YOLOv4-tiny

YOLOv4-tiny is an object detection model that is included in the TAO Toolkit. YOLOv4-tiny supports the following tasks:

  • dataset_convert

  • kmeans

  • train

  • evaluate

  • inference

  • prune

  • export

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

tao yolo_v4_tiny <sub_task> <args_per_subtask>

where args_per_subtask are the command line arguments required for a given subtask. Each subtask is explained in detail below.

Preparing the Input Data Structure

The dataset structure of YOLOv4-tiny is identical to that of DetectNet_v2. The only difference is the command line used to generate the TFRecords from KITTI text labels. To generate TFRecords for YOLOv4-tiny training, use this command:

tao yolo_v4_tiny dataset_convert [-h] -d <dataset_spec>
                                     -o <output_tfrecords_file>
                                     [--gpu_index <gpu_index>]

Required Arguments

  • -d, --dataset_spec: path to the dataset spec file.

  • -o, --output_filename: path to the output TFRecords file.

Optional Arguments

  • --gpu_index: The GPU index to run this command on. We can specify the GPU index used to run this command if the machine has multiple GPUs installed. Note that this command can only run on a single GPU.

Creating a Configuration File

Below is a sample for the YOLOv4-tiny spec file. It has 6 major components: yolov4_config, training_config, eval_config, nms_config, augmentation_config, and dataset_config. 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.

random_seed: 42
yolov4_config {
  big_anchor_shape: "[(260.69, 172.35), (125.91, 81.47), (72.27, 42.42)]"
  mid_anchor_shape: "[(30.80, 71.40), (38.97, 26.86), (18.88, 17.11)]"
  box_matching_iou: 0.25
  matching_neutral_box_iou: 0.5
  arch: "cspdarknet_tiny"
  loss_loc_weight: 1.0
  loss_neg_obj_weights: 1.0
  loss_class_weights: 1.0
  label_smoothing: 0.0
  big_grid_xy_extend: 0.05
  mid_grid_xy_extend: 0.05
  freeze_bn: false
  force_relu: false
}
training_config {
  batch_size_per_gpu: 8
  num_epochs: 80
  enable_qat: false
  checkpoint_interval: 10
  learning_rate {
    soft_start_cosine_annealing_schedule {
      min_learning_rate: 1e-7
      max_learning_rate: 1e-4
      soft_start: 0.3
    }
  }
  regularizer {
    type: L1
    weight: 3e-5
  }
  optimizer {
    adam {
      epsilon: 1e-7
      beta1: 0.9
      beta2: 0.999
      amsgrad: false
    }
  }
}
eval_config {
  average_precision_mode: SAMPLE
  batch_size: 8
  matching_iou_threshold: 0.5
}
nms_config {
  confidence_threshold: 0.001
  clustering_iou_threshold: 0.5
  top_k: 200
}
augmentation_config {
  hue: 0.1
  saturation: 1.5
  exposure:1.5
  vertical_flip:0
  horizontal_flip: 0.5
  jitter: 0.3
  output_width: 1248
  output_height: 384
  output_channel: 3
  randomize_input_shape_period: 10
  mosaic_prob: 0.5
  mosaic_min_ratio:0.2
}
dataset_config {
  data_sources: {
      tfrecords_path: "/workspace/tao-experiments/data/training/tfrecords/train*"
      image_directory_path: "/workspace/tao-experiments/data/training"
  }
  include_difficult_in_training: true
  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_data_sources: {
      tfrecords_path: "/workspace/tao-experiments/data/val/tfrecords/val*"
      image_directory_path: "/workspace/tao-experiments/data/val"
  }
}

Training Config

The training configuration (training_config) defines the parameters needed for training, evaluation, and inference. Details are summarized in the table below.

