MaskRCNN

MaskRCNN supports the following tasks:

  • dataset_convert

  • train

  • evaluate

  • prune

  • inference

  • export

These tasks may be invoked from the TAO Toolkit Launcher using the following convention on the command line:

tao mask_rcnn <sub_task> <args_per_subtask>

where args_per_subtask are the command-line arguments required for a given subtask. Each of these subtasks are explained in detail below.

Pre-processing the Dataset

The raw image data and the corresponding annotation file need to be converted to TFRecords before training and evaluation. The dataset_convert tool helps to achieve seamless conversion while providing insight on potential issues in an annotation file. The following sections detail how to use dataset_convert.

Sample Usage of the Dataset Converter Tool

The dataset_convert tool is described below:

tao mask_rcnn dataset-convert [-h] -i <image_directory>
                                   -a <annotation_json_file>
                                   -o <tfrecords_output_directory>
                                   [-t <tag>]
                                   [-s <num_shards>]
                                   [--include_mask]

You can use the following arguments:

  • -i, --image_dir: The path to the directory where raw images are stored

  • -a, --annotations_file: The annotation JSON file

  • -o, --output_dir: The output directory where TFRecords are saved

  • -t, --tag: The tag for the converted TFRecords (e.g. “train”). The tag defaults to the name of the annotation file.

  • -s, --num_shards: The number of shards for the converted TFRecords. The default value is 256.

  • --include_mask: Whether to include segmentation groundtruth during conversion. The default value is True.

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

    Note

    A log file named <tag>_warnings.json will be generated in the output_dir if the bounding box of an object is out of bounds with respect to the image frame or if an object mask is out of bounds with respect to its bounding box. The log file records the image_id that has problematic object IDs. For example, {"200365": {"box": [918], "mask": []} means the bounding box of object 918 is out of bounds in image 200365.

The following example shows how to use the command with the dataset:

tao mask_rcnn dataset_convert -i /path/to/image_dir
                              -a /path/to/train.json
                              -o /path/to/output_dir

Creating a Configuration File

Below is a sample MaskRCNN spec file. It has three major components: top level experiment configs, data_config, and maskrcnn_config, explained below in detail. The format of the spec file is a protobuf text (prototxt) message and each of its fields can be either a basic data type or a nested message. The top level structure of the spec file is summarized in the table below.

Here’s a sample of the MaskRCNN spec file:

seed: 123
use_amp: False
warmup_steps: 0
checkpoint: "/workspace/tao-experiments/maskrcnn/pretrained_resnet50/tlt_instance_segmentation_vresnet50/resnet50.hdf5"
learning_rate_steps: "[60000, 80000, 100000]"
learning_rate_decay_levels: "[0.1, 0.02, 0.002]"
total_steps: 120000
train_batch_size: 2
eval_batch_size: 4
num_steps_per_eval: 10000
momentum: 0.9
l2_weight_decay: 0.0001
l1_weight_decay: 0.0
warmup_learning_rate: 0.0001
init_learning_rate: 0.02
num_examples_per_epoch: 14700
# pruned_model_path: "/workspace/tao-experiments/maskrcnn/pruned_model/model.tlt"

data_config{
        image_size: "(832, 1344)"
        augment_input_data: True
        eval_samples: 500
        training_file_pattern: "/workspace/tao-experiments/data/train*.tfrecord"
        validation_file_pattern: "/workspace/tao-experiments/data/val*.tfrecord"
        val_json_file: "/workspace/tao-experiments/data/annotations/instances_val2017.json"

        # dataset specific parameters
        num_classes: 91
        skip_crowd_during_training: True
        max_num_instances: 200
}

maskrcnn_config {
        nlayers: 50
        arch: "resnet"
        freeze_bn: True
        freeze_blocks: "[0,1]"
        gt_mask_size: 112

        # Region Proposal Network
        rpn_positive_overlap: 0.7
        rpn_negative_overlap: 0.3
        rpn_batch_size_per_im: 256
        rpn_fg_fraction: 0.5
        rpn_min_size: 0.

