|
|
发表于 2026-6-9 11:09:43
|
显示全部楼层
本帖最后由 1970134465 于 2026-6-9 11:10 编辑
大佬，帮看一下，我的都无法用GPU跑
执行命令：
"python\python.exe" -m lada.cli.main --input "D:\Favorites\**\**.mp4" --output "D:\116" --temporary-directory "D:\116" --output-file-pattern "{orig_file_name}-U.mp4" --mosaic-detection-model "v4-fast" --encoding-preset "hevc-nvidia-gpu-uhq" --max-clip-length 180 --no-detect-face-mosaics --fp16 --tensorrt --torchcodec-encoder --no-fast-pipeline --device cuda:0
[06/09/2026-10:40:13] [TRT] [W] Functionality provided through tensorrt.plugin module is experimental.
W0609 10:40:14.155000 4184 Lib\site-packages\torch\distributed\elastic\multiprocessing\redirects.py:29] NOTE: Redirects are currently not supported in Windows or MacOs.
Processing video: 0%| |Processed: 00:00 (0f) | Remaining: ? | Speed: ? [TensorRT] Pre-building engines to avoid runtime conflicts...
WARNING: [Torch-TensorRT] - WARNING The logger passed into createInferRuntime differs from one already registered for an existing builder, runtime, or refitter. So the current new logger is ignored, and TensorRT will use the existing one which is returned by nvinfer1::getLogger() instead.
WARNING: [Torch-TensorRT] - WARNING The logger passed into createInferRuntime differs from one already registered for an existing builder, runtime, or refitter. So the current new logger is ignored, and TensorRT will use the existing one which is returned by nvinfer1::getLogger() instead.
WARNING: [Torch-TensorRT] - WARNING The logger passed into createInferRuntime differs from one already registered for an existing builder, runtime, or refitter. So the current new logger is ignored, and TensorRT will use the existing one which is returned by nvinfer1::getLogger() instead.
WARNING: [Torch-TensorRT] - WARNING The logger passed into createInferRuntime differs from one already registered for an existing builder, runtime, or refitter. So the current new logger is ignored, and TensorRT will use the existing one which is returned by nvinfer1::getLogger() instead.
WARNING: [Torch-TensorRT] - WARNING The logger passed into createInferRuntime differs from one already registered for an existing builder, runtime, or refitter. So the current new logger is ignored, and TensorRT will use the existing one which is returned by nvinfer1::getLogger() instead.
WARNING: [Torch-TensorRT] - WARNING The logger passed into createInferRuntime differs from one already registered for an existing builder, runtime, or refitter. So the current new logger is ignored, and TensorRT will use the existing one which is returned by nvinfer1::getLogger() instead.
WARNING: [Torch-TensorRT] - WARNING The logger passed into createInferRuntime differs from one already registered for an existing builder, runtime, or refitter. So the current new logger is ignored, and TensorRT will use the existing one which is returned by nvinfer1::getLogger() instead.
WARNING: [Torch-TensorRT] - WARNING The logger passed into createInferRuntime differs from one already registered for an existing builder, runtime, or refitter. So the current new logger is ignored, and TensorRT will use the existing one which is returned by nvinfer1::getLogger() instead.
WARNING: [Torch-TensorRT] - WARNING The logger passed into createInferRuntime differs from one already registered for an existing builder, runtime, or refitter. So the current new logger is ignored, and TensorRT will use the existing one which is returned by nvinfer1::getLogger() instead.
WARNING: [Torch-TensorRT] - WARNING The logger passed into createInferRuntime differs from one already registered for an existing builder, runtime, or refitter. So the current new logger is ignored, and TensorRT will use the existing one which is returned by nvinfer1::getLogger() instead.
Processing video: 7%|████████▎ |Proce |
|