Field

Description

Data Type and Constraints

Recommended/Typical Value

batch_size_per_gpu

The batch size for each GPU; the effective batch size is batch_size_per_gpu * num_gpus

Unsigned int, positive

checkpoint_interval

The number of training epochs per one model checkpoint/validation

Unsigned int, positive

10

num_epochs

The number of epochs to train the network

Unsigned int, positive.

enable_qat

Whether to use quantization-aware training

Boolean

Note: YOLOv4-tiny does not support loading a pruned QAT model and retraining it with QAT disabled, or vice versa. For example, to get a pruned QAT model, perform the initial training with QAT enabled or enable_qat=True.

learning_rate

One soft_start_annealing_schedule and soft_start_cosine_annealing_schedule with the following nested parameters are supported:

  1. min_learning_rate: The minimum learning late during the entire experiment

  2. max_learning_rate: The maximum learning rate during the entire experiment

  3. soft_start: The time to lapse before warm up (expressed as a percentage of progress between 0 and 1)

  4. annealing: (only for soft_start_annealing_schedule) The time to start annealing the learning rate

Message type

regularizer

This parameter configures the regularizer to use while training and contains the following nested parameters:

  1. type: The type of regularizer to use. NVIDIA supports NO_REG, L1, or L2.

  2. weight: The floating point value for regularizer weight

Message type

L1 (Note: NVIDIA suggests using the L1 regularizer when training a network before pruning, as L1 regularization makes the network weights more prunable.)

optimizer

The optimizer can be one of adam, sgd, and rmsprop. Each type has the following parameters:

  1. adam: epsilon, beta1, beta2, amsgrad

  2. sgd: momentum, nesterov

  3. rmsprop: rho, momentum, epsilon, centered

The meanings of above parameters are same as those in Keras.

Message type

pretrain_model_path

The path to the pretrained model, if any

At most, one pretrain_model_path, resume_model_path, and pruned_model_path may be present.

String

resume_model_path

The path to the TAO checkpoint model to resume training, if any

At most, one pretrain_model_path, resume_model_path, and pruned_model_path may be present.

String

pruned_model_path

The path to the TAO pruned model for re-training, if any

At most, one pretrain_model_path, resume_model_path, and pruned_model_path may be present.

String

max_queue_size

The number of prefetch batches in data loading

Unsigned int, positive

n_workers

The number of workers for data loading per GPU

Unsigned int, positive

use_multiprocessing

Whether to use multiprocessing mode of keras sequence data loader

Boolean

true (in case of deadlock, restart training and use False)

visualizer

Visualization configuration during training

Message type

early_stopping

The parameters for early stopping

Message type

Note

The learning rate is automatically scaled with the number of GPUs used during training, or the effective learning rate is learning_rate * n_gpu.

Visualization during training

Visualization during training is configured by the visualizer parameter. The parameters of it are described in the table below.

Parameter

Description

Data Type and Constraints

Default/Suggested Value

enabled

Boolean flag to enable or disable this feature

bool.

num_images

The maximum number of images to be visualized in TensorBoard.

int.

3

Visualization during training supports 3 types of visualizations, namely: scalar, image and histogram. These types of visualization all leverage the TensorBoard tool. Each type will have a tab in TensorBoard GUI interface. With the scalar tab, it can visualize scalars like loss, learning rate and validation mAP over time(training step). With the image tab, it can visualize augmented images during training, with bounding boxes drawn on the them. With the histogram tab, it can visualize histograms of each layer’s weights and bias of the model being trained.

If the parameter enabled is set to True, then all above visualizations will be enabled. Otherwise, all visualization will be disabled.

The parameter num_images is used to limit the maximum number of images to be visualized on the image tab in TensorBoard.

During the training, visualization can be done anywhere that can access the TensorBoard log directory. Usually the TAO Toolkit containers will map volumes to host machine, so TensorBoard can be called on host machine. The command tensorboard --logdir=/path/to/logs can be used to open the TensorBoard visualization GUI in web browser. Make sure tensorboard is installed before running this command. One can run pip3 install tensorboard to install it if it is not installed in the environment. The /path/to/logs argument is the result directory for training, with the suffix /logs appended.

Early Stopping

The parameters for early stopping are described in the table below.

Parameter

Description

Data Type and Constraints

Default/Suggested Value

monitor

The metric to monitor in order to enable early stopping.

string

loss

patience

The number of checks of monitor value before stopping the training.

int

Positive integers

min_delta

The delta of the minimum value of monitor value below which we regard it as not decreasing.

float

Non-negative floats

Evaluation Config

The evaluation configuration (eval_config) defines the parameters needed for the evaluation either during training or standalone evaluation. Details are summarized in the table below.

