YOLOv4-tiny

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

• dataset_convert

• kmeans

• train

• evaluate

• inference

• prune

• export

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

            

            
tao model 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.

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 model 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.

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.

Visualization during training

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

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 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.

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.

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.

Augmentation Config

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

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.

TFRecords format

TFRecords format requires tfrecords for all labels. This requires running of tao model 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.

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 model 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 model 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.

Train the YOLOv4-tiny model using this command:

            

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

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

            

            
tao model 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.

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

The tao model yolo_v4_tiny prune command includes these parameters:

            

            
tao model 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 model yolo_v4_tiny prune command:

            

            
tao model 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
        

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 model 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 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 model 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 model yolo_v4_tiny export command:

            

            
tao model yolo_v4_tiny export [-h]
                    -m <path to the .tlt model file generated by tao model 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.

Sample usage

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

            

            
tao model 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 \
        

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

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