README.md

UNet++ Inference

UNet++ Inference best known configurations with Intel® Extension for PyTorch.

Model Information

Use Case	Framework	Model Repo	Branch/Commit/Tag	Optional Patch
Inference	PyTorch	https://github.com/qubvel/segmentation_models.pytorch	-	-

Pre-Requisite

• Host has Intel® Data Center GPU Flex Series

• Host has installed latest Intel® Data Center GPU Flex Series Drivers https://dgpu-docs.intel.com/driver/installation.html

• The following Intel® oneAPI Base Toolkit components are required:

  • Intel® oneAPI DPC++ Compiler (Placeholder DPCPPROOT as its installation path)
  • Intel® oneAPI Math Kernel Library (oneMKL) (Placeholder MKLROOT as its installation path)
  • Intel® oneAPI MPI Library
  • Intel® oneAPI TBB Library

  Follow instructions at Intel® oneAPI Base Toolkit Download page to setup the package manager repository.

Inference

1. git clone https://github.com/IntelAI/models.git
2. cd models/models_v2/pytorch/unetpp/inference/gpu
3. Create virtual environment venv and activate it:

   python3 -m venv venv
   . ./venv/bin/activate
   

4. Run setup.sh

   ./setup.sh
   

5. Install the latest GPU versions of torch, torchvision and intel_extension_for_pytorch:

   python -m pip install torch==<torch_version> torchvision==<torchvision_version> intel-extension-for-pytorch==<ipex_version> --extra-index-url https://pytorch-extension.intel.com/release-whl-aitools/
   

6. Set environment variables for Intel® oneAPI Base Toolkit: Default installation location {ONEAPI_ROOT} is /opt/intel/oneapi for root account, ${HOME}/intel/oneapi for other accounts

   source {ONEAPI_ROOT}/compiler/latest/env/vars.sh
   source {ONEAPI_ROOT}/mkl/latest/env/vars.sh
   source {ONEAPI_ROOT}/tbb/latest/env/vars.sh
   source {ONEAPI_ROOT}/mpi/latest/env/vars.sh
   source {ONEAPI_ROOT}/ccl/latest/env/vars.sh

7. Setup required environment paramaters

Parameter	export command
MULTI_TILE	export MULTI_TILE=False (False)
PLATFORM	export PLATFORM=Flex (Flex)
OUTPUT_DIR	export OUTPUT_DIR=$PWD
BATCH_SIZE (optional)	export BATCH_SIZE=8
PRECISION (optional)	export PRECISION=fp16

8. Run run_model.sh

Output

Single-tile output will typically looks like:

Latency: 0.03823380470275879
Throughput: 209.23891990855813

Final results of the inference run can be found in results.yaml file.

results:
 - key: throughput
   value: 209.23892
   unit: fps
 - key: latency
   value: 0.03823380470275879
   unit: s
 - key: accuracy
   value: None
   unit: Acc