Keras Frontend

Installing Dependencies

Updating pip:

The pip version required in this subproject must be >= 19.3.

To upgrade pip:

pip install --upgrade pip

To check installed pip version:

pip -V

Importing and Creating the Required Conda Environment:

conda env create -f keras_environment.yml --name ${KERAS_ENV_NAME}

Note: pip version MUST be > 19.3

This is a one-time installation step.

Activating Conda Environment:

conda activate ${KERAS_ENV_NAME}

NOTE: This step must be performed each time (for each shell process) the frontend is to be used.

Building and Installing Frontend:

python setup.py build

python setup.py install

NOTE: This step must be performed each time (for each shell process) the frontend is to be used.

Running Benchmaks

Benchmarks under ./src/

NOTE: Activate conda environment (above) before running benchmarks

List of benchmarks and the expected accuracies:

Synopsis

python src/${BENCH_NAME}.py  [hpvm_reload|keras_reload]  [frontend] [compile]

Command-line Parameters

hpvm_reload : Reloads HPVM weights ('.bin' binary format used in model_params found here: https://gitlab.engr.illinois.edu/llvm/hpvm/-/tree/approx_hpvm_reorg_keras/hpvm/test/dnn_benchmarks/model_params) from directory path specified in the reload_dir parameter set in code - this is described in "Parameters to Change in Code" (below).

keras_reload: Alternatively, reload weights in Keras .h5 file format with path to file specified in keras_model_file described in "Parameters to Change in Code" (below).

frontend: Invokes the HPVM frontend and dumps weights (in HPVM .bin format) in the output directory specified. The parameters that control where data and source files are dumped are specified by parameters data_dir and src_dir, respectively. These are described below.

compile: Optional Parameter. When specified, it compiles the HPVM-C code generated by the frontend into an HPVM binary under the directory specified by src_dir (described below). If src_dir path exists, a unique directory (which appends a unique ID) is created. The binary is built with the name HPVM_binary.

NOTE: Before running HPVM_binary necessary to set CUDA/CUDNN paths with:

source ${HPVM_root}/set_paths.sh

Parameters to Change in Code

The AlexNet source is commented with explanations on how to use the Keras frontend interface. AlexNet source is here.

• NAME: Benchmark Name - Can be set to any desired value

• reload_dir: Path to directory from where to reload weights in HPVM format. This directory is used to reload weights if hpvm_reload command-line option is used.

• keras_model_file: Path to Keras .h5 model file to reload weigths from. Either of reload_dir or keras_model_file can be used. keras_model_file is used when keras_reload commad-line parameter is used with the Benchmark script.

• data_dir: Directory to dump weights specified specified in constructor

• src_dir: Directory to dump ApproxHPVM sources in HPVM-C (C with HPVM compiler intrinsics) specified in constructor

• num_classes: number of output classes - dependent on the dataset used. For CIFAR10, num_classes is 10, CIFAR100 has 100 classes, for ImageNet, number of classes is 1000.

• batch_size: This parameter controls the size of each batch that is processed in HPVM. The batch size should be kept as large as the GPU memory can support. This parameter should be adapted according to the memory size of the deployed device.

Using the Frontend with Custom (New) Benchmarks

Any new benchmarks must inherit from the commom parent Benchmark class and override the virtual functions for building the model, training, and data preprocessing. These methods are described below:

def buildModel(self): Constructs and returns a keras model

def data_preprocess(self): returns X_train, y_train, X_test, y_test, X_tuner, and y_tuner data (in that order): These are described here:

• X_train: Training data (fp32) in NCHW format

• y_train: Training labels (int32)

• X_test: Testing/Evaluation data in NCHW format

• y_test: Testing/Evaluation labels

• X_tuner: Data to be used for autotuning

• y_tuner: Labels corresponding to tuning data

def trainModel(self, model, X_train, y_train, X_test, y_test): Trains the Keras model constructed in buildModel and is expected to return the trained keras model - training parameters should be tuned here.

Suppported Operations

List of supported operations and limitations detailed in https://gitlab.engr.illinois.edu/llvm/hpvm/-/blob/approx_hpvm_reorg_keras/hpvm/projects/keras/docs/Support.md