Last active
May 11, 2020 19:11
-
-
Save rmccorm4/8a2111306f6f7caad215ab3012d6de93 to your computer and use it in GitHub Desktop.
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
# Export sample Alexnet model to ONNX with a dynamic batch dimension | |
wget https://gist.githubusercontent.com/rmccorm4/b72abac18aed6be4c1725db18eba4930/raw/3919c883b97a231877b454dae695fe074a1acdff/alexnet_onnx.py | |
python3 alexnet_onnx.py | |
# Emulate "maxBatchSize" behavior from implicit batch engines by setting | |
# an optimization profile with min=(1, *shape), opt=max=(maxBatchSize, *shape) | |
MAX_BATCH_SIZE=32 | |
INPUT_NAME="actual_input_1" | |
# Convert dynamic batch ONNX model to TRT Engine with optimization profile defined | |
trtexec --explicitBatch --onnx=alexnet_dynamic.onnx \ | |
--minShapes=${INPUT_NAME}:1x3x224x224 \ # kMIN shape | |
--optShapes=${INPUT_NAME}:${MAX_BATCH_SIZE}x3x224x224 \ # kOPT shape | |
--maxShapes=${INPUT_NAME}:${MAX_BATCH_SIZE}x3x224x224 \ # kMAX shape | |
--shapes=${INPUT_NAME}:1x3x224x224 \ # Inference shape - this is like context.set_binding_shape(0, (1,3,224,224)) | |
--saveEngine=alexnet_dynamic.engine |
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment