ExperimentConfig Fields

Field	value_type	description	default_value	valid_min	valid_max	valid_options	automl_enabled
model_name	string	Name of model if invoking task via model_agnostic
encryption_key	string	Key for encrypting model checkpoints
results_dir	string	Path to where all the assets generated from a task are stored	/results
wandb	collection	Configurable parameters to construct the wandb client for a DepthNet experiment					FALSE
dataset	collection	Configurable parameters to construct the dataset for a DepthNet experiment					FALSE
model	collection	Configurable parameters to construct the model for a DepthNet experiment					FALSE
inference	collection	Configurable parameters to construct the inferencer for a DepthNet experiment					FALSE
evaluate	collection	Configurable parameters to construct the evaluator for a DepthNet experiment					FALSE
train	collection	Configurable parameters to construct the trainer for a DepthNet experiment					FALSE
export	collection	Configurable parameters to construct the onnx export for a DepthNet experiment					FALSE
gen_trt_engine	collection	Configurable parameters to construct the TensorRT engine builder for a DepthNet experiment					FALSE

WandBConfig Fields

Field	value_type	description	default_value	valid_min	valid_max	valid_options	automl_enabled
enable	bool		True
project	string		TAO Toolkit
entity	string
tags	list		[‘tao-toolkit’]				FALSE
reinit	bool		FALSE
sync_tensorboard	bool		FALSE
save_code	bool		FALSE
name	string		TAO Toolkit Training
run_id	string

DepthNetDatasetConfig Fields

Field	value_type	description	default_value	valid_min	valid_max	valid_options	automl_enabled
dataset_name	categorical	Dataset name	StereoDataset			MonoDataset,StereoDataset
normalize_depth	bool	Whether to normalize depth	FALSE
max_depth	float	Maximum depth in meters in MetricDepthAnythingV2		1.0	inf
min_depth	float	Minimum depth in meters in MetricDepthAnythingV2		0.0	inf
max_disparity	int	Maximum allowed disparity for which we compute losses during training	416	1	416
baseline	float	Baseline for stereo datasets	0.193001	0.0	inf
focal_x	float	Focal length along x-axis	1998.842	0.0	inf
train_dataset	collection	Configurable parameters to construct the train dataset for a DepthNet experiment					FALSE
val_dataset	collection	Configurable parameters to construct the val dataset for a DepthNet experiment					FALSE
test_dataset	collection	Configurable parameters to construct the test dataset for a DepthNet experiment					FALSE
infer_dataset	collection	Configurable parameters to construct the infer dataset for a DepthNet experiment					FALSE

DepthNetModelConfig Fields

Field	value_type	description	default_value	valid_min	valid_max	valid_options	automl_enabled
model_type	categorical	Network name	MetricDepthAnythingV2			FoundationStereo,MetricDepthAnything,RelativeDepthAnything
mono_backbone	collection	Network defined paths for Monocular DepthNet Backbone					FALSE
stereo_backbone	collection	Network defined paths for Edgenext and Depthanythingv2					FALSE
hidden_dims	list	Hidden dimensions	[128, 128, 128]				FALSE
corr_radius	int	Width of the correlation pyramid	4	1			TRUE
cv_group	int	cv group	8	1			TRUE
train_iters	int	Train iteration	22	1			TRUE
valid_iters	int	Validation iteration	22	1
volume_dim	int	Volume dimension	32	1			TRUE
low_memory	int	reduce memory usage	0	0	4
mixed_precision	bool	Whether to use mixed precision training	FALSE
n_gru_layers	int	Number of hidden GRU levels	3	1	3
corr_levels	int	Number of levels in the correlation pyramid	2	1	2
n_downsample	int	Resolution of the disparity field (1/2^K)	2	1	2
encoder	categorical	DepthAnythingV2 Encoder options	vitl			vits,vitl
max_disparity	int	Maximum disparity of the model used in the training of a stereo model	416

DepthNetInferenceExpConfig Fields

Field	value_type	description	default_value	valid_min	valid_max	valid_options	automl_enabled
num_gpus	int	Number of GPUs to run the inference job.	1	1
gpu_ids	list	List of GPU IDs to run the inference on. The length of this list must be equal to the number of gpus in inference.num_gpus.	[0]				FALSE
num_nodes	int	Number of nodes to run the inference on. If > 1, then multi-node is enabled.	1	1
checkpoint	string	Path to the checkpoint used for inference.	???
trt_engine	string	Path to the TensorRT engine to be used for inference. This only works with tao-deploy.
results_dir	string	Path to where all the assets generated from a task are stored.
batch_size	int	Batch size of the input Tensor. This is important if batch_size > 1 for a large dataset.	-1	-1
conf_threshold	float	Value of the confidence threshold to be used when filtering out the final list of boxes.	0.5
input_width	int	Width of the input image tensor.		1
input_height	int	Height of the input image tensor.		1
save_raw_pfm	bool	Whether to save the raw pfm output during inference.	FALSE