Field

Description

Data Type and Constraints

Recommended/Typical Value

average_precision_mode

Average Precision (AP) calculation mode can be either SAMPLE or INTEGRATE. SAMPLE is used as VOC metrics for VOC 2009 or before. INTEGRATE is used for VOC 2010 or after.

ENUM type ( SAMPLE or INTEGRATE)

SAMPLE

matching_iou_threshold

The lowest IoU of the predicted box and ground truth box that can be considered a match

float

0.5

visualize_pr_curve

Boolean flag to enable or disable visualization of Precision-Recall curve.

bool.

Note

The parameter visualize_pr_curve, if set to True, will produce an image of precision-recall curve during the evaluate command, the exact path of the image can be seen in the screen log. By checking the image, we can see each class’s performance regarding the tradeoff between precision and recall.

NMS Config

The NMS configuration (nms_config) defines the parameters needed for the NMS postprocessing. NMS config applies to the NMS layer of the model in training, validation, evaluation, inference, and export. Details are summarized in the table below.

Field

Description

Data Type and Constraints

Recommended/Typical Value

confidence_threshold

Boxes with a confidence score less than confidence_threshold are discarded before applying NMS.

float

0.01

cluster_iou_threshold

The IoU threshold below which boxes will go through the NMS process.

float

0.6

top_k

top_k boxes will be output after the NMS keras layer. If the number of valid boxes is less than k, the returned array will be padded with boxes whose confidence score is 0.

Unsigned int

200

infer_nms_score_bits

The number of bits to represent the score values in NMS plugin in TensorRT OSS. The valid range is integers in [1, 10]. Setting it to any other values will make it fall back to ordinary NMS. Currently this optimized NMS plugin is only available in FP16 but it should also be selected by INT8 data type as there is no INT8 NMS in TensorRT OSS and hence this fastest implementation in FP16 will be selected. If falling back to ordinary NMS, the actual data type when building the engine will decide the exact precision(FP16 or FP32) to run at.

int. In the interval [1, 10].

0

Augmentation Config

The augmentation configuration (augmentation_config) defines the parameters needed for online data augmentation. Details are summarized in the table below.

Field

Description

Data Type and Constraints

Recommended/Typical Value

hue

Image hue to be changed within [-hue, hue] * 180.0

float of [0, 1]

0.1

saturation

Image saturation to be changed within [1.0 / saturation, saturation] times

float >= 1.0

1.5

exposure

Image exposure to be changed within [1.0 / exposure, exposure] times

float >= 1.0

1.5

vertical_flip

The probability of images to be vertically flipped

float of [0, 1]

0

horizontal_flip

The probability of images to be horizontally flipped

float of [0, 1]

0.5

jitter

The maximum jitter allowed in augmentation; “jitter” here refers to jitter augmentation in YOLO networks

float of [0, 1]

0.3

output_width

The base output image width of augmentation pipeline

integer, multiple of 32

output_height

The base output image height of augmentation pipeline

integer, multiple of 32

output_channel

The number of output channels of augmentation pipeline

1 or 3

randomize_input_shape_period

The batch interval to randomly change the output width and height. For value K, the augmentation pipeline will adjust output shape per K batches, and the adjusted output width/height will be within 0.6 to 1.5 times of the base width/height.

Note: If K=0, the output width/height will always be the exact base width/height as configured, and training will be much faster. But the accuracy of the trained network might not be as good.

non-negative integer

10

mosaic_prob

The probability of mosaic augmentation to be applied on one image

float of [0, 1]

0.5

mosaic_min_ratio

The minimum ratio of width/height one sub-image should occupy

float of (0, 0.5)

0.2

image_mean

A key/value pair to specify image mean values. If omitted, ImageNet mean will be used for image preprocessing. If set, depending on output_channel, either ‘r/g/b’ or ‘l’ key/value pair must be configured.

dict

Dataset Config

YOLOv4-tiny supports two data formats: the sequence format (images folder and raw labels folder with KITTI format) and the tfrecords format (images folder and TFRecords). From our experience, if mosaic augmentation is disabled (mosaic_prob=0), training with TFRecords format is faster. If mosaic augmentation is enabled (mosaic_prob>0), training with sequence format is faster. The train and evaluate command will determine the data format based on your dataset_config.

