EfficientDet (TF2)

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:

Copy
Copied!

tao efficientdet_tf2 <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.

Data Input for EfficientDet

EfficientDet expects directories of images for training or validation and annotation JSON files in COCO format. See the Data Annotation Format page for more information about the data format for EfficientDet.

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:

Copy
Copied!

tao efficientdet_tf2 dataset-convert [-h] -e <conversion spec file>


Below is a sample for the data conversion spec file. The format of the spec file is YAML with configuration parameters under the scopre of dataset_convert.

Copy
Copied!

dataset_convert:
image_dir: '/workspace/tao-experiments/data/raw-data/train2017/'
annotations_file: '/workspace/tao-experiments/data/raw-data/annotations/instances_train2017.json'
output_dir: '/workspace/tao-experiments/data'
tag: 'train'
num_shards: 256
include_masks: True


The details of each parameter are summarized in the table below:

 Field Description Data Type and Constraints Recommended/Typical Value image_dir The path to the directory where raw images are stored String – annotations_file The path to the annotation JSON file String – output_dir The output directory where TFRecords are saved String – tag The number of shards for the converted TFRecords Integer 256 num_shards The path to a TAO pruned model for re-training, if any String – include_mask Whether to include segmentation groundtruth during conversion Boolean False
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:

Copy
Copied!

tao efficientdet_tf2 dataset_convert -i /path/to/convert.yaml


Creating a Configuration File

Below is a sample for the EfficientDet spec file. It has 8 major components: data, model, train, evaluate, inference, augment, prune and export config as well as mandatory parameters for the encryption key (key) and results directory (results_dir).

Copy
Copied!

data:
prefetch_size: 4
shuffle_file: False
shuffle_buffer: 10000
cycle_length: 32
block_length: 16
max_instances_per_image: 100
skip_crowd_during_training: True
image_size: '512x512'
num_classes: 91
train_tfrecords:
- '/datasets/coco/train-*'
val_tfrecords:
- '/datasets/coco/val-*'
val_json_file: '/datasets/coco/annotations/instances_val2017.json'
train:
optimizer:
name: 'sgd'
momentum: 0.9
lr_schedule:
name: 'cosine'
warmup_epoch: 5
warmup_init: 0.0001
learning_rate: 0.2
amp: True
checkpoint: "/weights/efficientnet-b0_500.eff"
num_examples_per_epoch: 100
moving_average_decay: 0.999
batch_size: 20
checkpoint_interval: 5
l2_weight_decay: 0.00004
l1_weight_decay: 0.0
image_preview: True
qat: False
random_seed: 42
pruned_model_path: ''
num_epochs: 200
model:
name: 'efficientdet-d0'
aspect_ratios: '[(1.0, 1.0), (1.4, 0.7), (0.7, 1.4)]'
anchor_scale: 4
min_level: 3
max_level: 7
num_scales: 3
freeze_bn: False
freeze_blocks: []
augment:
rand_hflip: True
random_crop_min_scale: 0.1
random_crop_max_scale: 2
auto_color_distortion: False
auto_translate_xy: False
evaluate:
batch_size: 8
num_samples: 5000
max_detections_per_image: 100
model_path: ''
export:
max_batch_size: 8
dynamic_batch_size: True
min_score_thresh: 0.4
model_path: ""
output_path: ""
inference:
model_path: ""
image_dir: ""
output_dir: ""
dump_label: False
batch_size: 1
prune:
model_path: ""
normalizer: 'max'
output_path: ""
equalization_criterion: 'union'
granularity: 8
threshold: 0.5
min_num_filters: 16
excluded_layers: []
key: 'nvidia_tlt'
results_dir: '/workspace/results_dir'


The format of the spec file is YAML. The top level structure of the spec file is summarized in the table below:

 Field Description data Configuration related to data sources and dataloader model Configuration related to model construction augment Configuration related to data augmentation during training train Configuration related to the training process evaluate Configuration related to the standalone evaluation process prune Configuration for pruning a trained model inference Configuration for running model inference export Configuration for exporting a trained model key Global encryption key results_dir Directory where experiment results and status logging are saved

Training Config

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

 Field Description Data Type and Constraints Recommended/Typical Value batch_size The batch size for each GPU, so the effective batch size is batch_size_per_gpu * num_gpus. Unsigned int, positive 16 num_epochs The number of epochs to train the network Unsigned int, positive 300 num_examples_per _epoch Total number of images in the training set Unsigned int, positive – checkpoint The path to the pretrained model, if any String – pruned_model_path The path to a TAO pruned model for re-training, if any String – checkpoint_interval The number of training epochs that should run per model checkpoint/validation Unsigned int, positive 10 amp Whether to use mixed precision training Boolean – moving_average_decay Moving average decay Float 0.9999 l2_weight_decay L2 weight decay Float – l1_weight_decay L1 weight decay Float – random_seed Random seed Unsigned int, positive 42 clip_gradients_norm Clip gradients by the norm value Float 5 qat Enabled quantization aware training Boolean False optimizer Optimizer configuration lr_schedule Learning rate scheduler configuration