DepthNetEvalExpConfig Fields

Field	value_type	description	default_value	valid_min	valid_max	valid_options	automl_enabled
num_gpus	int	Number of GPUs to run the evaluation job.	1	1
gpu_ids	list	List of GPU IDs to run the evaluation on. The length of this list must be equal to the number of gpus in evaluate.num_gpus.	[0]				FALSE
num_nodes	int	Number of nodes to run the evaluation on. If > 1, then multi-node is enabled.	1	1
checkpoint	string	Path to the checkpoint used for evaluation.	???
trt_engine	string	Path to the TensorRT engine to be used for evaluation. This only works with tao-deploy.
results_dir	string	Path to where all the assets generated from a task are stored.
batch_size	int	Batch size of the input Tensor. This is important if batch_size > 1 for large dataset.	-1	-1
input_width	int	Width of the input image tensor.	736	1
input_height	int	Height of the input image tensor.	320	1

DepthNetTrainExpConfig Fields

Field	value_type	description	default_value	valid_min	valid_max	valid_options	automl_enabled
num_gpus	int	Number of GPUs to run the train job.	1	1
gpu_ids	list	List of GPU IDs to run the training on. The length of this list must be equal to the number of gpus in train.num_gpus.	[0]				FALSE
num_nodes	int	Number of nodes to run the training on. If > 1, then multi-node is enabled.	1	1
seed	int	Seed for the initializer in PyTorch. If < 0, disable fixed seed.	1234	-1	inf
cudnn	collection						FALSE
num_epochs	int	Number of epochs to run the training.	10	1	inf
checkpoint_interval	int	Interval (in epochs) at which a checkpoint is to be saved; helps resume training.	1	1
checkpoint_interval_unit	categorical	Unit of the checkpoint interval.	epoch			epoch,step
validation_interval	int	Interval (in epochs) at which a evaluation will be triggered on the validation dataset.	1	1
resume_training_checkpoint_path	string	Path to the checkpoint from which to resume training.
results_dir	string	Path to where all the assets generated from a task are stored.
checkpoint_interval_steps	int	Number of steps to save the checkpoint.
pretrained_model_path	string	Path to a pretrained DepthNet model from which to initialize the current training.
clip_grad_norm	float	Amount to clip the gradient by L2 Norm. A value of 0.0 specifies no clipping.	0.1
dataloader_visualize	bool	Whether to visualize the dataloader.	FALSE				TRUE
vis_step_interval	int	Visualization interval in step.	10				TRUE
is_dry_run	bool	Whether to run the trainer in Dry Run mode. This serves as a good means to validate the specification file and run a sanity check on the trainer without actually initializing and running the trainer.	FALSE
optim	collection	Hyperparameters to configure the optimizer.					FALSE
precision	categorical	Precision on which to run the training.	fp32			bf16,fp32,fp16
distributed_strategy	categorical	Multi-GPU training strategy. DDP (Distributed Data Parallel) and Fully Sharded DDP are supported.	ddp			ddp,fsdp
activation_checkpoint	bool	Whether train is to recompute in backward pass to save GPU memory (TRUE) or store activations (FALSE).	TRUE
verbose	bool	Whether to display verbose logs to console.	FALSE
inference_tile	bool	Whether to use tiled inference, particularly for transformers which expect fixed size of sequences.	FALSE
tile_wtype	string	Use tiled inference weight type.	gaussian
tile_min_overlap	list	Minimum overlap for tile.	[16, 16]				FALSE
log_every_n_steps	int	Interval steps of logging training results and running validation numbers within one epoch.	500

DepthNetExportExpConfig Fields

Field	value_type	description	default_value	valid_min	valid_max	valid_options	automl_enabled
results_dir	string	Path to where all the assets generated from a task are stored.
gpu_id	int	Index of the GPU to build the TensorRT engine.	0
checkpoint	string	Path to the checkpoint file to run export.	???
onnx_file	string	Path to the onnx model file.	???
on_cpu	bool	Whether to export CPU compatible model.	FALSE
input_channel	ordered_int	Number of channels in the input Tensor.	3	1		1,3
input_width	int	Width of the input image tensor.	960	32
input_height	int	Height of the input image tensor.	544	32
opset_version	int	Operator set version of the ONNX model used to generate TensorRT engine.	17	1
batch_size	int	Batch size of the input Tensor for the engine. A value of -1 implies dynamic tensor shapes.	-1	-1
verbose	bool	Whether to enable verbose TensorRT logging.	FALSE
format	categorical	File format to export to.	onnx			onnx,xdl
valid_iters	int	Number of GRU iterations to export the model.	22	1

