NVIDIA TAO Toolkit v4.0.1

YOLOv4 with TAO Deploy

YOLOv4 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 YOLOv4, please refer to YOLOv4 training documentation.

Same spec file can be used as the tao yolo_v4 export command.

Use the following command to run YOLOv4 engine generation:

Copy
Copied!
            

tao-deploy yolo_v4 gen_trt_engine [-h] [-v] -m MODEL_PATH -k KEY -e EXPERIMENT_SPEC [--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 .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.

  • -k, --key: A user-specific encoding key to load a .etlt model.

Optional Arguments

  • -h, --help: Show this help message and exit.

  • --data_type: The desired engine data type. The options are fp32, fp16, int8. The default value is fp32. 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: Directory of images to use for calibration.

Note

--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_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.

Note

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:

Copy
Copied!
            

tao-deploy yolo_v4 gen_trt_engine -m /workspace/yolov4_resnet18_epoch_100_int8.etlt \ -e /workspace/yolov4_retrain_resnet18_kitti.txt \ -k $KEY \ --cal_image_dir /workspace/data/training/image_2 \ --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:

Copy
Copied!
            

eval_config { batch_size: 8 matching_iou_threshold: 0.5 } nms_config { confidence_threshold: 0.001 } augmentation_config { output_width: 1248 output_height: 384 output_channel: 3 } dataset_config { validation_data_sources: { image_directory_path: "/workspace/tao-experiments/data/val/images" label_directory_path: "/workspace/tao-experiments/data/val/labels" } image_extension: "png" target_class_mapping { key: "car" value: "car" } target_class_mapping { key: "pedestrian" value: "pedestrian" } target_class_mapping { key: "cyclist" value: "cyclist" } target_class_mapping { key: "van" value: "car" } target_class_mapping { key: "person_sitting" value: "pedestrian" } validation_fold: 0 }

Use the following command to run YOLOv4 engine evaluation:

Copy
Copied!
            

tao-deploy yolo_v4 evaluate [-h] -e EXPERIMENT_SPEC -m MODEL_PATH [-i IMAGE_DIR] [-l LABEL_DIR] [-b BATCH_SIZE] [-r RESULTS_DIR] [--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.

  • -i, --image_dir: The directory where test images are located. If not specified, validation_data_sources.image_directory_path from the spec file will be used.

  • -l, --label_dir: The directory where test annotations are located. If not specified, validation_data_sources.label_directory_path from the spec file will be used.

  • -r, --results_dir: The directory where evaluation results will be stored.

  • -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, eval_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:

Copy
Copied!
            

tao-deploy yolo_v4 evaluate -m /export/int8.engine \ -e /workspace/yolov4_retrain_resnet18_kitti.txt \ -i /workspace/tao-experiments/data/val/images \ -l /workspace/tao-experiments/data/val/labels \ -r /workspace/tao-experiments/evaluate


Copy
Copied!
            

tao-deploy yolo_v4 inference [-h] -e EXPERIMENT_SPEC -m MODEL_PATH [-i IMAGE_DIR] [-b BATCH_SIZE] [-r RESULTS_DIR] [--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.

  • -i, --image_dir: The directory where test images are located. If not specified, validation_data_sources.image_directory_path from the spec file will be used.

  • -r, --results_dir: The directory where evaluation results will be stored.

  • -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, eval_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:

Copy
Copied!
            

tao-deploy yolo_v4 inference -m /export/int8.engine \ -e /workspace/yolov4_retrain_resnet18_kitti.txt \ -i /workspace/tao-experiments/data/val/images \ -r /workspace/tao-experiments/inference

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

© Copyright 2023, NVIDIA.. Last updated on Aug 2, 2023.