The optimizer configuration(train.optimizer) specifies the type and parameters of an optimizer. +———————+——————————————————————————————————-+——————————-+————————————————————————————–+ | Field | Description | Data Type and Constraints | Recommended/Typical Value | +———————+——————————————————————————————————-+——————————-+————————————————————————————–+ | name | Optimizer name (only sgd is supported) | String | ‘sgd’ | +———————+——————————————————————————————————-+——————————-+————————————————————————————–+ | momentum | Momentum | float | 0.9 | +———————+——————————————————————————————————-+——————————-+————————————————————————————–+

The learning rate scheduler configuration(train.lr_schedule) specifies the type and parameters of a learning rate scheduler. +———————+——————————————————————————————————-+——————————-+————————————————————————————–+ | Field | Description | Data Type and Constraints | Recommended/Typical Value | +———————+——————————————————————————————————-+——————————-+————————————————————————————–+ | name | The name of the learning rate scheduler. Available options are cosine and soft_anneal | String | ‘cosine’ | +———————+——————————————————————————————————-+——————————-+————————————————————————————–+ | warmup_epoch | The number of warmup epochs in the learning rate schedule | Unsigned int, positive | – | +———————+——————————————————————————————————-+——————————-+————————————————————————————–+ | warmup_init | The initial learning rate in the warmup period | Float | – | +———————+——————————————————————————————————-+——————————-+————————————————————————————–+ | learning_rate | The maximum learning rate | Float | – | +———————+——————————————————————————————————-+——————————-+————————————————————————————–+

Evaluation Config

The evaluation configuration (evaluate) 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 model_path The path to the model to be evaluated String – max_detections_per_image The maximum number of detections to visualize Unsigned int, positive 100 batch_size The batch size for each GPU, so the effective batch size is batch_size_per_gpu * num_gpus Unsigned int, positive 16 num_samples The number of samples for evaluation Unsigned int – label_map YAML file that stores index to label name mapping. (Optional) If set, per class AP metric will be calculated String – start_eval_epoch Evaluation will not start until this epoch (Default: 1) Unsigned int –

Inference Config

The inference configuration (inference) defines the parameters needed for the standalone inference with the trained .tlt model. Details are summarized in the table below.

 Field Description Data Type and Constraints Recommended/Typical Value model_path The path to the model to run inference with String – image_dir The path to the image directory String – output_dir The path to the output directory where annotated images will be saved String – dump_label Whether to dump label files in KITTI format Boolean – batch_size Batch size to run inference with Unsigned int – min_score_thresh Minimum confidence threshold to render the predicted bounding boxes String – label_map YAML file that stores index to label name mapping (Optional) If set, annotated images will have class labels associated with bounding boxes String – max_boxes_to_draw The maximum number of bounding boxes that will be rendered in the annotated images String –

Dataset Config

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

 Field Description Data Type and Constraints Recommended/Typical Value image_size The image dimension in “WxH” format, where W and H indicates the dimension of the resized and padded input. String “512x512” train_tfrecords The TFRecord path for training String – val_tfrecords 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 – max_instances_per_image The maximum number of object instances to parse (default: 100) Unsigned int 100 skip_crowd_during_training Specifies whether to skip crowd during training Boolean True loader Data loader configuration

The dataloader configuration (data.loader) specifies how batches of data are fed into the model.

 Field Description Data Type and Constraints Recommended/Typical Value prefetch_size The image dimension in “WxH” format, where W and H indicates the dimension of the resized and padded input. String “512x512” shuffle_file The TFRecord path for training String – shuffle_buffer The image dimension in “WxH” format, where W and H indicates the dimension of the resized and padded input. String “512x512” cycle_length The TFRecord path for training String – block_length The TFRecord path for training String –

Model Config

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

 Field Description Data Type and Constraints Recommended/Typical Value model_name EfficientDet model name string “efficientdet_d0” min_level The minimum level of the output feature pyramid Unsigned int 3 (only 3 is supported) max_level The maximum level of the output feature pyramid Unsigned int 7 (only 7 is supported) 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 3 max_instances_per_image The maximum number of object instances to parse (default: 100) Unsigned int 100 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 4

Augmentation Config

The augment configuration specifies the image augmentation methods used after preprocessing.

