UNet with TAO Deploy
The UNet .onnx
file generated from tao model export
is taken as an input to tao deploy
to generate
optimized TensorRT engine. For more information about training the UNet, please refer to UNet training documentation.
Same spec file can be used as the tao model unet export
command.
Use the following command to run UNet engine generation:
tao deploy unet gen_trt_engine [-h] [-v]
-m MODEL_PATH
-e EXPERIMENT_SPEC
-r RESULTS_DIR
[-k KEY]
[--data_type {fp32,fp16,int8}]
[--engine_file ENGINE_FILE]
[--cal_image_dir CAL_IMAGE_DIR]
[--cal_data_file CAL_DATA_FILE]
[--cal_cache_file CAL_CACHE_FILE]
[--cal_json_file CAL_JSON_FILE]
[--max_batch_size MAX_BATCH_SIZE]
[--min_batch_size MIN_BATCH_SIZE]
[--opt_batch_size OPT_BATCH_SIZE]
[--batch_size BATCH_SIZE]
[--batches BATCHES]
[--max_workspace_size MAX_WORKSPACE_SIZE]
[-s STRICT_TYPE_CONSTRAINTS]
[--force_ptq FORCE_PTQ]
[--gpu_index GPU_INDEX]
[--log_file LOG_FILE]
Required Arguments
-m, --model_path
: The.onnx
or.etlt
model to be converted.-e, --experiment_spec
: The experiment spec file to set up the TensorRT engine generation. This should be the same as the export specification file.-r, --results_dir
: The directory where the JSON status-log file will be dumped
Optional Arguments
-h, --help
: Show this help message and exit.-k, --key
: A user-specific encoding key to load a.etlt
model.--data_type
: The desired engine data type. The options arefp32
,fp16
,int8
. The default value isfp32
. A calibration cache will be generated in INT8 mode. If using INT8, the following INT8 arguments are required.--engine_file
: Path to the serialized TensorRT engine file. Note that this file is hardware specific, and cannot be generalized across GPUs. As TensorRT engine file is hardware specific, you cannot use this engine file for deployment unless the deployment GPU is identical to training GPU.-s, --strict_type_constraints
: A Boolean flag indicating whether to apply the TensorRT strict type constraints when building the TensorRT engine.--gpu_index
: The index of (discrete) GPUs used for exporting the model. You can specify the index of the GPU to run export if the machine has multiple GPUs installed. Note that gen_trt_engine can only run on a single GPU.--log_file
: The path to the log file. The default path is “stdout”.
INT8 Engine Generation Required Arguments
--cal_data_file
: Tensorfile generated for calibrating the engine. This can also be an output file if used with--cal_image_dir
.
--cal_image_dir
parameter for images and applies the necessary preprocessing
to generate a tensorfile at the path mentioned in the --cal_data_file
parameter, which is in turn used for calibration. The number of batches in the
tensorfile generated is obtained from the value set to the --batches
parameter,
and the batch_size
is obtained from the value set to the --batch_size
parameter. Be sure that the directory mentioned in --cal_image_dir
has at least
batch_size * batches
number of images in it. The valid image extensions are .jpg,
.jpeg, and .png. In this case, the input_dimensions
of the calibration tensors
are derived from the input layer of the .etlt
model.
INT8 Engine Generation Optional Arguments
--cal_image_dir
: Directory of images to use for calibration. If not specified, training data from the spec file will be used.--cal_cache_file
: The path to save the calibration cache file to. The default value is./cal.bin
.--cal_json_file
: The path to the json file containing tensor scale for QAT models. This argument is required if an engine for QAT model is being generated.--batches
: Number of batches to use for calibration. The default value is 10.--batch_size
: Batch size to use for calibration. The default value is 1.--max_batch_size
: Maximum batch size of TensorRT engine. The default value is 1.--min_batch_size
: Minimum batch size of TensorRT engine. The default value is 1.--opt_batch_size
: Optimal batch size of TensorRT engine. The default value is 1.--max_workspace_size
: Maximum workspace size in Gb of TensorRT engine. The default value is: (2 Gb).--force_ptq
: A boolean flag to force post training quantization on the exported etlt model.
When generating TensorRT engine for a model trained with QAT enabled, the tensor scale factors
defined by the cal_cache_file
argument is required. However, note that the current version of
QAT doesn’t natively support DLA int8 deployment in the Jetson. In order to deploy
this model on a Jetson with DLA int8
, use the --force_ptq
flag to use
TensorRT post training quantization to generate the calibration cache file.