The YOLOv4-tiny dataloader assumes the training/validation split is already done and the data is prepared in KITTI format: images and labels are in two separate folders, where each image in the image folder has a .txt label file with the same filename in the label folder, and the label file content follows KITTI format. The COCO data format is supported but only through TFRecords. Prepare the TFRecords using dataset_convert.

Sequence format

The following is an example dataset_config element if you want to use sequence format:

dataset_config {
   data_sources: {
       label_directory_path: "/workspace/tao-experiments/data/training/label_2"
       image_directory_path: "/workspace/tao-experiments/data/training/image_2"
   }
   data_sources: {
       label_directory_path: "/workspace/tao-experiments/data/training/label_3"
       image_directory_path: "/workspace/tao-experiments/data/training/image_3"
   }
   include_difficult_in_training: true
   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_data_sources: {
       label_directory_path: "/workspace/tao-experiments/data/val/label_1"
       image_directory_path: "/workspace/tao-experiments/data/val/image_1"
   }
}

The parameters in dataset_config are defined as follows:

  • data_sources: The path to datasets to train on. If you have multiple data sources for training, you may use multiple data_sources. This field contains 2 parameters:

    • label_directory_path: The path to the data source label folder.

    • image_directory_path: The path to the data source image folder.

  • include_difficult_in_training: A flag specifying whether to include difficult boxes in training. If set to false, difficult boxes will be ignored. Difficult boxes are those with non-zero occlusion levels in KITTI labels.

  • target_class_mapping: This parameter maps the class names in the labels to the target class to be trained in the network. An element is defined for every source class to target class mapping. This field was included with the intention of grouping similar class objects under one umbrella. For example, “car”, “van”, “heavy_truck”, etc. may be grouped under “automobile”. The “key” field is the value of the class name in the tfrecords file, and the “value” field corresponds to the value that the network is expected to learn.

  • validation_data_sources: Captures the path to datasets to validate on. If you have multiple data sources for validation, you may use multiple validation_data_sources. Like data_sources, this field contains two parameters.

Note

The class names key in the target_class_mapping must be identical to the one shown in the KITTI labels so that the correct classes are picked up for training.

TFRecords format

TFRecords format requires tfrecords for all labels. This requires running of tao yolo_v4_tiny dataset-convert command. The command has same functionality and argument requirements as that of detectnet_v2 and for details of how to generate tfrecords, check Pre-processing the Dataset in detectnet_v2.

The following is an example dataset_config element if you want to use tfrecords format that was converted from KITTI data format. Here, we assume your tfrecords are all generated under a folder called tfrecords, which is under same parent folder with images and labels:

dataset_config {
   data_sources: {
       tfrecords_path: "/workspace/tao-experiments/data/training/tfrecords/<tfrecords pattern>"
       image_directory_path: "/workspace/tao-experiments/data/training"
   }
   include_difficult_in_training: true
   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_data_sources: {
       tfrecords_path: "/workspace/tao-experiments/data/val/tfrecords/<tfrecords pattern>"
       image_directory_path: "/workspace/tao-experiments/data/val"
   }
}

The parameters in dataset_config are defined as follows:

  • data_sources: The path to datasets to train on. If you have multiple data sources for training, you may use multiple data_sources. This field contains 2 parameters:

    • tfrecords_path: The path to the data source tfrecords.

    • image_directory_path: The path to the root directory containing the image folder.

  • image_extension: Image extensions of images contained in the image folder. Note, to use tfrecords format, all images must have same extensions and currently we support jpg and png

  • validation_data_sources: Captures the path to datasets to validate on. This field contains two parameters same as data_sources. If you have multiple data sources for validation, you may use multiple validation_data_sources.

All other fields are same as those in sequence format dataset_config.

