Dynamic onnx model can't convert to engine file with flag --maxShape and --minShape

Description

if I convert my onnx model only with --optShape, it can be converted to engine file; but if I convert it with --minShape, --optShapes and --optShape, it failed.

# successful convert 
./trtexec --onnx=model.onnx  --optShapes=image1:1x3x640x960,image2:1x3x640x960  --verbose=true --workspace=6000 --builderOptimizationLevel=0 --saveEngine=model.engine --tacticSources=-CUDNN,+CUBLAS --noTF32 --fp16

# failed convert
./trtexec --onnx=model.onnx --minShapes=image1:1x3x480x640,image2:1x3x480x640 --optShapes=image1:1x3x640x960,image2:1x3x640x960  --maxShapes=image1:1x3x960x1024,image2:1x3x960x1024 --verbose=true --workspace=6000 --builderOptimizationLevel=0 --saveEngine=model.engine --tacticSources=-CUDNN,+CUBLAS --noTF32 --fp16

Environment

TensorRT Version: 8.6.1
GPU Type: RTX 3060
Nvidia Driver Version: 535.183.01
CUDA Version: 11.8
CUDNN Version: 8.5.0
Operating System + Version: Ubuntu 20.04
Python Version (if applicable): 3.9
TensorFlow Version (if applicable):
PyTorch Version (if applicable): 2.0.1
Baremetal or Container (if container which image + tag):

Relevant Files

onnx model: model.onnx - Google Drive
log info:log.txt (10.7 MB)
error info:
[07/02/2024-16:55:36] [W] --workspace flag has been deprecated by --memPoolSize flag.
[07/02/2024-16:55:40] [W] [TRT] onnx2trt_utils.cpp:374: Your ONNX model has been generated with INT64 weights, while TensorRT does not natively support INT64. Attempting to cast down to INT32.
[07/02/2024-16:55:40] [W] [TRT] onnx2trt_utils.cpp:400: One or more weights outside the range of INT32 was clamped
[07/02/2024-17:08:50] [E] Error[10]: Could not find any implementation for node /update_block/encoder/convc1_1/Conv + /update_block/encoder_1/Relu.
[07/02/2024-17:08:50] [E] Error[10]: [optimizer.cpp::computeCosts::3869] Error Code 10: Internal Error (Could not find any implementation for node /update_block/encoder/convc1_1/Conv + /update_block/encoder_1/Relu.)
[07/02/2024-17:08:50] [E] Engine could not be created from network
[07/02/2024-17:08:50] [E] Building engine failed
[07/02/2024-17:08:50] [E] Failed to create engine from model or file.
[07/02/2024-17:08:50] [E] Engine set up failed

Steps To Reproduce

following command to convert model

./trtexec --onnx=model.onnx --minShapes=image1:1x3x480x640,image2:1x3x480x640 --optShapes=image1:1x3x640x960,image2:1x3x640x960  --maxShapes=image1:1x3x960x1024,image2:1x3x960x1024 --verbose=true --workspace=6000 --builderOptimizationLevel=0 --saveEngine=model.engine --tacticSources=-CUDNN,+CUBLAS --noTF32 --fp16

@NVES hello, is there any solution? Thanks~

Hello @oscarcwy92 ,
Trying a repro at our end.

@AakankshaS hello, could you reproduce the same result ? or you need more files or infos? Thanks

@NVES hello,is there any update for this problem? Thanks~