video-streaming - 输入少量输入样本后,英特尔图形硬件 H264 MFT ProcessInput 调用失败,同样适用于 Nvidia 硬件 MFT
问题描述
我正在使用 DesktopDuplication API 捕获桌面并将样本从 RGBA 转换为 GPU 中的 NV12,并将其提供给 MediaFoundation 硬件 H264 MFT。这适用于 Nvidia 图形,也适用于软件编码器,但当只有英特尔图形硬件 MFT 可用时失败。如果我回退到软件 MFT,该代码在同一台英特尔图形机上运行良好。我还确保编码实际上是在 Nvidia 图形机器上的硬件中完成的。
在 Intel 显卡上,MFT 返回 MEError ( "Unspecified error" ),这仅在输入第一个样本后发生,随后对 ProcessInput 的调用(当事件生成器触发 METransformNeedInput 时)返回"The callee is current not accepting further input"。MFT 在返回这些错误之前很少消耗更多样本。这种行为令人困惑,我仅在事件生成器通过 IMFAsyncCallback 异步触发 METransformNeedInput 时才提供样本,并且还正确检查是否在提供样本后立即触发 METransformHaveOutput。当相同的异步逻辑与 Nvidia 硬件 MFT 和 Microsoft 软件编码器一起正常工作时,这真的让我感到困惑。
英特尔论坛本身也有一个类似的未解决问题。我的代码类似于 intel 线程中提到的代码,除了我还将 d3d 设备管理器设置为编码器,如下所示。
而且,还有其他三个堆栈溢出线程报告了类似的问题,但没有给出解决方案(MFTransform 编码器->ProcessInput 返回 E_FAIL以及 如何从 D11 纹理为英特尔 MFT 编码器创建 IMFSample和异步 MFT 未发送 MFTransformHaveOutput 事件(英特尔硬件 MJPEG 解码器MFT))。我已经尝试了所有可能的选项,但没有任何改进。
颜色转换器代码取自 intel media sdk 示例。我也在这里上传了我的完整代码。
设置d3d管理器的方法:
void SetD3dManager() {
HRESULT hr = S_OK;
if (!deviceManager) {
// Create device manager
hr = MFCreateDXGIDeviceManager(&resetToken, &deviceManager);
}
if (SUCCEEDED(hr))
{
if (!pD3dDevice) {
pD3dDevice = GetDeviceDirect3D(0);
}
}
if (pD3dDevice) {
// NOTE: Getting ready for multi-threaded operation
const CComQIPtr<ID3D10Multithread> pMultithread = pD3dDevice;
pMultithread->SetMultithreadProtected(TRUE);
hr = deviceManager->ResetDevice(pD3dDevice, resetToken);
CHECK_HR(_pTransform->ProcessMessage(MFT_MESSAGE_SET_D3D_MANAGER, reinterpret_cast<ULONG_PTR>(deviceManager.p)), "Failed to set device manager.");
}
else {
cout << "Failed to get d3d device";
}
}
Getd3d设备:
CComPtr<ID3D11Device> GetDeviceDirect3D(UINT idxVideoAdapter)
{
// Create DXGI factory:
CComPtr<IDXGIFactory1> dxgiFactory;
DXGI_ADAPTER_DESC1 dxgiAdapterDesc;
// Direct3D feature level codes and names:
struct KeyValPair { int code; const char* name; };
const KeyValPair d3dFLevelNames[] =
{
KeyValPair{ D3D_FEATURE_LEVEL_9_1, "Direct3D 9.1" },
KeyValPair{ D3D_FEATURE_LEVEL_9_2, "Direct3D 9.2" },
KeyValPair{ D3D_FEATURE_LEVEL_9_3, "Direct3D 9.3" },
KeyValPair{ D3D_FEATURE_LEVEL_10_0, "Direct3D 10.0" },
KeyValPair{ D3D_FEATURE_LEVEL_10_1, "Direct3D 10.1" },
KeyValPair{ D3D_FEATURE_LEVEL_11_0, "Direct3D 11.0" },
KeyValPair{ D3D_FEATURE_LEVEL_11_1, "Direct3D 11.1" },
};
// Feature levels for Direct3D support
const D3D_FEATURE_LEVEL d3dFeatureLevels[] =
{
D3D_FEATURE_LEVEL_11_1,
D3D_FEATURE_LEVEL_11_0,
D3D_FEATURE_LEVEL_10_1,
D3D_FEATURE_LEVEL_10_0,
D3D_FEATURE_LEVEL_9_3,
D3D_FEATURE_LEVEL_9_2,
D3D_FEATURE_LEVEL_9_1,
};
constexpr auto nFeatLevels = static_cast<UINT> ((sizeof d3dFeatureLevels) / sizeof(D3D_FEATURE_LEVEL));
CComPtr<IDXGIAdapter1> dxgiAdapter;
D3D_FEATURE_LEVEL featLevelCodeSuccess;
CComPtr<ID3D11Device> d3dDx11Device;
std::wstring_convert<std::codecvt_utf8<wchar_t>> transcoder;
HRESULT hr = CreateDXGIFactory1(IID_PPV_ARGS(&dxgiFactory));
CHECK_HR(hr, "Failed to create DXGI factory");