YOLO4 Config

The YOLOv4 configuration (yolov4_config) defines the parameters needed for building the YOLOv4-tiny model. Details are summarized in the table below.

Field

Description

Data Type and Constraints

Recommended/Typical Value

big_anchor_shape, mid_anchor_shape, and small_anchor_shape

These settings should be 1-d arrays inside quotation marks. The elements of those arrays are tuples representing the pre-defined anchor shape in the order of “width, height”.

The default YOLOv4 configuration has nine predefined anchor shapes. They are divided into three groups corresponding to big, medium, and small objects. The detection output corresponding to different groups are from different depths in the network. You should run the kmeans command (tao yolo_v4_tiny kmeans) to determine the best anchor shapes for your dataset and put those anchor shapes in the spec file. It is worth noting that the number of anchor shapes for any field is not limited to three; you only need to specify one anchor shape in each of those three fields. For YOLOv4-tiny, if using cspdarknet_tiny arch, only big_anchor_shape and mid_anchor_shape should be provided; if using cspdarknet_tiny_3l arch, all 3 shapes should be provided.

string

Use the tao yolo_v4_tiny kmeans command to generate those shapes

box_matching_iou

This field should be a float number between 0 and 1. Any anchor with at least this IoU to any ground truth boxes will be matched to the ground truth box it has the largest IoU with. In contrast with YOLOv3, one ground truth box might match to multiple anchors in YOLOv4-tiny.

float

0.5

matching_neutral_box_iou

This field should be a float number between 0.25 and 1. Any inferred bounding box with at least this IoU to any ground truth boxes will not be treated as negative box and will be assigned 0 for its negative objectiveness loss (neutral box)

float

0.5

loss_loc_weight, loss_neg_obj_weights, and loss_class_weights

These loss weights can be configured as float numbers.

The YOLOv4-tiny loss is a summation of localization loss, negative objectiveness loss, positive objectiveness loss, and classification loss. These weights should be set to all 1.

float

loss_loc_weight: 1.0 loss_neg_obj_weights: 1.0 loss_class_weights: 1.0

label_smoothing

Label smoothing applied to classification loss.

float of [0, 0.3]

0, 0.1, 0.2

big_grid_xy_extend, mid_grid_xy_extend, and small_grid_xy_extend

These settings should be small positive floats. The calculated box center relative to the anchor box will be re-calibrated according to following:

center_xy = calculated_xy * (grid_xy_extend + 1.0) - grid_xy_extend / 2.0

The default YOLOv4-tiny has nine predefined anchor shapes. They are divided into three groups corresponding to big, medium, and small objects. The detection output corresponding to different groups are from different depths in the network. The three different grid_xy_extend configs allow users to define different grid_xy_extend values for different anchor-shape groups. For YOLOv4-tiny, if using cspdarknet_tiny arch, to align with anchor shapes, only big_grid_xy_extend and mid_grid_xy_extend should be provided; if using cspdarknet_tiny_3l arch, all of them should be provided. The grid_xy_extend settings make it easier for the network to propose an inferenced box with a center that is close to or on the anchor border.

float of [0, 0.3]

0.05, 0.1, 0.2

arch

The backbone for feature extraction. For YOLOv4-tiny, only cspdarknet_tiny and cspdarknet_tiny_3l are supported. The former arch has two heads(stride 8 and 16), while the latter has three heads(stride 8, 16, and 32).

string

cspdarknet_tiny

freeze_bn

A flag specifying whether to freeze all batch normalization layers during training.

Boolean

False

freeze_blocks

The list of block IDs to be frozen in the model during training. You can choose to freeze some of the CNN blocks in the model to make the training more stable and/or easier to converge. The definition of a block is heuristic for a specific architecture (for example, by stride or by logical blocks in the model). However, the block ID numbers identify the blocks in the model in a sequential order so you don’t have to know the exact locations of the blocks when you do training. A general principle to keep in mind is that the smaller the block ID, the closer it is to the model input; the larger the block ID, the closer it is to the model output. For YOLOv4-tiny, it should be a subset of {0, 1, 2, 3, 4, 5}.

list(repeated integers), should be subset of {0, 1, 2, 3, 4, 5}

force_relu

A flag specifying whether to replace all activation functions with ReLU. This is useful for training models for NVDLA.

