API tools faq
paste
Advertisement
Guest User

Untitled

a guest
Oct 12th, 2023
152
0
Never
Add comment
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
Prolog 6.83 KB | None | 0 0
raw download clone embed print report
  1. &&&& RUNNING TensorRT.trtexec [TensorRT v8501] # C:/Program Files (x86)/SVP 4/rife\vsmlrt-cuda\trtexec --onnx=C:/Program Files (x86)/SVP 4/rife\models\rife\rife_v4.6.onnx --timingCacheFile=C:\Users\Loserfailure\AppData\Roaming\SVP4\cache\Program Files (x86)/SVP 4/rife\models\rife\rife_v4.6.onnx.3840x2144_fp16_trt-8502_cudnn_I-fp16_O-fp16_NVIDIA-GeForce-RTX-4090_3dcbe72f.engine.cache --device=0 --saveEngine=C:\Users\Loserfailure\AppData\Roaming\SVP4\cache\Program Files (x86)/SVP 4/rife\models\rife\rife_v4.6.onnx.3840x2144_fp16_trt-8502_cudnn_I-fp16_O-fp16_NVIDIA-GeForce-RTX-4090_3dcbe72f.engine --shapes=input:1x11x2144x3840 --fp16 --tacticSources=-CUBLAS,-CUBLAS_LT --useCudaGraph --noDataTransfers --inputIOFormats=fp16:chw --outputIOFormats=fp16:chw
  2. [10/12/2023-16:01:07] [I] === Model Options ===
  3. [10/12/2023-16:01:07] [I] Format: ONNX
  4. [10/12/2023-16:01:07] [I] Model: C:/Program Files (x86)/SVP 4/rife\models\rife\rife_v4.6.onnx
  5. [10/12/2023-16:01:07] [I] Output:
  6. [10/12/2023-16:01:07] [I] === Build Options ===
  7. [10/12/2023-16:01:07] [I] Max batch: explicit batch
  8. [10/12/2023-16:01:07] [I] Memory Pools: workspace: default, dlaSRAM: default, dlaLocalDRAM: default, dlaGlobalDRAM: default
  9. [10/12/2023-16:01:07] [I] minTiming: 1
  10. [10/12/2023-16:01:07] [I] avgTiming: 8
  11. [10/12/2023-16:01:07] [I] Precision: FP32+FP16
  12. [10/12/2023-16:01:07] [I] LayerPrecisions:
  13. [10/12/2023-16:01:07] [I] Calibration:
  14. [10/12/2023-16:01:07] [I] Refit: Disabled
  15. [10/12/2023-16:01:07] [I] Sparsity: Disabled
  16. [10/12/2023-16:01:07] [I] Safe mode: Disabled
  17. [10/12/2023-16:01:07] [I] DirectIO mode: Disabled
  18. [10/12/2023-16:01:07] [I] Restricted mode: Disabled
  19. [10/12/2023-16:01:07] [I] Build only: Disabled
  20. [10/12/2023-16:01:07] [I] Save engine: C:\Users\Loserfailure\AppData\Roaming\SVP4\cache\Program Files (x86)/SVP 4/rife\models\rife\rife_v4.6.onnx.3840x2144_fp16_trt-8502_cudnn_I-fp16_O-fp16_NVIDIA-GeForce-RTX-4090_3dcbe72f.engine
  21. [10/12/2023-16:01:07] [I] Load engine:
  22. [10/12/2023-16:01:07] [I] Profiling verbosity: 0
  23. [10/12/2023-16:01:07] [I] Tactic sources: cublas [OFF], cublasLt [OFF],
  24. [10/12/2023-16:01:07] [I] timingCacheMode: global
  25. [10/12/2023-16:01:07] [I] timingCacheFile: C:\Users\Loserfailure\AppData\Roaming\SVP4\cache\Program Files (x86)/SVP 4/rife\models\rife\rife_v4.6.onnx.3840x2144_fp16_trt-8502_cudnn_I-fp16_O-fp16_NVIDIA-GeForce-RTX-4090_3dcbe72f.engine.cache
  26. [10/12/2023-16:01:07] [I] Heuristic: Disabled
  27. [10/12/2023-16:01:07] [I] Preview Features: Use default preview flags.
