blob: d06306e178429af238c349bcc50b91243a1524a6 (
plain)
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
|
//
// Copyright © 2017 Arm Ltd. All rights reserved.
// SPDX-License-Identifier: MIT
//
#include "ClSoftmaxUint8Workload.hpp"
#include <backends/cl/ClTensorHandle.hpp>
#include <backends/CpuTensorHandle.hpp>
#include "ClWorkloadUtils.hpp"
namespace armnn
{
ClSoftmaxUint8Workload::ClSoftmaxUint8Workload(const SoftmaxQueueDescriptor& descriptor, const WorkloadInfo& info,
std::shared_ptr<arm_compute::MemoryManagerOnDemand>& memoryManager)
: Uint8Workload<SoftmaxQueueDescriptor>(descriptor, info)
, m_SoftmaxLayer(memoryManager)
{
m_Data.ValidateInputsOutputs("ClSoftmaxUint8Workload", 1, 1);
arm_compute::ICLTensor& input = static_cast<ClTensorHandle*>(m_Data.m_Inputs[0])->GetTensor();
arm_compute::ICLTensor& output = static_cast<ClTensorHandle*>(m_Data.m_Outputs[0])->GetTensor();
const auto outputQuantization = output.info()->quantization_info();
if ((outputQuantization.scale != (1.0f / 256.0f)) || (outputQuantization.offset != 0))
{
throw InvalidArgumentException(
"Invalid quantization for output. Only scale = 1.0f / 256.0f and offset = 0 supported");
}
m_SoftmaxLayer.configure(&input, &output, descriptor.m_Parameters.m_Beta);
}
void ClSoftmaxUint8Workload::Execute() const
{
ARMNN_SCOPED_PROFILING_EVENT_CL("ClSoftmaxUint8Workload_Execute");
RunClFunction(m_SoftmaxLayer, CHECK_LOCATION());
}
} //namespace armnn
|