DepthNetGenTrtEngineExpConfig Fields

Field	value_type	description	default_value	valid_min	valid_max	valid_options	automl_enabled
results_dir	string	Path to where all the assets generated from a task are stored.
gpu_id	int	Index of the GPU to build the TensorRT engine.	0	0
onnx_file	string	Path to the ONNX model file.	???
trt_engine	string	Path to the TensorRT engine generated should be stored. This only works with tao-deploy.	???
timing_cache	string	Path to a TensorRT timing cache that speeds up engine generation. This will be created/read/updated.
batch_size	int	Batch size of the input tensor for the engine. A value of -1 implies dynamic tensor shapes.	-1	-1
verbose	bool	Whether to enable verbose TensorRT logging.	FALSE
tensorrt	collection	Hyperparameters to configure the TensorRT Engine builder.					FALSE

BaseDepthNetDatasetConfig Fields

Field	value_type	description	default_value	valid_min	valid_max	valid_options	automl_enabled
data_sources	list	List of data sources for training: dataset_name : The type of the dataset data_file : The path of the data file	[{‘dataset_name’: ‘’, ‘data_file’: ‘’}]				FALSE
image_path	string	Path to the image directory for tao-deploy
right_image_path	string	Path to the right image directory for tao-deploy
depth_image_path	string	Path to the depth image directory for tao-deploy
batch_size	int	Natch size for training and validation	1	1	inf		TRUE
workers	int	Number of parallel workers processing data	8	1	inf		TRUE
pin_memory	bool	Whether to enable the dataloader to allocate pagelocked memory for faster data copying between the CPU and GPU	TRUE
augmentation	collection	Configuration parameters for data augmentation					FALSE

BaseDepthNetDatasetConfig Fields

Field	value_type	description	default_value	valid_min	valid_max	valid_options	automl_enabled
data_sources	list	List of data sources for training: dataset_name : The type of the dataset data_file : The path of the data file	[{‘dataset_name’: ‘’, ‘data_file’: ‘’}]				FALSE
image_path	string	Path to the image directory for tao-deploy
right_image_path	string	Path to the right image directory for tao-deploy
depth_image_path	string	Path to the depth image directory for tao-deploy
batch_size	int	Batch size for training and validation	1	1	inf		TRUE
workers	int	Number of parallel workers processing data	8	1	inf		TRUE
pin_memory	bool	Whether to enable the dataloader to allocate pagelocked memory for faster data copying between the CPU and GPU	TRUE
augmentation	collection	Configuration parameters for data augmentation					FALSE

BaseDepthNetDatasetConfig Fields

Field	value_type	description	default_value	valid_min	valid_max	valid_options	automl_enabled
data_sources	list	List of data sources for training: dataset_name : The type of the dataset data_file : The path of the data file	[{‘dataset_name’: ‘’, ‘data_file’: ‘’}]				FALSE
image_path	string	Path to the image directory for tao-deploy
right_image_path	string	Path to the right image directory for tao-deploy
depth_image_path	string	Path to the depth image directory for tao-deploy
batch_size	int	Batch size for training and validation	1	1	inf		TRUE
workers	int	Number of parallel workers processing data	8	1	inf		TRUE
pin_memory	bool	Whether to enable the dataloader to allocate pagelocked memory for faster data copying between the CPU and GPU	TRUE
augmentation	collection	Configuration parameters for data augmentation					FALSE

BaseDepthNetDatasetConfig Fields

Field	value_type	description	default_value	valid_min	valid_max	valid_options	automl_enabled
data_sources	list	List of data sources for training: dataset_name : The type of the dataset data_file : The path of the data file	[{‘dataset_name’: ‘’, ‘data_file’: ‘’}]				FALSE
image_path	string	Path to the image directory for tao-deploy
right_image_path	string	Path to the right image directory for tao-deploy
depth_image_path	string	Path to the depth image directory for tao-deploy
batch_size	int	Batch size for training and validation	1	1	inf		TRUE
workers	int	Number of parallel workers processing data	8	1	inf		TRUE
pin_memory	bool	Whether to enable the dataloader to allocate pagelocked memory for faster data copying between the CPU and GPU	TRUE
augmentation	collection	Configuration parameters for data augmentation					FALSE

MonoBackBone Fields

Field	value_type	description	default_value	valid_min	valid_max	valid_options	automl_enabled
pretrained_path	string	Path to load DepthAnythingv2 as an encoder for Monocular DepthNet
use_bn	bool	Whether to use batch normalization in Monocular DepthNet	FALSE
use_clstoken	bool	Whether to use class token	FALSE