 Field Description Data Type and Constraints Recommended/Typical Value rand_hflip Whether to perform random horizontal flip Boolean – random_crop_min_scale The minimum scale of RandomCrop augmentation. Default: 0.1 Float 0.1 random_crop_max_scale The maximum scale of RandomCrop augmentation. Default: 2.0 Float 2.0 auto_color_distortion Whether to enable automatic color augmentation Boolean False auto_translate_xy Whether to enable automatic image translation in X/Y axis Boolean False

Pruning Config

The prune configuration defines the pruning process for a trained model. A detailed description is summarized in the table below.

 Field Description Data Type and Constraints Recommended/Typical Value normalizer Normalization method. Specify max to normalize by dividing each norm by the maximum norm within a layer or L2 to normalize by dividing by the L2 norm of the vector comprising all kernel norms String max equalization_criterion The criteria to equalize the stats of inputs to an element-wise op layer or depth-wise conv layer. Options are arithmetic_mean geometric_mean,union, and intersection. String union granularity The number of filters to remove at a time Integer 8 threshold Pruning threshold Float – min_num_filters The minimum number of filters to keep per layer. Default: 16 Integer 16 excluded_layers A list of layers to be excluded from pruning List – model_path The path to the .tlt model file to be pruned String –

Export Config

The export configuration contains the parameters of exporting a .tlt model to .etlt model, which can be used for deployment.

 Field Description Data Type and Constraints Recommended/Typical Value max_batch_size The maximum batch size of the .etlt model if dynamic_batch_size is set to False Boolean – dynamic_batch_size Whether to use dynamic batch size in the exported .etlt model Boolean True model_path The path to the .tlt model file to be exported String – output_path The path to save the exported .etlt model String False

Training the Model

Train the EfficientDet model using this command:

Copy
Copied!

tao efficientdet_tf2 train [-h] -e <experiment_spec>
[--gpus <num_gpus>]
[--gpu_index <gpu_index>]
[--log_file <log_file_path>]


Required Arguments

• -e, --experiment_spec: The experiment specification file to set up the training experiment.

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:

Copy
Copied!

tao efficientdet_tf2 train --gpus 2 -e /path/to/spec.yaml


Evaluating the Model

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

Copy
Copied!

tao efficientdet_tf2 evaluate [-h] -e <experiment_spec>
[--gpu_index <gpu_index>]
[--log_file <log_file_path>]


Required Arguments

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

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:

Copy
Copied!

tao efficientdet_tf2 evaluate -e /path/to/spec.yaml


Running Inference with an EfficientDet Model

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.

Copy
Copied!

tao efficientdet_tf2 inference [-h] -e <experiment spec file>
[--gpu_index <gpu_index>]
[--log_file <log_file_path>]


Required Arguments

• -e, --experiment_spec: The path to an experiment spec file

Optional Arguments

• --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:

Copy
Copied!

tao efficientdet_tf2 inference -e /path/to/spec.yaml


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 efficientdet_tf2 prune command.

The tao efficientdet_tf2 prune command includes these parameters:

Copy
Copied!

tao efficientdet_tf2 prune [-h] -e <experiment spec file>
[--gpu_index <gpu_index>]
[--log_file <log_file_path>]


Required Arguments

• -e, --experiment_spec: The path to an experiment spec file

Optional Arguments

• --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: 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.

Note

Due to the complexity of larger EfficientDet models, the pruning process will take significantly longer to finish. For example, pruning the EfficientDet-D5 model may take at least 25 minutes on a V100 server.

Using the Prune Command

Here’s an example of using the tao efficientdet_tf2 prune command:

Copy
Copied!

tao efficientdet_tf2 prune -e /path/to/spec.yaml


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 the accuracy, we recommend that you retrain this pruned model over the same dataset. To do this, use the tao efficientdet_tf2 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 mentioned in the Training config section. All the other parameters may be retained in the spec file from the previous training.

Exporting the Model

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 a model.

Exporting the EfficientDet Model

Here’s an example of the command line arguments of the tao efficientdet_tf2 export command:

Copy
Copied!

tao efficientdet_tf2 export [-h] -e <path to experiment spec>
[--gpu_index <gpu_index>]
[--log_file <log_file_path>]


Required Arguments

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

Optional Arguments

• --gpu_index: The index of (discrete) GPUs used for exporting the model. You can specify the index of the GPU to run export if the machine has multiple GPUs installed. Note that export 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 exits.

Sample usage

Here’s a sample command to export an EfficientDet model in INT8 mode.

Copy
Copied!

tao efficientdet_tf2 export -e /path/to/spec.yaml


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 the Integrating an EfficientDet (TF1/TF2) Model page to learn more about deploying an EfficientDet TF2 model to Deepsteram.

© Copyright 2022, NVIDIA.. Last updated on Jan 23, 2023.