;
}
int CELU::forward_inplace(Mat& bottom_top_blob, const Option& opt) const
{
int w = bottom_top_blob.w;
int h = bottom_top_blob.h;
int d = bottom_top_blob.d;
int channels = bottom_top_blob.c;
int size = w * h * d;
#pragma omp parallel for num_threads(opt.num_threads)
for (int q = 0; q < channels; q++)
{
float* ptr = bottom_top_blob.channel(q);
for (int i = 0; i < size; i++)
{
if (ptr[i] < 0.f)
ptr[i] = (expf(ptr[i] / alpha) - 1.f) * alpha;
}
}
return 0;
}
} // namespace ncnn
|