|
|
发表于 2026-5-17 20:01:33
|
显示全部楼层
重新下了补丁2又重新跑了一下：
[offline] GPU runtime initialization may take a while on first use. If this is the first offline run after installation or a driver/model update, the window can stay quiet for 1-3 minutes while CUDA/ONNX Runtime caches are built.
[offline] run: E:\VR_Video_Passthrough_Server\pt_core.exe tool offline_alpha_passthrough E:\VR_Video_Passthrough_Server\videos\1.mp4 --engine rvm --out E:\VR_Video_Passthrough_Server\videos\1_rvm2_S000000_ALL_FISHEYE180_alpha.mp4 --audio copy --model E:\VR_Video_Passthrough_Server\models\rvm_resnet50_fp32.onnx --alpha-stride 1 --input-size 1024 --sbs-batch --bitrate live --preset P7 --cq -1
[offline] gpu warmup: state=cache-hit reason=cache_hit eta=1s gpu=NVIDIA GeForce RTX 4070 Laptop GPU cc=8.9 ort=1.25.1
[offline] env: decoder=simple batch=1 buffer=2 preset=P7 model=
[offline-alpha] input codec=mpeg4 profile=Simple Profile pix_fmt=yuv420p bit_depth=8 size=4096x2048
[offline-alpha] cuda gpu_id=0 name=NVIDIA GeForce RTX 4070 Laptop GPU cc=8.9 vram=8.0GB free=6.9GB driver=13020 runtime=12090
[offline-alpha] decoder=simple batch=1 buffer=2 owned_copy=False
[matting] CuPy 14.0.1 detected, GPU composite enabled.
[matting] options: input_size=1024 square=False split_sbs=True sbs_batch=True alpha_stride=1 alpha_mode=reuse alpha_cutoff=0.0 alpha_hard_edge=False alpha_contrast=1.0
2026-05-17 20:00:15.2258264 [W nnxruntime:, transformer_memcpy.cc:111 onnxruntime::MemcpyTransformer::ApplyImpl] 1 Memcpy nodes are added to the graph torch-jit-export for CUDAExecutionProvider. It might have negative impact on performance (including unable to run CUDA graph). Set session_options.log_severity_level=1 to see the detail logs before this message.
[matting] model kind=rvm input=src shape=['batch_size', 3, 'height', 'width'] type=tensor(float) batch2=True model_batch2=True rvm_iobinding=True providers=['CUDAExecutionProvider', 'CPUExecutionProvider'] inputs=['src', 'r1i', 'r2i', 'r3i', 'r4i', 'downsample_ratio'] outputs=['fgr', 'pha', 'r1o', 'r2o', 'r3o', 'r4o']
[offline-alpha] src=E:\VR_Video_Passthrough_Server\videos\1.mp4 out=E:\VR_Video_Passthrough_Server\videos\1_rvm2_S000000_ALL_FISHEYE180_alpha.mp4 engine=rvm 4096x2048 source_fps=59.938000 output_fps=59.938000 target=20289 audio=copy bitrate=50000000 maxbitrate=60000000 vbvbufsize=100000000 rc=vbr cq=-1 preset=P7
[offline-alpha] projection=sbs half-equirect 180 -> fisheye sbs radius_scale=1
[offline-alpha] packing=DeoVR-style red-channel alpha blocks scale=0.4 layout=alpha-packer-6block
[offline] mux=.\ffmpeg.EXE -hide_banner -loglevel warning -y -fflags +genpts -f hevc -framerate 59.938000 -i - -map 0:v:0 -c:v copy -an -movflags +faststart -f mp4 E:\VR_Video_Passthrough_Server\videos\1_rvm2_S000000_ALL_FISHEYE180_alpha._video_only.mp4
Traceback (most recent call last):
File "main.py", line 359, in <module>
File "main.py", line 148, in main
File "main.py", line 83, in _run_legacy_tool
File "tools\offline_alpha_passthrough.py", line 1775, in main
File "pipeline\pynv_io.py", line 292, in frame_at
File " yNvVideoCodec\decoders\SimpleDecoder.py", line 86, in __getitem__
_PyNvVideoCodec.PyNvVCExceptionUnsupported: NvDecoder::HandleVideoSequence :
Error code : 801
Error Type : MBCount not supported on this GPU
MBCount : 32768
Max Supported mbcnt : 8192
at G:\build\sw\devrel\PyNvVideoCodec\rel_2_1\src\VideoCodecSDKUtils\helper_classes\NvCodec\NvDecoder\NvDecoder.cpp:275
[PYI-34856:ERROR] Failed to execute script 'main' due to unhandled exception!
|
|
楼主: zelefans