Boolean

False

Generate anchor shape

The anchor shape should match most ground truth boxes in the dataset to help the network learn bounding boxes. The YOLOv4 paper proposes using the kmeans algorithm to get the anchor shapes, and the tao yolo_v4_tiny kmeans command is implemented in the TAO algorithm. You should use the output as your anchor shape in the yolov4_config spec file.

tao yolo_v4_tiny kmeans [-h] -l <label_folders>
                        -i <image_folders>
                        -x <network base input width>
                        -y <network base input height>
                        [-n <num_clusters>]
                        [--max_steps <kmeans max steps>]
                        [--min_x <ignore boxes with width less than this value>]
                        [--min_y <ignore boxes with height less than this value>]

Required Arguments

  • -l: Paths to the training label folders. Multiple folder paths should be separated with spaces.

  • -i: Paths to corresponding training image folders. Folder counts and orders must match label folders.

  • -x: The base network input width. This should be the output_width in the augmentation config part of your spec file.

  • -y: The base network input height. This should be the output_height in the augmentation config part of your spec file.

Optional Arguments

  • -n: The number of shape clusters. This defines how many shape centers the command will output. The default is 9 (3 per group and 3 groups).

  • --max_steps: The max number of steps the kmeans algorithm should run. If the algorithm does not converge at this step, a suboptimal result will be returned. The default value is 10000.

  • --min_x: Ignore ground truth boxes with width less than this value in a reshaped image (images are first reshaped to network base shape as -x, -y).

  • --min_y: Ignore ground truth boxes with height less than this value in a reshaped image (images are first reshaped to network base shape as -x, -y).

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

Training the Model

Train the YOLOv4-tiny model using this command:

tao yolo_v4_tiny train [-h] -e <experiment_spec>
                       -r <output_dir>
                       -k <key>
                       [--gpus <num_gpus>]
                       [--gpu_index <gpu_index>]
                       [--use_amp]
                       [--log_file <log_file_path>]

Required Arguments

  • -r, --results_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: The number of GPUs to use for training in a multi-GPU scenario (default: 1).

  • --gpu_index: The GPU indices used to run the training. You can specify the indices of GPUs to use for training when the machine has multiple GPUs installed.

  • --use_amp: A flag to enable AMP training.

  • --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 = 1 or 3, W >= 128, H >= 128, W, H are multiples of 32)

  • Image format: JPG, JPEG, PNG

  • Label format: KITTI detection

Sample Usage

Here’s an example of using the train command on a YOLOv4-tiny model:

tao yolo_v4_tiny train --gpus 2 -e /path/to/spec.txt -r /path/to/result -k $KEY

Evaluating the Model

To run evaluation on a YOLOv4-tiny model, use this command:

tao yolo_v4_tiny 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-specification file.

  • -m, --model: The path to the model file to use for evaluation. The model can be either a .tlt model file or TensorRT engine.

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

Optional Arguments

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

  • --gpu_index: The GPU index used to run the evaluation. You can specify the index of a GPU to run evaluation 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. The default path is stdout.

Running Inference on a YOLOv4-tiny Model

The inference tool for YOLOv4-tiny networks, which may be used to visualize bboxes or generate frame-by-frame KITTI format labels on a single image or a directory of images. An example of the command for this tool is shown here:

tao yolo_v4_tiny inference [-h] -i <input directory>
                           -o <output annotated image directory>
                           -e <experiment spec file>
                           -m <model file>
                           -k <key>
                           [-l <output label directory>]
                           [-t <visualization threshold>]
                           [--gpu_index <gpu_index>]
                           [--log_file <log_file_path>]

Required Arguments

  • -m, --model: The path to the trained model (TAO model) or TensorRT engine.

  • -i, --in_image_dir: The directory of input images for inference.

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

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

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

Optional Arguments

  • -t, --draw_conf_thres: Threshold for drawing a bbox. default: 0.3.

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

  • -l, --out_label_dir: The directory to output KITTI labels.