Sample Usage
Here’s an example of using the gen_trt_engine
command to generate INT8 TensorRT engine:
tao deploy unet gen_trt_engine -m /workspace/unet.onnx \
-e /workspace/default_spec.txt \
-r /export/ \
--cal_image_dir /workspace/tao-experiments/data/isbi/images/val \
--data_type int8 \
--batch_size 8 \
--batches 10 \
--cal_cache_file /export/cal.bin \
--cal_data_file /export/cal.tensorfile \
--engine_file /export/int8.engine
Same spec file as TAO evaluation spec file. Sample spec file:
model_config {
model_input_width: 320
model_input_height: 320
model_input_channels: 1
num_layers: 18
all_projections: true
load_graph: true
arch: "resnet"
use_batch_norm: False
training_precision {
backend_floatx: FLOAT32
}
}
dataset_config {
dataset: "custom"
augment: False
input_image_type: "grayscale"
train_images_path:"/workspace/tao-experiments/data/isbi/images/train"
train_masks_path:"/workspace/tao-experiments/data/isbi/masks/train"
val_images_path:"/workspace/tao-experiments/data/isbi/images/val"
val_masks_path:"/workspace/tao-experiments/data/isbi/masks/val"
test_images_path:"/workspace/tao-experiments/data/isbi/images/test"
data_class_config {
target_classes {
name: "foreground"
mapping_class: "foreground"
label_id: 0
}
target_classes {
name: "background"
mapping_class: "background"
label_id: 1
}
}
}
Use the following command to run UNet engine evaluation:
tao deploy unet evaluate [-h]
-e EXPERIMENT_SPEC
-m MODEL_PATH
-r RESULTS_DIR
[-i IMAGE_DIR]
[-l LABEL_DIR]
[-b BATCH_SIZE]
[--gpu_index GPU_INDEX]
[--log_file LOG_FILE]
Required Arguments
-e, --experiment_spec
: The experiment spec file for evaluation. This should be the same as the tao evaluate specification file.-m, --model_path
: The engine file to run evaluation.-r, --results_dir
: The directory where evaluation results will be stored
Optional Arguments
-i, --image_dir
: The directory where test images are located. If not specified,dataset_config.val_data_sources.data_source.images_path
from the spec file will be used.-l, --label_dir
: The directory where test annotations are located. If not specified,dataset_config.val_data_sources.data_source.labels_path
from the spec file will be used.-b, --batch_size
: The batch size used for evaluation. Note that this value can not be larger than--max_batch_size
used during the engine generation. If not specified,training_config.batch_size
will be used instead.
Sample Usage
Here’s an example of using the evaluate
command to run evaluation with the TensorRT engine:
tao deploy unet evaluate -m /export/int8.engine \
-e /workspace/default_spec.txt \
-i /workspace/tao-experiments/data/isbi/images/val \
-l /workspace/tao-experiments/data/isbi/masks/val \
-r /workspace/tao-experiments/evaluate
tao deploy unet inference [-h]
-e EXPERIMENT_SPEC
-m MODEL_PATH
-r RESULTS_DIR
[-i IMAGE_DIR]
[-b BATCH_SIZE]
[--gpu_index GPU_INDEX]
[--log_file LOG_FILE]
Required Arguments
-e, --experiment_spec
: The experiment spec file for evaluation. This should be the same as the tao evaluate specification file.-m, --model_path
: The engine file to run evaluation.-r, --results_dir
: The directory where evaluation results will be stored
Optional Arguments
-i, --image_dir
: The directory where test images are located. If not specified,dataset_config.val_data_sources.data_source.images_path
from the spec file will be used.-b, --batch_size
: The batch size used for evaluation. Note that this value can not be larger than--max_batch_size
used during the engine generation. If not specified,training_config.batch_size
will be used instead.
Sample Usage
Here’s an example of using the inference
command to run inference with the TensorRT engine:
tao deploy unet inference -m /export/int8.engine \
-e /workspace/default_spec.txt \
-i /workspace/tao-experiments/data/isbi/images/val \
-r /workspace/tao-experiments/inference
The visualization will be stored under $RESULTS_DIR/images_annotated
and PNG format mask predictions will be stored under $RESULTS_DIR/labels
.