// Get a video adapter:
dxgiFactory->EnumAdapters1(idxVideoAdapter, &dxgiAdapter);
// Get video adapter description:
dxgiAdapter->GetDesc1(&dxgiAdapterDesc);
CHECK_HR(hr, "Failed to retrieve DXGI video adapter description");
std::cout << "Selected DXGI video adapter is \'"
<< transcoder.to_bytes(dxgiAdapterDesc.Description) << '\'' << std::endl;
// Create Direct3D device:
hr = D3D11CreateDevice(
dxgiAdapter,
D3D_DRIVER_TYPE_UNKNOWN,
nullptr,
(0 * D3D11_CREATE_DEVICE_SINGLETHREADED) | D3D11_CREATE_DEVICE_VIDEO_SUPPORT,
d3dFeatureLevels,
nFeatLevels,
D3D11_SDK_VERSION,
&d3dDx11Device,
&featLevelCodeSuccess,
nullptr
);
// Might have failed for lack of Direct3D 11.1 runtime:
if (hr == E_INVALIDARG)
{
// Try again without Direct3D 11.1:
hr = D3D11CreateDevice(
dxgiAdapter,
D3D_DRIVER_TYPE_UNKNOWN,
nullptr,
(0 * D3D11_CREATE_DEVICE_SINGLETHREADED) | D3D11_CREATE_DEVICE_VIDEO_SUPPORT,
d3dFeatureLevels + 1,
nFeatLevels - 1,
D3D11_SDK_VERSION,
&d3dDx11Device,
&featLevelCodeSuccess,
nullptr
);
}
// Get name of Direct3D feature level that succeeded upon device creation:
std::cout << "Hardware device supports " << std::find_if(
d3dFLevelNames,
d3dFLevelNames + nFeatLevels,
[featLevelCodeSuccess](const KeyValPair& entry)
{
return entry.code == featLevelCodeSuccess;
}
)->name << std::endl;
done:
return d3dDx11Device;
}
异步回调实现:
struct EncoderCallbacks : IMFAsyncCallback
{
EncoderCallbacks(IMFTransform* encoder)
{
TickEvent = CreateEvent(0, FALSE, FALSE, 0);
_pEncoder = encoder;
}
~EncoderCallbacks()
{
eventGen = nullptr;
CloseHandle(TickEvent);
}
bool Initialize() {
_pEncoder->QueryInterface(IID_PPV_ARGS(&eventGen));
if (eventGen) {
eventGen->BeginGetEvent(this, 0);
return true;
}
return false;
}
// dummy IUnknown impl
virtual HRESULT STDMETHODCALLTYPE QueryInterface(REFIID riid, void** ppvObject) override { return E_NOTIMPL; }
virtual ULONG STDMETHODCALLTYPE AddRef(void) override { return 1; }
virtual ULONG STDMETHODCALLTYPE Release(void) override { return 1; }
virtual HRESULT STDMETHODCALLTYPE GetParameters(DWORD* pdwFlags, DWORD* pdwQueue) override
{
// we return immediately and don't do anything except signaling another thread
*pdwFlags = MFASYNC_SIGNAL_CALLBACK;
*pdwQueue = MFASYNC_CALLBACK_QUEUE_IO;
return S_OK;
}
virtual HRESULT STDMETHODCALLTYPE Invoke(IMFAsyncResult* pAsyncResult) override
{
IMFMediaEvent* event = 0;
eventGen->EndGetEvent(pAsyncResult, &event);
if (event)
{
MediaEventType type;
event->GetType(&type);
switch (type)
{
case METransformNeedInput: InterlockedIncrement(&NeedsInput); break;
case METransformHaveOutput: InterlockedIncrement(&HasOutput); break;
}
event->Release();
SetEvent(TickEvent);
}
eventGen->BeginGetEvent(this, 0);
return S_OK;
}
CComQIPtr<IMFMediaEventGenerator> eventGen = nullptr;
HANDLE TickEvent;
IMFTransform* _pEncoder = nullptr;
unsigned int NeedsInput = 0;
unsigned int HasOutput = 0;
};
生成样本方法:
bool GenerateSampleAsync() {
DWORD processOutputStatus = 0;
HRESULT mftProcessOutput = S_OK;