        # Proposal layer.
        batch_size_per_im: 512
        fg_fraction: 0.25
        fg_thresh: 0.5
        bg_thresh_hi: 0.5
        bg_thresh_lo: 0.

        # Faster-RCNN heads.
        fast_rcnn_mlp_head_dim: 1024
        bbox_reg_weights: "(10., 10., 5., 5.)"

        # Mask-RCNN heads.
        include_mask: True
        mrcnn_resolution: 28

        # training
        train_rpn_pre_nms_topn: 2000
        train_rpn_post_nms_topn: 1000
        train_rpn_nms_threshold: 0.7

        # evaluation
        test_detections_per_image: 100
        test_nms: 0.5
        test_rpn_pre_nms_topn: 1000
        test_rpn_post_nms_topn: 1000
        test_rpn_nms_thresh: 0.7

        # model architecture
        min_level: 2
        max_level: 6
        num_scales: 1
        aspect_ratios: "[(1.0, 1.0), (1.4, 0.7), (0.7, 1.4)]"
        anchor_scale: 8

        # localization loss
        rpn_box_loss_weight: 1.0
        fast_rcnn_box_loss_weight: 1.0
        mrcnn_weight_loss_mask: 1.0
}

Field

Description

Data Type and Constraints

Recommended/Typical Value

seed

The random seed for the experiment

Unsigned int

123

warmup_steps

The steps taken for learning rate to ramp up to the init_learning_rate

Unsigned int

warmup_learning_rate

The initial learning rate during the warmup phase

float

learning_rate_steps

A list of steps at which the learning rate decays by the factor specified in learning_rate_decay_levels

string

learning_rate_decay_levels

A list of decay factors. The length should match the length of learning_rate_steps.

string

total_steps

The total number of training iterations

Unsigned int

train_batch_size

The batch size during training

Unsigned int

4

eval_batch_size

The batch size during validation or evaluation

Unsigned int

8

num_steps_per_eval

Save a checkpoint and run evaluation every N steps.

Unsigned int

momentum

Momentum of the SGD optimizer

float

0.9

l1_weight_decay

L1 weight decay

float

0.0001

l2_weight_decay

L2 weight decay

float

0.0001

use_amp

Specifies whether to use Automatic Mixed Precision training

boolean

False

checkpoint

The path to a pretrained model

string

maskrcnn_config

The architecture of the model

message

data_config

The input data configuration

message

skip_checkpoint_variables

If specified, the weights of the layers with matching regular expressions will not be loaded. This is especially helpful for transfer learning.

string

pruned_model_path

The path to a pruned MaskRCNN model

string

num_examples_per_epoch

The total number of images in the training set divided by the number of GPUs

Unsigned int

num_epochs

The number of epochs to train the network

Unsigned int

visualize_images_summary

Whether to preview images and inference results in TensorBoard. If enabled, 10 images with predicted bounding boxes from the validation set will be saved in the TensorBoard events file.

boolean

Note

The num_examples_per_epoch parameter must be specified, and either num_epochs or total_steps should be specified. If both are set, total_steps will be overwritten by num_epochs * num_examples_per_epoch / train_batch_size

Note

When using skip_checkpoint_variables, you can first find the model structure in the training log (Part of the MaskRCNN+ResNet50 model structure is shown below). If, for example, you want to retrain all prediction heads, you can set skip_checkpoint_variables to “head”. TAO Toolkit uses the Python re library to check whether “head” matches any layer name or re.search($skip_checkpoint_variables, $layer_name).