  • --gpu_index: The GPU index used to run the inference. We can specify the GPU index used to run evaluation 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. The default path is stdout.

Pruning the Model

Pruning removes parameters from the model to reduce the model size without compromising the integrity of the model itself using the tao yolo_v4_tiny prune command.

The tao yolo_v4_tiny prune command includes these parameters:

tao yolo_v4_tiny prune [-h] -m <pretrained_model>
                       -o <output_file>
                       -k <key>
                       [-n <normalizer>]
                       [-eq <equalization_criterion>]
                       [-pg <pruning_granularity>]
                       [-pth <pruning threshold>]
                       [-nf <min_num_filters>]
                       [-el [<excluded_list>]

Required Arguments

  • -m, --model: The path to pretrained YOLOv4-tiny model

  • -o, --output_file: The path to the output checkpoints

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

Optional Arguments

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

  • -n, –normalizer: Use max to normalize by dividing each norm by the maximum norm within a layer; use L2 to normalize by dividing by the L2 norm of the vector comprising all kernel norms. The default value is 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 MoblieNets. Options are arithmetic_mean, geometric_mean, union, and intersection. The default value is union.

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

  • -pth: The threshold to compare a normalized norm against (default: 0.1)

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

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

After pruning, the model needs to be retrained. See Re-training the Pruned Model for more details.

Using the Prune Command

Here’s an example of using the tao yolo_v4_tiny prune command:

tao yolo_v4_tiny prune -m /workspace/output/weights/cspdarknet_tiny_003.tlt \
                  -o /workspace/output/weights/cspdarknet_tiny_003_pruned.tlt \
                  -eq union \
                  -pth 0.7 -k $KEY

Re-training the Pruned Model

Once the model has been pruned, there might be a slight decrease in accuracy because some previously useful weights may have been removed. To regain accuracy, we recommend retraining the pruned model over the same dataset. To do this, use the tao yolo_v4_tiny train command as documented in Training the model, with an updated spec file that points to the newly pruned model as the pruned_model_path.

We recommend turning off the regularizer in the training_config for detectnet to recover the accuracy when retraining a pruned model. You may do this by setting the regularizer type to NO_REG as mentioned in the Training Config section. All other parameters in the spec file can be carried over from the previous training.

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 .tlt, the .etlt model format is also an encrypted model format with the same key of 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. If tao yolo_v4_tiny export is run with the --data_type flag set to int8, the calibration cache is generated using a calibration tensor file. 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 depending on the size of the Tensorfile and the model itself.

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

  • Option 1: Using 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: Pointing 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 that is required is to provide a .tlt model from the training/retraining step to be converted into .etlt.

Exporting the Model

Here’s an example of the command line arguments of the tao yolo_v4_tiny export command:

tao yolo_v4_tiny export [-h]
                    -m <path to the .tlt model file generated by tao train>
                    -k <key>
                    [-o <path to output file>]
                    [--cal_json_file <path to calibration json file>]
                    [--experiment_spec <path to experiment spec file>]
                    [--gen_ds_config]
                    [--verbose]
                    [--gpu_index <gpu_index>]
                    [--log_file <log_file_path>]

Required Arguments

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

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

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

Optional Arguments

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

  • -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.

QAT Export Mode Required Arguments

  • --cal_json_file: The path to the json file containing tensor scale for QAT models. This argument is required if engine for QAT model is being generated.

Note

When exporting a model trained with QAT enabled, the tensor scale factors to calibrate the activations are peeled out of the model and serialized to a JSON file defined by the cal_json_file argument.

Sample usage

The following is a sample command to export a YOLOv4-tiny model:

tao yolo_v4_tiny export -m /workspace/yolov4_cspdarknet_tiny_epoch_100.tlt  \
                         -o /workspace/yolov4_cspdarknet_tiny_epoch_100_int8.etlt \
                         -e /workspace/yolov4_retrain_cspdarknet_tiny_kitti.txt \
                         -k $KEY \

TensorRT engine generation, validation, and int8 calibration

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

Deploying to DeepStream

For deploying to deep stream, please refer to Deploying to DeepStream for YOLOv4.