StereoBackBone Fields

Field	value_type	description	default_value	valid_min	valid_max	valid_options	automl_enabled
depth_anything_v2_pretrained_path	string	Path to load DepthAnythingv2 as an encoder for Stereo DepthNet (FoundationStereo)
edgenext_pretrained_path	string	Path to load edgenext encoder for Stereo DepthNet (FoundationStereo)
use_bn	bool	Whether to use batch normalization in DepthAnythingV2	FALSE
use_clstoken	bool	Whether to use class token	FALSE

CuDNNConfig Fields

Field	value_type	description	default_value	valid_min	valid_max	valid_options	automl_enabled
benchmark	bool		FALSE
deterministic	bool		TRUE

OptimConfig Fields

Field	value_type	description	default_value	valid_min	valid_max	valid_options	automl_enabled
optimizer	categorical	Type of optimizer used to train the network	AdamW			AdamW,SGD
monitor_name	categorical	Metric value to be monitored for the AutoReduce Scheduler	val_loss			val_loss,train_loss
lr	float	Initial learning rate for training the model, excluding the backbone	0.0001				TRUE
momentum	float	Momentum for the AdamW optimizer	0.9				TRUE
weight_decay	float	Weight decay coefficient	0.0001				TRUE
lr_scheduler	categorical	Learning scheduler: MultiStepLR : Decrease the lr by lr_decay from lr_steps StepLR : Decrease the lr by lr_decay at every lr_step_size	MultiStepLR			MultiStep,StepLR,CustomMultiStepLRScheduler,LambdaLR,PolynomialLR,OneCycleLR,CosineAnnealingLR
lr_steps	list	Steps at which the learning rate must be decreased This is applicable only with the MultiStep LR	[1000]				FALSE
lr_step_size	int	Number of steps to decrease the learning rate in the StepLR	1000				TRUE
lr_decay	float	Decreasing factor for the learning rate scheduler	0.1				TRUE
min_lr	float	Minimum learning rate value for the learning rate scheduler	1e-07				TRUE
warmup_steps	int	Number of steps to perform linear learning rate” warm-up before engaging a learning rate scheduler	20	0	inf

DepthNetTrtConfig Fields

Field	value_type	description	default_value	valid_min	valid_max	valid_options	automl_enabled
workspace_size	int	Size in megabytes of the workspace TensorRT has for running its optimization tactics and generating the TensorRT engine	1024	0
min_batch_size	int	Minimum batch size in the optimization profile for the input tensor of the TensorRT engine	1	1
opt_batch_size	int	Optimum batch size in the optimization profile for the input tensor of the TensorRT engine	1	1
max_batch_size	int	Maximum batch size in the optimization profile for the input tensor of the TensorRT engine	1	1
layers_precision	list	List to specify layer precision	[]				FALSE
data_type	categorical	Precision to be set for building the TensorRT engine	FP32			FP32,FP16

DepthNetAugmentationConfig Fields

Field	value_type	description	default_value	valid_min	valid_max	valid_options	automl_enabled
input_mean	list	Input mean for RGB frames	[0.485, 0.456, 0.406]				FALSE
input_std	list	Input standard deviation per pixel for RGB frames	[0.229, 0.224, 0.225]				FALSE
crop_size	list	Crop size for input RGB images [height, width]	[518, 518]				FALSE
min_scale	float	Minimum scale in data augmentation	-0.2	0.2	1
max_scale	float	Maximum scale in data augmentation	0.4	-0.2	1
do_flip	bool	Whether to perform flip in data augmentation	FALSE
yjitter_prob	float	Probability for y jitter	1.0	0.0	1.0		TRUE
gamma	list	Gamma range in data augmentation	[1, 1, 1, 1]				FALSE
color_aug_prob	float	Probability for asymmetric color augmentation	0.2	0.0	1.0		TRUE
color_aug_brightness	float	Color jitter brightness	0.4	0.0	1.0
color_aug_contrast	float	Color jitter contrast	0.4	0.0	1.0
color_aug_saturation	list	Color jitter saturation	[0.0, 1.4]				FALSE
color_aug_hue_range	list	Hue range in data augmentation	[-0.027777777777777776, 0.027777777777777776]				FALSE
eraser_aug_prob	float	Probability for eraser augmentation	0.5	0.0	1.0		TRUE
spatial_aug_prob	float	Probability for spatial augmentation	1.0	0.0	1.0		TRUE
stretch_prob	float	Probability for stretch augmentation	0.8	0.0	1.0		TRUE
max_stretch	float	Maximum stretch augmentation	0.2	0.0	1.0
h_flip_prob	float	Probability for horizontal flip augmentation	0.5	0.0	1.0		TRUE
v_flip_prob	float	Probability for vertical flip augmentation	0.5	0.0	1.0		TRUE
hshift_prob	float	Probability for horizontal shift augmentation	0.5	0.0	1.0		TRUE
crop_min_valid_disp_ratio	float	Probability for minimum crop valid disparity ratio	0.0	0.0	1.0		TRUE