[MaskRCNN] INFO    : ================ TRAINABLE VARIABLES ==================
[MaskRCNN] INFO    : [#0001] conv1/kernel:0                                               => (7, 7, 3, 64)
[MaskRCNN] INFO    : [#0002] bn_conv1/gamma:0                                             => (64,)
[MaskRCNN] INFO    : [#0003] bn_conv1/beta:0                                              => (64,)
[MaskRCNN] INFO    : [#0004] block_1a_conv_1/kernel:0                                     => (1, 1, 64, 64)
[MaskRCNN] INFO    : [#0005] block_1a_bn_1/gamma:0                                        => (64,)
[MaskRCNN] INFO    : [#0006] block_1a_bn_1/beta:0                                         => (64,)
[MaskRCNN] INFO    : [#0007] block_1a_conv_2/kernel:0                                     => (3, 3, 64, 64)
[MaskRCNN] INFO    : [#0008] block_1a_bn_2/gamma:0                                        => (64,)
[MaskRCNN] INFO    : [#0009] block_1a_bn_2/beta:0                                         => (64,)
[MaskRCNN] INFO    : [#0010] block_1a_conv_3/kernel:0                                     => (1, 1, 64, 256)
[MaskRCNN] INFO    : [#0011] block_1a_bn_3/gamma:0                                        => (256,)
[MaskRCNN] INFO    : [#0012] block_1a_bn_3/beta:0                                         => (256,)
[MaskRCNN] INFO    : [#0110] block_3d_bn_3/gamma:0                                        => (1024,)
[MaskRCNN] INFO    : [#0111] block_3d_bn_3/beta:0                                         => (1024,)
[MaskRCNN] INFO    : [#0112] block_3e_conv_1/kernel:0                                     => (1, 1, 1024, [MaskRCNN] INFO    : [#0144] block_4b_bn_1/beta:0                                         => (512,)
                                …     …       …    …                                                                       ...
[MaskRCNN] INFO    : [#0174] post_hoc_d5/kernel:0                                     => (3, 3, 256, 256)
[MaskRCNN] INFO    : [#0175] post_hoc_d5/bias:0                                       => (256,)
[MaskRCNN] INFO    : [#0176] rpn/kernel:0                                        => (3, 3, 256, 256)
[MaskRCNN] INFO    : [#0177] rpn/bias:0                                          => (256,)
[MaskRCNN] INFO    : [#0178] rpn-class/kernel:0                                  => (1, 1, 256, 3)
[MaskRCNN] INFO    : [#0179] rpn-class/bias:0                                    => (3,)
[MaskRCNN] INFO    : [#0180] rpn-box/kernel:0                                    => (1, 1, 256, 12)
[MaskRCNN] INFO    : [#0181] rpn-box/bias:0                                      => (12,)
[MaskRCNN] INFO    : [#0182] fc6/kernel:0                                        => (12544, 1024)
[MaskRCNN] INFO    : [#0183] fc6/bias:0                                          => (1024,)
[MaskRCNN] INFO    : [#0184] fc7/kernel:0                                        => (1024, 1024)
[MaskRCNN] INFO    : [#0185] fc7/bias:0                                          => (1024,)
[MaskRCNN] INFO    : [#0186] class-predict/kernel:0                              => (1024, 91)
[MaskRCNN] INFO    : [#0187] class-predict/bias:0                                => (91,)
[MaskRCNN] INFO    : [#0188] box-predict/kernel:0                                => (1024, 364)
[MaskRCNN] INFO    : [#0189] box-predict/bias:0                                  => (364,)
[MaskRCNN] INFO    : [#0190] mask-conv-l0/kernel:0                              => (3, 3, 256, 256)
[MaskRCNN] INFO    : [#0191] mask-conv-l0/bias:0                                => (256,)
[MaskRCNN] INFO    : [#0192] mask-conv-l1/kernel:0                              => (3, 3, 256, 256)
[MaskRCNN] INFO    : [#0193] mask-conv-l1/bias:0                                => (256,)
[MaskRCNN] INFO    : [#0194] mask-conv-l2/kernel:0                              => (3, 3, 256, 256)
[MaskRCNN] INFO    : [#0195] mask-conv-l2/bias:0                                => (256,)
[MaskRCNN] INFO    : [#0196] mask-conv-l3/kernel:0                              => (3, 3, 256, 256)
[MaskRCNN] INFO    : [#0197] mask-conv-l3/bias:0                                => (256,)
[MaskRCNN] INFO    : [#0198] conv5-mask/kernel:0                                => (2, 2, 256, 256)
[MaskRCNN] INFO    : [#0199] conv5-mask/bias:0                                  => (256,)
[MaskRCNN] INFO    : [#0200] mask_fcn_logits/kernel:0                           => (1, 1, 256, 91)
[MaskRCNN] INFO    : [#0201] mask_fcn_logits/bias:0                             => (91,)

