TAO v5.5.0
NVIDIA TAO v5.5.0

Deformable DETR with TAO Deploy

To generate an optimized TensorRT engine, a Deformable DETR ONNX file, which is first generated using tao model deformable_detr export, is taken as an input to tao deploy dino gen_trt_engine. For more information about training a Deformable DETR model, refer to the Deformable DETR training documentation.

To convert the .onnx file, you can reuse the spec file from the tao model deformable_detr export command.

gen_trt_engine

The gen_trt_engine parameter defines TensorRT engine generation.

Copy
Copied!
            

gen_trt_engine: onnx_file: /path/to/onnx_file trt_engine: /path/to/trt_engine input_channel: 3 input_width: 960 input_height: 544 tensorrt: data_type: int8 workspace_size: 1024 min_batch_size: 1 opt_batch_size: 10 max_batch_size: 10 calibration: cal_image_dir: - /path/to/cal/images cal_cache_file: /path/to/cal.bin cal_batch_size: 10 cal_batches: 1000

Parameter Datatype Default Description Supported Values
onnx_file string The precision to be used for the TensorRT engine
trt_engine string The maximum workspace size for the TensorRT engine
input_channel unsigned int 3 The input channel size. Only a value of 3 is supported. 3
input_width unsigned int 960 The input width >0
input_height unsigned int 544 The input height >0
batch_size unsigned int -1 The batch size of the ONNX model >=-1

tensorrt

The tensorrt parameter defines the TensorRT engine generation.

Parameter Datatype Default Description Supported Values
data_type string fp32 The precision to be used for the TensorRT engine fp32/fp16/int8
workspace_size unsigned int 1024 The maximum workspace size for the TensorRT engine >1024
min_batch_size unsigned int 1 The minimum batch size used for the optimization profile shape >0
opt_batch_size unsigned int 1 The optimal batch size used for the optimization profile shape >0
max_batch_size unsigned int 1 The maximum batch size used for the optimization profile shape >0

calibration

The calibration parameter defines the TensorRT engine generation with PTQ INT8 calibration.

Parameter Datatype Default Description Supported Values
cal_image_dir string list The list of paths that contain images used for calibration
cal_cache_file string The path to calibration cache file to be dumped
cal_batch_size unsigned int 1 The batch size per batch during calibration >0
cal_batches unsigned int 1 The number of batches to calibrate >0

Use the following command to run Deformable DETR engine generation:

Copy
Copied!
            

tao deploy deformable_detr gen_trt_engine -e /path/to/spec.yaml \ results_dir=/path/to/results \ gen_trt_engine.onnx_file=/path/to/onnx/file \ gen_trt_engine.trt_engine=/path/to/engine/file \ gen_trt_engine.tensorrt.data_type=<data_type>

Required Arguments

  • -e, --experiment_spec: The experiment spec file to set up the TensorRT engine generation

Optional Arguments

  • results_dir: The directory where the JSON status-log file will be dumped

  • gen_trt_engine.onnx_file: The .onnx model to be converted

  • gen_trt_engine.trt_engine: The path where the generated engine will be stored

  • gen_trt_engine.tensorrt.data_type: The precision to be exported

Sample Usage

Here’s an example of using the gen_trt_engine command to generate FP16 TensorRT engine:

Copy
Copied!
            

tao deploy deformable_detr gen_trt_engine -e $DEFAULT_SPEC gen_trt_engine.onnx_file=$ONNX_FILE \ gen_trt_engine.trt_engine=$ENGINE_FILE \ gen_trt_engine.tensorrt.data_type=FP16

You can reuse the TAO evaluation spec file for evaluation through a TensorRT engine. The following is a sample spec file:

Copy
Copied!
            

evaluate: trt_engine: /path/to/engine/file conf_threshold: 0.0 input_width: 960 input_height: 544 dataset: test_data_sources: image_dir: /data/raw-data/val2017/ json_file: /data/raw-data/annotations/instances_val2017.json num_classes: 91 batch_size: 8

Use the following command to run Deformable DETR engine evaluation:

Copy
Copied!
            

tao deploy deformable_detr evaluate -e /path/to/spec.yaml \ results_dir=/path/to/results \ evaluate.trt_engine=/path/to/engine/file

Required Arguments

  • -e, --experiment_spec: The experiment spec file for evaluation. This should be the same as the tao evaluate specification file.

Optional Arguments

  • results_dir: The directory where the JSON status-log file and evaluation results will be dumped

  • evaluate.trt_engine: The engine file to run evaluation

Sample Usage

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

Copy
Copied!
            

tao deploy deformable_detr evaluate -e $DEFAULT_SPEC results_dir=$RESULTS_DIR \ evaluate.trt_engine=$ENGINE_FILE

You can reuse the TAO inference spec file for inference through a TensorRT engine. The following is a sample spec file:

Copy
Copied!
            

inference: conf_threshold: 0.5 input_width: 960 input_height: 544 trt_engine: /path/to/engine/file color_map: person: green car: red cat: blue dataset: infer_data_sources: image_dir: /data/raw-data/val2017/ classmap: /path/to/coco/annotations/coco_classmap.txt num_classes: 91 batch_size: 8

Use the following command to run Deformable DETR engine inference:

Copy
Copied!
            

tao deploy deformable_detr inference -e /path/to/spec.yaml \ -r /path/to/results \ inference.trt_engine=/path/to/engine/file

Required Arguments

  • -e, --experiment_spec: The experiment spec file for inference. This should be the same as the tao inference specification file.

Optional Arguments

  • results_dir: The directory where the JSON status-log file and inference results will be dumped.

  • inference.trt_engine: The engine file to run inference

Sample Usage

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

Copy
Copied!
            

tao deploy deformable_detr inference -e $DEFAULT_SPEC results_dir=$RESULTS_DIR \ evaluate.trt_engine=$ENGINE_FILE

The visualization will be stored under $RESULTS_DIR/images_annotated, and KITTI format predictions will be stored under $RESULTS_DIR/labels.

Previous Classification (TF2) with TAO Deploy
Next DINO with TAO Deploy
© Copyright 2024, NVIDIA. Last updated on Oct 15, 2024.