EfficientDet (TF1)

With EfficientDet, the following tasks are supported:

• dataset_convert

• train

• evaluate

• prune

• inference

• export

These tasks may be invoked from the TAO Toolkit Launcher by following the below convention from command line:

            

            
tao model efficientdet_tf1 <sub_task> <args_per_subtask>
        

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

EfficientDet expects directories of images for training or validation and annotated JSON files in COCO format.

The raw image data and 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 model efficientdet_tf1 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 annotations 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 ground truth during conversion. The default value is False.

• -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 a dataset:

            

            
tao model efficientdet_tf1 dataset_convert -i /path/to/image_dir
                                 -a /path/to/train.json
                                 -o /path/to/output_dir
        

Below is a sample for the EfficientDet spec file. It has 5 major components: model_config, training_config, eval_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.

            

            
training_config {
  train_batch_size: 16
  iterations_per_loop: 10
  checkpoint_period: 10
  num_examples_per_epoch: 14700
  num_epochs: 300
  model_name: 'efficientdet-d0'
  profile_skip_steps: 100
  tf_random_seed: 42
  lr_warmup_epoch: 5
  lr_warmup_init: 0.00005
  learning_rate: 0.1
  amp: True
  moving_average_decay: 0.9999
  l2_weight_decay: 0.00004
  l1_weight_decay: 0.0
  checkpoint: "/path/to/your/pretrained_model"
  # pruned_model_path: "/path/to/your/pruned/model"
}
dataset_config {
  num_classes: 91
  image_size: "512,512"
  training_file_pattern: "/path/to/coco/train-*"
  validation_file_pattern: "/path/to/coco/val-*"
  validation_json_file: "/path/to/coco/annotations/instances_val2017.json"
}
eval_config {
  eval_batch_size: 16
  eval_epoch_cycle: 10
  eval_after_training: True
  eval_samples: 5000
  min_score_thresh: 0.4
  max_detections_per_image: 100
}
model_config {
  model_name: 'efficientdet-d0'
  min_level: 3
  max_level: 7
  num_scales: 3
}
augmentation_config {
  rand_hflip: True
  random_crop_min_scale: 0.1
  random_crop_max_scale: 2.0
}
        

The top level structure of the spec file is summarized in the following tables:

Training Config

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

Evaluation Config

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

Dataset 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.

Model Config

The model configuration (model_config) specifies the model structure. A detailed description is summarized in the table below.

Augmentation Config

The augmentation_config parameter defines image augmentation after preprocessing.

Train the EfficientDet model using this command:

            

            
tao model efficientdet_tf1 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: The number of GPUs to be used for training in a multi-GPU scenario. The default value is 1.

• --gpu_index: The indices of the GPUs to use for training. This argument can be used when the machine has multiple GPUs installed.

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

• Label format: COCO detection

Sample Usage

Here’s an example of the train command:

            

            
tao model efficientdet_tf1 train --gpus 2 -e /path/to/spec.txt -d /path/to/result -k $KEY
        

To run evaluation with an EfficientDet model, use this command:

            

            
tao model efficientdet_tf1 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_path: The path to the model file to use for evaluation (only TAO models are supported)

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

Optional Arguments

• --gpu_index: The index of the GPU to use for evaluation. This argument can be used 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 value is stdout.

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

Sample Usage

Here’s an example of using the evaluate command:

            

            
tao model efficientdet_tf1 evaluate -e /path/to/spec.txt -m /path/to/model.tlt -k $KEY
        

The inference tool for EfficientDet models can be used to visualize bboxes and generate frame-by- frame KITTI format labels on a directory of images.

            

            
tao model efficientdet_tf1 inference [-h] -i <input directory>
                                -o <output annotated image directory>
                                -e <experiment spec file>
                                -m <model file>
                                -k <key>
                                [-l <output label directory>]
                                [--gpu_index <gpu_index>]
                                [--log_file <log_file_path>]
        

Required Arguments

• -m, --model_path: The path to the pretrained model (supports both the TAO model and TensorRT engine)

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

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

• -k, --key: The key to load a TAO model (this argument is not required if a TensorRT engine is used)

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

Optional Arguments

• -l, --out_label_path: The directory to output KITTI labels

• --label_map: The path to a text file of training labels

• --gpu_index: The index of the GPU to run inference on. This argument can be used when the machine has multiple GPUs installed. Note that inference can only run on a single GPU.

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

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

Sample Usage

Here’s an example of using the inference command:

            

            
tao model efficientdet_tf1 inference -e /path/to/spec.txt -m /path/to/model.tlt -k $KEY
                           -o /path/to/output_dir -i /path/to/input_dir
        

The tao model efficientdet_tf1 prune command removes parameters from the model to reduce the model size without compromising the integrity of the model itself.

The tao model efficientdet_tf1 prune command includes these parameters:

            

            
tao model efficientdet_tf1 prune [-h] -m <efficientdet 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_path>]
        

Required Arguments

• -m, --model: The path to a pretrained EfficientDet model.

• -o, --output_dir: The path to output checkpoints.

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

Optional Arguments

• -n, –normalizer: Specify max to normalize by dividing each norm by the maximum norm within a layer; specify L2 to normalize by dividing by the L2 norm of the vector comprising all kernel norms. The default value is max.

• -eq, --equalization_criterion: The 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 include arithmetic_mean geometric_mean, union, and intersection. The default option is union.

• -pg, -pruning_granularity: The number of filters to remove at a time. The default value is 8.

• -pth: The threshold to compare the normalized norm against. The default value is 0.1.

  Note

  NVIDIA recommends changing the threshold to keep the number of parameters in the model to within 10-20% of the original unpruned model.

• -nf, --min_num_filters: The minimum number of filters to keep per layer. The default value is 16.

• -el, --excluded_layers: A list of excluded layers (e.g. “-i item1 item2”). The default value is [].

• --gpu_index: The index of the GPU to run pruning on. This argument can be used when the machine has multiple GPUs installed. Note that inference can only run on a single GPU.

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

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

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 efficientdet_tf1 prune command:

            

            
tao model efficientdet_tf1 prune -m /path/to/model.step-0.tlt \
                       -o /path/to/pruned_model/ \
                       -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 this pruned model over the same dataset. To do this, use the tao model efficientdet_tf1 train command, as documented in Training the Model, with an updated spec file that points to the newly pruned model as the pretrained model file.

We recommend turning off the regularizer or reducing the weight decay in the training_config for EfficientDet to recover the accuracy when retraining a pruned model. To do this, set the regularizer type to NO_REG, as documented in the Training config section. The other parameters may be retained in the spec file from the previous training.

Exporting the model decouples the training process from deployment 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. The .etlt model format is also 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.

Exporting the EfficientDet Model

Here’s an example of the command line arguments of the tao model efficientdet_tf1 export command:

            

            
tao model efficientdet_tf1 export [-h]  -m <path to the .tlt model file>
                              -e <path to experiment spec file>
                              -k <key>
                              [-o <path to output file>]
                              [--gpu_index <gpu_index>]
                              [--log_file <log_file_path>]
                              [--verbose]
        

Required Arguments

• -m, --model_path: 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

• -o, --output_path: The path to save the exported model

Sample usage

Here’s a sample command to export an EfficientDet model to a .etlt file.

            

            
tao model efficientdet_tf1 export -m /path/to/model.step-0.tlt  \
                        -o /path/to/export/model.step-0.etlt \
                        -e /ws/spec.txt \
                        -k $KEY
        

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

For deploying to DeepStream, refer to the Integrating an EfficientDet (TF1/TF2) Model page.