MaskRCNN Config

The MaskRCNN configuration (maskrcnn_config) defines the model structure. This model is used for training, evaluation, and inference. A detailed description is included in the table below. Currently, MaskRCNN only supports ResNet10/18/34/50/101 as its backbone.

Field

Description

Data Type and Constraints

Recommended/Typical Value

nlayers

The number of layers in ResNet arch

Unsigned int

50

arch

The backbone feature extractor name

string

resnet

freeze_bn

Whether to freeze all BatchNorm layers in the backbone

boolean

False

freeze_blocks

A list of conv blocks in the backbone to freeze

string

ResNet: For the ResNet series, the block IDs valid for freezing are any subset of [0, 1, 2, 3] (inclusive)

gt_mask_size

The groundtruth mask size

Unsigned int

112

rpn_positive_overlap

The lower-bound threshold to assign positive labels for anchors

float

0.7

rpn_negative_overlap

The upper-bound threshold to assign negative labels for anchors

float

0.3

rpn_batch_size_per_im

The number of sampled anchors per image in RPN

Unsigned int

256

rpn_fg_fraction

The desired fraction of positive anchors in a batch

Unsigned int

0.5

rpn_min_size

The minimum proposal height and width

0

batch_size_per_im

The RoI minibatch size per image

Unsigned int

512

fg_fraction

The target fraction of RoI minibatch that is labeled as foreground

float

0.25

fast_rcnn_mlp_head_dim

The Fast-RCNN classification head dimension

Unsigned int

1024

bbox_reg_weights

The bounding-box regularization weights

string

“(10, 10, 5, 5)”

include_mask

Specifies whether to include a mask head

boolean

True

(currently only True is supported)

mrcnn_resolution

The mask-head resolution (must be multiple of 4)

Unsigned int

28

train_rpn_pre_nms_topn

The number of top-scoring RPN proposals to keep before applying NMS (per FPN level) during training

Unsigned int

2000

train_rpn_post_nms_topn

The number of top-scoring RPN proposals to keep after applying NMS (total number produced) during training

Unsigned int

1000

train_rpn_nms_threshold

The NMS IOU threshold in RPN during training

float

0.7

test_detections_per_image

The number of bounding box candidates after NMS

Unsigned int

100

test_nms

The NMS IOU threshold during test

float

0.5

test_rpn_pre_nms_topn

The number of top-scoring RPN proposals to keep before applying NMS (per FPN level) during test

Unsigned int

1000

test_rpn_post_nms_topn

The number of top scoring RPN proposals to keep after applying NMS (total number produced) during test

Unsigned int

1000

test_rpn_nms_threshold

The NMS IOU threshold in RPN during test

float

0.7

min_level

The minimum level of the output feature pyramid

Unsigned int

2

max_level

The maximum level of the output feature pyramid

Unsigned int

6

num_scales

The number of anchor octave scales on each pyramid level (e.g. if set to 3, the anchor scales are [2^0, 2^(1/3), 2^(2/3)])

Unsigned int

1

aspect_ratios

A list of tuples representing the aspect ratios of anchors on each pyramid level

string

“[(1.0, 1.0), (1.4, 0.7), (0.7, 1.4)]”

anchor_scale

Scale of the base-anchor size to the feature-pyramid stride

Unsigned int

8

rpn_box_loss_weight

The weight for adjusting RPN box loss in the total loss

float

1.0

fast_rcnn_box_loss_weight

The weight for adjusting FastRCNN box regression loss in the total loss

float

1.0

mrcnn_weight_loss_mask

The weight for adjusting mask loss in the total loss

float

1.0

Note

The min_level, max_level, num_scales, aspect_ratios, and anchor_scale are used to determine anchor generation for MaskRCNN. anchor_scale is the base anchor scale, while min_level and max_level set the range of the scales on different feature maps. For example, the actual anchor scale for the feature map at min_level will be anchor_scale * 2^min_level and the actual anchor scale for the feature map at max_level will be anchor_scale * 2^max_level. And it will generate anchors of different aspect_ratios based on the actual anchor scale.