bool frameSent = false;
// Create sample
CComPtr<IMFSample> currentVideoSample = nullptr;
MFT_OUTPUT_STREAM_INFO StreamInfo;
// wait for any callback to come in
WaitForSingleObject(_pEventCallback->TickEvent, INFINITE);
while (_pEventCallback->NeedsInput) {
if (!currentVideoSample) {
(pDesktopDuplication)->releaseBuffer();
(pDesktopDuplication)->cleanUpCurrentFrameObjects();
bool bTimeout = false;
if (pDesktopDuplication->GetCurrentFrameAsVideoSample((void**)& currentVideoSample, waitTime, bTimeout, deviceRect, deviceRect.Width(), deviceRect.Height())) {
prevVideoSample = currentVideoSample;
}
// Feed the previous sample to the encoder in case of no update in display
else {
currentVideoSample = prevVideoSample;
}
}
if (currentVideoSample)
{
InterlockedDecrement(&_pEventCallback->NeedsInput);
_frameCount++;
CHECK_HR(currentVideoSample->SetSampleTime(mTimeStamp), "Error setting the video sample time.");
CHECK_HR(currentVideoSample->SetSampleDuration(VIDEO_FRAME_DURATION), "Error getting video sample duration.");
CHECK_HR(_pTransform->ProcessInput(inputStreamID, currentVideoSample, 0), "The resampler H264 ProcessInput call failed.");
mTimeStamp += VIDEO_FRAME_DURATION;
}
}
while (_pEventCallback->HasOutput) {
CComPtr<IMFSample> mftOutSample = nullptr;
CComPtr<IMFMediaBuffer> pOutMediaBuffer = nullptr;
InterlockedDecrement(&_pEventCallback->HasOutput);
CHECK_HR(_pTransform->GetOutputStreamInfo(outputStreamID, &StreamInfo), "Failed to get output stream info from H264 MFT.");
CHECK_HR(MFCreateSample(&mftOutSample), "Failed to create MF sample.");
CHECK_HR(MFCreateMemoryBuffer(StreamInfo.cbSize, &pOutMediaBuffer), "Failed to create memory buffer.");
CHECK_HR(mftOutSample->AddBuffer(pOutMediaBuffer), "Failed to add sample to buffer.");
MFT_OUTPUT_DATA_BUFFER _outputDataBuffer;
memset(&_outputDataBuffer, 0, sizeof _outputDataBuffer);
_outputDataBuffer.dwStreamID = outputStreamID;
_outputDataBuffer.dwStatus = 0;
_outputDataBuffer.pEvents = nullptr;
_outputDataBuffer.pSample = mftOutSample;
mftProcessOutput = _pTransform->ProcessOutput(0, 1, &_outputDataBuffer, &processOutputStatus);
if (mftProcessOutput != MF_E_TRANSFORM_NEED_MORE_INPUT)
{
if (_outputDataBuffer.pSample) {
CComPtr<IMFMediaBuffer> buf = NULL;
DWORD bufLength;
CHECK_HR(_outputDataBuffer.pSample->ConvertToContiguousBuffer(&buf), "ConvertToContiguousBuffer failed.");
if (buf) {
CHECK_HR(buf->GetCurrentLength(&bufLength), "Get buffer length failed.");
BYTE* rawBuffer = NULL;
fFrameSize = bufLength;
fDurationInMicroseconds = 0;
gettimeofday(&fPresentationTime, NULL);
buf->Lock(&rawBuffer, NULL, NULL);
memmove(fTo, rawBuffer, fFrameSize > fMaxSize ? fMaxSize : fFrameSize);
bytesTransfered += bufLength;
FramedSource::afterGetting(this);
buf->Unlock();
frameSent = true;
}
}
if (_outputDataBuffer.pEvents)
_outputDataBuffer.pEvents->Release();
}
else if (MF_E_TRANSFORM_STREAM_CHANGE == mftProcessOutput) {
// some encoders want to renegotiate the output format.
