Open ndeep27 opened 2 months ago
Getting below error when running a TensorRT converted model. 2024-07-08 17:23:06.193422: E external/org_tensorflow/tensorflow/compiler/tf2tensorrt/utils/trt_logger.cc:87] DefaultLogger 7: [shapeMachine.cpp::executeContinuation::864] Error Code 7: Internal Error (IShuffleLayer (Unnamed Layer* 190) [Shuffle]: reshaping failed for tensor: TensorRTInputPH_38 reshape would change volume 97200 to 98100 Instruction: RESHAPE_ZERO_IS_PLACEHOLDER{3240 1 30} {545 180}.)
My original model is in TF and I used the TFTConverter to convert the model
converter = trt.TrtGraphConverterV2( input_saved_model_dir=SAVED_MODEL_PATH, use_dynamic_shape=True, dynamic_shape_profile_strategy="Range", precision_mode=trt.TrtPrecisionMode.FP32 )
trt_func = converter.convert()
Any pointers on the above error? When running the TF model on its own, i don't see any issues in inference.
similar case https://forums.developer.nvidia.com/t/ishufflelayer-reshape-8-reshaping-failed-for-tensor/277844
lix19937
commented
2 months ago
Description
Getting below error when running a TensorRT converted model. 2024-07-08 17:23:06.193422: E external/org_tensorflow/tensorflow/compiler/tf2tensorrt/utils/trt_logger.cc:87] DefaultLogger 7: [shapeMachine.cpp::executeContinuation::864] Error Code 7: Internal Error (IShuffleLayer (Unnamed Layer* 190) [Shuffle]: reshaping failed for tensor: TensorRTInputPH_38 reshape would change volume 97200 to 98100 Instruction: RESHAPE_ZERO_IS_PLACEHOLDER{3240 1 30} {545 180}.)
My original model is in TF and I used the TFTConverter to convert the model
converter = trt.TrtGraphConverterV2( input_saved_model_dir=SAVED_MODEL_PATH, use_dynamic_shape=True, dynamic_shape_profile_strategy="Range", precision_mode=trt.TrtPrecisionMode.FP32 )
trt_func = converter.convert()
Any pointers on the above error? When running the TF model on its own, i don't see any issues in inference.