Data Config

The data configuration (data_config) specifies the input data source and format. This is used for training, evaluation, and inference. A detailed description is summarized in the table below.

Field

Description

Data Type and Constraints

Recommended/Typical Value

image_size

The image dimension as a tuple within quote marks. “(height, width)” indicates the dimension of the resized and padded input.

string

“(832, 1344)”

augment_input_data

Specifies whether to augment the data

boolean

True

eval_samples

The number of samples for evaluation

Unsigned int

training_file_pattern

The TFRecord path for training

string

validation_file_pattern

The TFRecord path for validation

string

val_json_file

The annotation file path for validation

string

num_classes

The number of classes. If there are N categories in the annotation, num_classes should be N+1 (background class)

Unsigned int

skip_crowd_during_training

Specifies whether to skip crowd during training

boolean

True

prefetch_buffer_size

The prefetch buffer size used by tf.data.Dataset (default: AUTOTUNE)

Unsigned int

shuffle_buffer_size

The shuffle buffer size used by tf.data.Dataset (default: 4096)

Unsigned int

4096

n_workers

The number of workers to parse and preprocess data (default: 16)

Unsigned int

16

max_num_instances

The maximum number of object instances to parse (default: 200)

Unsigned int

200

Note

If an out-of-memory error occurs during training, try to set a smaller image_size or batch_size first. If the error persists, try reducing the n_workers, shuffle_buffer_size, and prefetch_buffer_size values. Lastly, if the original images have a very large resolution, resize the images offline and create new tfrecords to avoid loading large images to GPU memory.

Training the Model

Train the MaskRCNN model using this command:

tao mask_rcnn train [-h] -e <experiment_spec>
                         -d <output_dir>
                         -k <key>
                         [--gpus <num_gpus>]
                         [--gpu_index <gpu_index>]
                         [--log_file <log_file_path>]

Required Arguments

  • -d, --model_dir: The path to the folder where the experiment output is written.

  • -k, --key: The encryption key to decrypt the model.

  • -e, --experiment_spec_file: The experiment specification file to set up the evaluation. experiment. This should be the same as the training specification file.

Optional Arguments

  • --gpus num_gpus: The number of GPUs to use and processes to launch for training. The default value is 1.

  • --gpu_index: The index of the (discrete) GPU for exporting the model if the machine has multiple GPUs installed. Note that export can only run on a single GPU.

  • --log_file: The path to the log file. The default path is stdout.

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

Input Requirement

  • Input size: C * W * H (where C = 3, W >= 128, H >= 128 and W, H are multiples of 2^ max_level)

  • Image format: JPG

  • Label format: COCO detection

Sample Usage

Here’s an example of using the train command on a MaskRCNN model:

tao mask_rcnn train --gpus 2 -e /path/to/spec.txt -d /path/to/result -k $KEY

Evaluating the Model

To run evaluation for a MaskRCNN model, use this command:

tao mask_rcnn evaluate [-h] -e <experiment_spec_file>
                            -m <model_file>
                            -k <key>
                            [--gpu_index <gpu_index>]
                            [--log_file <log_file_path>]

Required Arguments

  • -e, --experiment_spec_file: The experiment spec file to set up the evaluation experiment. This should be the same as the training spec file.

  • -m, --model: The path to the model file to use for evaluation (only .tlt model is supported).

  • -k, --key: The key to load the model.

Optional Arguments

  • --gpu_index: The index of the (discrete) GPU for exporting the model if the machine has multiple GPUs installed. Note that export can only run on a single GPU.

