Classification (TF2) with TAO Deploy

TF2 Classification etlt file generated from tao export is taken as an input to tao-deploy to generate optimized TensorRT engine. For more information about training the TF2 Classification, please refer to TF2 Classification training documentation.

Converting .etlt File into TensorRT Engine

Same spec file can be used as the tao classification_tf2 export command.

Export Config

The export configuration contains the parameters of exporting a .etlt model to TensorRT engine, which can be used for deployment.

Field	Description	Data Type and Constraints	Recommended/Typical Value
output_path	The path to save the exported .etlt model	string	False
engine_file	The path where the generated engine will be stored	string	False
cal_image_dir	The directory containing images to be used for calibration	string	False
cal_cache_file	The path to calibration cache file	string	False
cal_data_file	The path to calibration data file	string	False
batches	The size of batches to be iterated for calibration	unsigned int	10
batch_size	The batch size for each batch	unsigned int	1
data_type	The precision to be used for the TensorRT engine	string	FP32
min_batch_size	The minimum batch size used for optimization profile shape	unsigned int	1
opt_batch_size	The optimal batch size used for optimization profile shape	unsigned int	1
max_batch_size	The maximum batch size used for optimization profile shape	unsigned int	1
max_workspace_size	The maximum workspace size for the TensorRT engine	unsigned int	2

Below is a sample spec file for TF2 classification.

Copy
Copied!

            
            results_dir: '/workspace/tao-experiments/'
key: 'nvidia_tao'
data:
  train_dataset_path: "/workspace/tao-experiments/data/split/train"
  val_dataset_path: "/workspace/tao-experiments/data/split/val"
  preprocess_mode: 'torch'
model:
  arch: 'efficientnet-b0'
  input_image_size: [3,256,256]
  input_image_depth: 8
evaluate:
  dataset_path: '/workspace/tao-experiments/data/split/test'
  model_path: '/export/efficientnet-b0.int8.engine'
  top_k: 3
  batch_size: 256
  n_workers: 8
inference:
  model_path: '/export/efficientnet-b0.int8.engine'
  image_dir: '/workspace/tao-experiments/data/split/test/aeroplane'
  classmap: '/workspace/tao-experiments/classmap.json'
export:
  output_path: '/export/efficientnet-b0.etlt'
  data_type: 'int8'
  engine_file: '/export/efficientnet-b0.int8.engine'
  cal_image_dir: '/workspace/tao-experiments/data/split/test'
  cal_data_file: '/export/calib.tensorfile'
  cal_cache_file: '/export/cal.bin'
  batch_size: 16
  max_batch_size: 16
  batches: 10

Use the following command to run TF2 Classification engine generation:

Copy
Copied!

            
            tao-deploy classification_tf2 gen_trt_engine -e /path/to/spec.yaml \
           key=<key> \
           export.output_path=/path/to/etlt/file \
           export.engine_file=/path/to/engine/file \
           export.data_type=<data_type>

Required Arguments

-e, --experiment_spec: The experiment spec file to set up the TensorRT engine generation. This should be the same as the export specification file.
-k, --key: A user-specific encoding key to load a .etlt model.

Sample Usage

Here’s an example of using the gen_trt_engine command to generate INT8 TensorRT engine:

Copy
Copied!

            
            tao-deploy classification_tf2 gen_trt_engine -e $DEFAULT_SPEC
           key=$YOUR_KEY \
           export.output_path=$ETLT_FILE \
           export.engine_file=$ENGINE_FILE \
           export.data_type=int8

Running Evaluation through TensorRT Engine

Same spec file as TAO evaluation spec file.

Use the following command to run TF2 Classification engine evaluation:

Copy
Copied!

            
            tao-deploy classification_tf2 evaluate -e /path/to/spec.yaml \
           evaluate.model_path=/path/to/engine/file \
           results_dir=/path/to/outputs

Required Arguments

-e, --experiment_spec: The experiment spec file for evaluation. This should be the same as the tao evaluate specification file.
evaluate.model_path: The engine file to run evaluation.
results_dir: The directory where evaluation results will be stored.

Sample Usage

Here’s an example of using the evaluate command to run evaluation with the TensorRT engine:

Copy
Copied!

            
            tao-deploy classification_tf2 evaluate -e $DEFAULT_SPEC
           evaluate.model_path=$ENGINE_FILE \
           results_dir=$RESULTS_DIR

Running Inference through TensorRT Engine

Same spec file as TAO inference spec file.

Use the following command to run TF2 Classification engine inference:

Copy
Copied!

            
            tao-deploy classification_tf2 inference -e /path/to/spec.yaml \
           inference.model_path=/path/to/engine/file \
           results_dir=/path/to/outputs

Required Arguments

-e, --experiment_spec: The experiment spec file for inference. This should be the same as the tao inference specification file.
inference.model_path: The engine file to run inference.
results_dir: The directory where inference results will be stored.

Sample Usage

Here’s an example of using the inference command to run inference with the TensorRT engine:

Copy
Copied!

            
            tao-deploy classification_tf2 inference -e $DEFAULT_SPEC
           inference.model_path=$ENGINE_FILE \
           results_dir=$RESULTS_DIR

The csv predictions will be stored under $RESULTS_DIR/result.csv.