jpcookie

Untitled

Oct 17th, 2021
1,044
Never
Not a member of Pastebin yet? Sign Up, it unlocks many cool features!
  1. [TensorRT] ERROR: 3: [executionContext.cpp::setBindingDimensions::969] Error Code 3: Internal Error (Parameter check failed at: runtime/api/executionContext.cpp::setBindingDimensions::969, condition: profileMaxDims.d[i] >= dimensions.d[i]. Supplied binding dimension [1,80,2378] for bindings[0] exceed min ~ max range at index 2, maximum dimension in profile is 1024, minimum dimension in profile is 1, but supplied dimension is 2378.
  2. )
  3. Traceback (most recent call last):
  4.   File "tts2.py", line 90, in <module>
  5.     audio = tts(args.text)
  6.   File "/jetson-voice/jetson_voice/models/tts/tts_engine.py", line 81, in __call__
  7.     audio = self.vocoder.execute(mels)
  8.   File "/jetson-voice/jetson_voice/backends/tensorrt/trt_model.py", line 114, in execute
  9.     setup_binding(self.bindings[idx], input)
  10.   File "/jetson-voice/jetson_voice/backends/tensorrt/trt_model.py", line 109, in setup_binding
  11.     binding.set_shape(input.shape)
  12.   File "/jetson-voice/jetson_voice/backends/tensorrt/trt_binding.py", line 80, in set_shape
  13.     raise ValueError(f"failed to set binding '{self.name}' with shape {shape}")
  14. ValueError: failed to set binding 'mels' with shape (1, 80, 2378)
  15. [TensorRT] INFO: [MemUsageChange] Init cuBLAS/cuBLASLt: CPU +0, GPU +0, now: CPU 2308, GPU 3704 (MiB)
RAW Paste Data