  • --log_file: The path to the log file. The default path is stdout.

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

Pruning the Model

Pruning removes parameters from the model to reduce the model size. Retraining is necessary to regain the performance of the unpruned model.

The prune command includes these parameters:

tao mask_rcnn prune [-h] -m <pretrained_model>
                         -o <output_dir>
                         -k <key>
                         [-n <normalizer>]
                         [-eq <equalization_criterion>]
                         [-pg <pruning_granularity>]
                         [-pth <pruning threshold>]
                         [-nf <min_num_filters>]
                         [-el [<excluded_list>]
                         [--gpu_index <gpu_index>]
                         [--log_file <log_file>]

Required Arguments

  • -m, --pretrained_model: The path to the pretrained model.

  • -o, --output_dir: The output directory which contains the pruned model, named as model.tlt.

  • -k, --key: The key to load a .tlt model.

Optional Arguments

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

  • -n, --normalizer: max to normalize by dividing each norm by the maximum norm within a layer; L2 to normalize by dividing by the L2 norm of the vector comprising all kernel norms. (default: max)

  • -eq, --equalization_criterion: Criteria to equalize the stats of inputs to an element wise op layer, or depth-wise convolutional layer. This parameter is useful for resnets and mobilenets. Options are arithmetic_mean, geometric_mean, union, and intersection. (default: union)

  • -pg, --pruning_granularity: Number of filters to remove at a time. (default:8)

  • -pth: Threshold to compare normalized norm against. (default:0.1)

  • -nf, --min_num_filters: Minimum number of filters to keep per layer (default:16)

  • -el, --excluded_layers: List of excluded_layers. Examples: -i item1 item2 (default: [])

  • --gpu_index: The index of the GPU to run evaluation (useful when the machine has multiple GPUs installed). Note that evaluation can only run on a single GPU.

  • --log_file: The path to the log file. Defaults to stdout.

Here’s an example of using the prune command:

tao mask_rcnn prune -m /workspace/model.step-100.tlt
                    -o /workspace/output
                    -eq union
                    -pth 0.7 -k $KEY

After pruning, the model needs to be retrained first before it can be used for inference or evaluation.

Re-training the Pruned Model

Once the model has been pruned, there might be a decrease in accuracy. This happens because some previously useful weights may have been removed. To regain accuracy, NVIDIA recommends that you retrain this pruned model over the same dataset. To do this, run the tao mask_rcnn train command with an updated spec file that points to the newly pruned model by setting pruned_model_path.

Users are advised to turn off the regularizer during retraining. You may do this by setting the regularizer weights to 0 for both l1_weight_decay and l2_weight_decay. The other parameters may be retained in the spec file from the previous training. train_batch_size and eval_batch_size must be kept unchanged.

Running Inference on the Model

The inference tool for MaskRCNN networks can be used to visualize bboxes or generate frame-by-frame COCO-format labels on a directory of images. Here’s an example of using this tool:

tao mask_rcnn inference [-h] -i <input directory>
                             -o <output annotated image directory>
                             -e <experiment spec file>
                             -m <model file>
                             -k <key>
                             [-l <label file>]
                             [-t <bbox confidence threshold>]
                             [--include_mask]
                             [--gpu_index <gpu_index>]
                             [--log_file <log_file_path>]

Required Arguments

  • -m, --model_path: The path to the trained MaskRCNN model (either a .tlt model or a converted TensorRT engine).

  • -i, --image_dir: The directory of input images for inference. Supported image formats include PNG, JPG and JPEG.

  • -e, --config_path: The path to an experiment spec file for training.

  • -o, --out_image_path: The directory path to output annotated images.

  • -k, --key: The key to load a .tlt model (not needed if TensorRT engine is used).

Optional Arguments

  • -t, --threshold: The threshold for drawing a bbox (default: 0.6)

  • -l, --out_label_path: The directory of predicted labels in COCO format (https://cocodataset.org/#format-results). This argument is only supported with the TensorRT engine.