if (_outputDataBuffer.dwStatus & MFT_OUTPUT_DATA_BUFFER_FORMAT_CHANGE)
{
CComPtr<IMFMediaType> pNewOutputMediaType = nullptr;
HRESULT res = _pTransform->GetOutputAvailableType(outputStreamID, 1, &pNewOutputMediaType);
res = _pTransform->SetOutputType(0, pNewOutputMediaType, 0);//setting the type again
CHECK_HR(res, "Failed to set output type during stream change");
}
}
else {
HandleFailure();
}
}
return frameSent;
}
创建视频样本和颜色转换:
bool GetCurrentFrameAsVideoSample(void **videoSample, int waitTime, bool &isTimeout, CRect &deviceRect, int surfaceWidth, int surfaceHeight)
{
FRAME_DATA currentFrameData;
m_LastErrorCode = m_DuplicationManager.GetFrame(¤tFrameData, waitTime, &isTimeout);
if (!isTimeout && SUCCEEDED(m_LastErrorCode)) {
m_CurrentFrameTexture = currentFrameData.Frame;
if (!pDstTexture) {
D3D11_TEXTURE2D_DESC desc;
ZeroMemory(&desc, sizeof(D3D11_TEXTURE2D_DESC));
desc.Format = DXGI_FORMAT_NV12;
desc.Width = surfaceWidth;
desc.Height = surfaceHeight;
desc.MipLevels = 1;
desc.ArraySize = 1;
desc.SampleDesc.Count = 1;
desc.CPUAccessFlags = 0;
desc.Usage = D3D11_USAGE_DEFAULT;
desc.BindFlags = D3D11_BIND_RENDER_TARGET;
m_LastErrorCode = m_Id3d11Device->CreateTexture2D(&desc, NULL, &pDstTexture);
}
if (m_CurrentFrameTexture && pDstTexture) {
// Copy diff area texels to new temp texture
//m_Id3d11DeviceContext->CopySubresourceRegion(pNewTexture, D3D11CalcSubresource(0, 0, 1), 0, 0, 0, m_CurrentFrameTexture, 0, NULL);
HRESULT hr = pColorConv->Convert(m_CurrentFrameTexture, pDstTexture);
if (SUCCEEDED(hr)) {
CComPtr<IMFMediaBuffer> pMediaBuffer = nullptr;
MFCreateDXGISurfaceBuffer(__uuidof(ID3D11Texture2D), pDstTexture, 0, FALSE, (IMFMediaBuffer**)&pMediaBuffer);
if (pMediaBuffer) {
CComPtr<IMF2DBuffer> p2DBuffer = NULL;
DWORD length = 0;
(((IMFMediaBuffer*)pMediaBuffer))->QueryInterface(__uuidof(IMF2DBuffer), reinterpret_cast<void**>(&p2DBuffer));
p2DBuffer->GetContiguousLength(&length);
(((IMFMediaBuffer*)pMediaBuffer))->SetCurrentLength(length);
//MFCreateVideoSampleFromSurface(NULL, (IMFSample**)videoSample);
MFCreateSample((IMFSample * *)videoSample);
if (videoSample) {
(*((IMFSample **)videoSample))->AddBuffer((((IMFMediaBuffer*)pMediaBuffer)));
}
return true;
}
}
}
}
return false;
}
机器中的英特尔显卡驱动程序已经是最新的。
只有 TransformNeedInput 事件一直被触发,但编码器抱怨它不能接受更多的输入。TransformHaveOutput 事件从未被触发。