  28. [10/12/2023-16:01:07] [I] Input(s): fp16:chw
  29. [10/12/2023-16:01:07] [I] Output(s): fp16:chw
  30. [10/12/2023-16:01:07] [I] Input build shape: input=1x11x2144x3840+1x11x2144x3840+1x11x2144x3840
  31. [10/12/2023-16:01:07] [I] Input calibration shapes: model
  32. [10/12/2023-16:01:07] [I] === System Options ===
  33. [10/12/2023-16:01:07] [I] Device: 0
  34. [10/12/2023-16:01:07] [I] DLACore:
  35. [10/12/2023-16:01:07] [I] Plugins:
  36. [10/12/2023-16:01:07] [I] === Inference Options ===
  37. [10/12/2023-16:01:07] [I] Batch: Explicit
  38. [10/12/2023-16:01:07] [I] Input inference shape: input=1x11x2144x3840
  39. [10/12/2023-16:01:07] [I] Iterations: 10
  40. [10/12/2023-16:01:07] [I] Duration: 3s (+ 200ms warm up)
  41. [10/12/2023-16:01:07] [I] Sleep time: 0ms
  42. [10/12/2023-16:01:07] [I] Idle time: 0ms
  43. [10/12/2023-16:01:07] [I] Streams: 1
  44. [10/12/2023-16:01:07] [I] ExposeDMA: Disabled
  45. [10/12/2023-16:01:07] [I] Data transfers: Disabled
  46. [10/12/2023-16:01:07] [I] Spin-wait: Disabled
  47. [10/12/2023-16:01:07] [I] Multithreading: Disabled
  48. [10/12/2023-16:01:07] [I] CUDA Graph: Enabled
  49. [10/12/2023-16:01:07] [I] Separate profiling: Disabled
  50. [10/12/2023-16:01:07] [I] Time Deserialize: Disabled
  51. [10/12/2023-16:01:07] [I] Time Refit: Disabled
  52. [10/12/2023-16:01:07] [I] NVTX verbosity: 0
  53. [10/12/2023-16:01:07] [I] Persistent Cache Ratio: 0
  54. [10/12/2023-16:01:07] [I] Inputs:
  55. [10/12/2023-16:01:07] [I] === Reporting Options ===
  56. [10/12/2023-16:01:07] [I] Verbose: Disabled
  57. [10/12/2023-16:01:07] [I] Averages: 10 inferences
  58. [10/12/2023-16:01:07] [I] Percentiles: 90,95,99
  59. [10/12/2023-16:01:07] [I] Dump refittable layers:Disabled
  60. [10/12/2023-16:01:07] [I] Dump output: Disabled
  61. [10/12/2023-16:01:07] [I] Profile: Disabled
  62. [10/12/2023-16:01:07] [I] Export timing to JSON file:
  63. [10/12/2023-16:01:07] [I] Export output to JSON file:
  64. [10/12/2023-16:01:07] [I] Export profile to JSON file:
  65. [10/12/2023-16:01:07] [I]
  66. [10/12/2023-16:01:07] [I] === Device Information ===
  67. [10/12/2023-16:01:07] [I] Selected Device: NVIDIA GeForce RTX 4090
  68. [10/12/2023-16:01:07] [I] Compute Capability: 8.9
  69. [10/12/2023-16:01:07] [I] SMs: 128
  70. [10/12/2023-16:01:07] [I] Compute Clock Rate: 2.55 GHz
  71. [10/12/2023-16:01:07] [I] Device Global Memory: 24563 MiB
  72. [10/12/2023-16:01:07] [I] Shared Memory per SM: 100 KiB
  73. [10/12/2023-16:01:07] [I] Memory Bus Width: 384 bits (ECC disabled)
  74. [10/12/2023-16:01:07] [I] Memory Clock Rate: 10.501 GHz
  75. [10/12/2023-16:01:07] [I]
  76. [10/12/2023-16:01:07] [I] TensorRT version: 8.5.1
  77. [10/12/2023-16:01:08] [I] [TRT] [MemUsageChange] Init CUDA: CPU +475, GPU +0, now: CPU 15323, GPU 1783 (MiB)
  78. [10/12/2023-16:01:09] [I] [TRT] [MemUsageChange] Init builder kernel library: CPU +504, GPU +116, now: CPU 16313, GPU 1899 (MiB)
  79. [10/12/2023-16:01:09] [W] [TRT] CUDA lazy loading is not enabled. Enabling it can significantly reduce device memory usage. See `CUDA_MODULE_LOADING` in [url]https://docs.nvidia.com/cuda/cuda-c-programming-guide/index.html#env-vars[/url]
  80. [10/12/2023-16:01:09] [I] Start parsing network model
  81. [10/12/2023-16:01:09] [I] [TRT] ----------------------------------------------------------------
  82. [10/12/2023-16:01:09] [I] [TRT] Input filename:   C:/Program Files (x86)/SVP 4/rife\models\rife\rife_v4.6.onnx
  83. [10/12/2023-16:01:09] [I] [TRT] ONNX IR version:  0.0.8
  84. [10/12/2023-16:01:09] [I] [TRT] Opset version:    16
  85. [10/12/2023-16:01:09] [I] [TRT] Producer name:    pytorch
  86. [10/12/2023-16:01:09] [I] [TRT] Producer version: 1.12.0
  87. [10/12/2023-16:01:09] [I] [TRT] Domain:          
  88. [10/12/2023-16:01:09] [I] [TRT] Model version:    0
  89. [10/12/2023-16:01:09] [I] [TRT] Doc string:      
  90. [10/12/2023-16:01:09] [I] [TRT] ----------------------------------------------------------------
  91. [10/12/2023-16:01:09] [W] [TRT] onnx2trt_utils.cpp:377: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32.
  92. [10/12/2023-16:01:09] [I] Finish parsing network model
  93. [10/12/2023-16:01:09] [W] Could not read timing cache from: C:\Users\Loserfailure\AppData\Roaming\SVP4\cache\Program Files (x86)/SVP 4/rife\models\rife\rife_v4.6.onnx.3840x2144_fp16_trt-8502_cudnn_I-fp16_O-fp16_NVIDIA-GeForce-RTX-4090_3dcbe72f.engine.cache. A new timing cache will be generated and written.
  94. [10/12/2023-16:01:10] [I] [TRT] [MemUsageChange] Init cuDNN: CPU +1133, GPU +406, now: CPU 17095, GPU 2305 (MiB)
  95. [10/12/2023-16:01:10] [I] [TRT] Global timing cache in use. Profiling results in this builder pass will be stored.
Advertisement
Add Comment
Please, Sign In to add comment
Advertisement
Public Pastes
Advertisement
We use cookies for various purposes including analytics. By continuing to use Pastebin, you agree to our use of cookies as described in the Cookies Policy.  OK, I Understand
Not a member of Pastebin yet?
Sign Up, it unlocks many cool features!