  • --include_mask: Specifies whether to draw masks on the annotated output.

  • --gpu_index: The index of the (discrete) GPU for exporting the model if the machine has multiple GPUs installed. Note that export can only run on a single GPU.

  • --log_file: The path to the log file. The default path is stdout.

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

Exporting the Model

Exporting the model decouples the training process from inference and allows conversion to TensorRT engines outside the TAO environment. TensorRT engines are specific to each hardware configuration and should be generated for each unique inference environment. The exported model may be used universally across training and deployment hardware.

The exported model format is referred to as .etlt. Like the .tlt model format, .etlt is an encrypted model format, and it uses the same key as the .tlt model that it is exported from. This key is required when deploying this model.

INT8 Mode Overview

TensorRT engines can be generated in INT8 mode to improve performance, but require a calibration cache at engine creation-time. The calibration cache is generated using a calibration tensor file, if export is run with the --data_type flag set to int8. Pre-generating the calibration information and caching it removes the need for calibrating the model on the inference machine. Moving the calibration cache is usually much more convenient than moving the calibration tensorfile, since it is a much smaller file and can be moved with the exported model. Using the calibration cache also speeds up engine creation as building the cache can take several minutes to generate depending on the size of the Tensorfile and the model itself.

The export tool can generate the INT8 calibration cache by ingesting training data using one of these options:

  • Option 1: Use the training data loader to load the training images for INT8 calibration. This option is now the recommended approach to support multiple image directories by leveraging the training dataset loader. This also ensures two important aspects of data during calibration:

    • Data pre-processing in the INT8 calibration step is the same as in the training process.

    • The data batches are sampled randomly across the entire training dataset, thereby improving the accuracy of the INT8 model.

  • Option 2: Point the tool to a directory of images that you want to use to calibrate the model. For this option, make sure to create a sub-sampled directory of random images that best represent your training dataset.

FP16/FP32 Model

The calibration.bin is only required if you need to run inference at INT8 precision. For FP16/FP32-based inference, the export step is much simpler: All you need to do is provide a .tlt model from the training/retraining step to be converted into .etlt format.

Exporting the MaskRCNN Model

Here’s an example of the command line arguments of the tao mask_rcnn export command:

tao mask_rcnn export [-h] -m <path to the .tlt model file generated by tao train>
                          -k <key>
                          --experiment_spec <path to experiment spec file>
                          [-o <path to output file>]
                          [--gen_ds_config <Flag to generate ds config and label file>]
                          [--gpu_index <gpu_index>]
                          [--log_file <log_file_path>]

Required Arguments

  • -m, --model: The path to the .tlt model file to be exported using export.

  • -k, --key: The key used to save the .tlt model file.

  • -e, --experiment_spec: The path to the spec file.

Optional Arguments

  • -o, --output_file: The path to save the exported model to. The default path is ./<input_file>.etlt.

  • --gen_ds_config: A Boolean flag indicating whether to generate the template DeepStream related configuration (“nvinfer_config.txt”) as well as a label file (“labels.txt”) in the same directory as the output_file. Note that the config file is NOT a complete configuration file and requires the user to update the sample config files in DeepStream with the parameters generated.

  • --gpu_index: The index of the (discrete) GPU for exporting the model if the machine has multiple GPUs installed. Note that export can only run on a single GPU.

  • --log_file: The path to the log file. The default path is stdout.

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

Note

MaskRCNN does not support QAT.

Sample usage

Here’s a sample command to export a MaskRCNN model in INT8 mode:

tao mask_rcnn export -m /ws/model.step-25000.tlt \
                     -k nvidia_tlt \
                     -e /ws/maskrcnn_train_resnet50.txt

TensorRT Engine Generation, Validation, and int8 Calibration

For TensorRT engine generation, validation, and int8 calibration, refer to the TAO Deploy documentation.

Deploying to DeepStream

Refer to Integrating a MaskRCNN Model to learn more about deploying a MaskRCNN model to DeepStream.