英特尔和 msdn 论坛上报告的类似问题:1) https://software.intel.com/en-us/forums/intel-media-sdk/topic/607189 2) https://social.msdn.microsoft.com/论坛/安全/en-US/fe051dd5-b522-4e4b-9cbb-2c06a5450e40/imfsinkwriter-merit-validation-failed-for-mft-intel-quick-sync-video-h264-encoder-mft?forum=mediafoundationdevelopment
更新: 我试图只模拟输入源(通过以编程方式创建动画矩形 NV12 示例),而其他所有内容都保持不变。这一次,英特尔编码器没有任何抱怨,我什至得到了输出样本。除了英特尔编码器的输出视频失真,而 Nvidia 编码器工作得非常好。
此外,我仍然收到带有英特尔编码器的原始 NV12 源的 ProcessInput 错误。我对 Nvidia MFT 和软件编码器没有任何问题。
解决方案
我看了你的代码。
根据您的帖子,我怀疑是英特尔视频处理器问题。
我的操作系统是 Win7,所以我决定在我的 Nvidia 卡上使用 D3D9Device 测试视频处理器的行为,然后在 Intel HD Graphics 4000 上测试。
我想视频处理器功能对于 D3D9Device 的行为方式与对于 D3D11Device 的行为方式相同。当然,这将是必要的检查。
所以我做了这个程序来检查:https ://github.com/mofo7777/DirectXVideoScreen (见 D3D9VideoProcessor 子项目)
看来您没有检查有关视频处理器功能的足够内容。
使用 IDXVAHD_Device::GetVideoProcessorDeviceCaps,这是我检查的内容:
DXVAHD_VPDEVCAPS.MaxInputStreams > 0
DXVAHD_VPDEVCAPS.VideoProcessorCount > 0
DXVAHD_VPDEVCAPS.OutputFormatCount > 0
DXVAHD_VPDEVCAPS.InputFormatCount > 0
DXVAHD_VPDEVCAPS.InputPool == D3DPOOL_DEFAULT
我还检查了 IDXVAHD_Device::GetVideoProcessorOutputFormats 和 IDXVAHD_Device::GetVideoProcessorInputFormats 支持的输入和输出格式。
这就是我发现 Nvidia GPU 和 Intel GPU 之间存在差异的地方。
NVIDIA : 4 输出格式
- D3DFMT_A8R8G8B8
- D3DFMT_X8R8G8B8
- D3DFMT_YUY2
- D3DFMT_NV12
INTEL : 3 输出格式
- D3DFMT_A8R8G8B8
- D3DFMT_X8R8G8B8
- D3DFMT_YUY2
在 Intel HD Graphics 4000 上,不支持 NV12 输出格式。
此外,为了让程序正常工作,我需要在使用 VideoProcessBltHD 之前设置流状态:
- DXVAHD_STREAM_STATE_D3DFORMAT
- DXVAHD_STREAM_STATE_FRAME_FORMAT
- DXVAHD_STREAM_STATE_INPUT_COLOR_SPACE
- DXVAHD_STREAM_STATE_SOURCE_RECT
- DXVAHD_STREAM_STATE_DESTINATION_RECT
对于 D3D11:
ID3D11VideoProcessorEnumerator::GetVideoProcessorCaps == IDXVAHD_Device::GetVideoProcessorDeviceCaps
(D3D11_VIDEO_PROCESSOR_FORMAT_SUPPORT_OUTPUT) ID3D11VideoProcessorEnumerator::CheckVideoProcessorFormat == IDXVAHD_Device::GetVideoProcessorOutputFormats
(D3D11_VIDEO_PROCESSOR_FORMAT_SUPPORT_INPUT) ID3D11VideoProcessorEnumerator::CheckVideoProcessorFormat == IDXVAHD_Device::GetVideoProcessorInputFormats
ID3D11VideoContext::(...) == IDXVAHD_VideoProcessor::SetVideoProcessStreamState
您能否首先验证您的 GPU 的视频处理器功能。你看到和我看到的一样的区别吗?
这是我们需要知道的第一件事,从我在您的 github 项目中看到的内容来看,您的程序似乎没有检查这一点。
推荐阅读
- windows-10 - 你如何为 MS Teams 制定 Windows Defender 防火墙规则?
- javascript - 过滤函数在reactjs中返回空数组
- sql-server - 死锁 - 从死锁报告中查找完整的 SQL 语句
- laravel - Laravel 获取模型可用座位
- node.js - 用 Jest 模拟模块无法正常工作
- c# - C# - Revit - 零件的长度和方向
- c# - 使用对象自己的值对数组中的对象执行更新
- awk - 使用 awk 打印不带双引号
- ios - 使用 Frida 枚举 ivars (iOS)
- html - 角度 12 通用,html 验证失败,routerLink 属性错误