Tao Train Deformable Detr

NVIDIAOfficialCreated by NVIDIA Corporation

Skill
Tool integration
Data and AI
Apache-2.0
Medium risk

From the author

Deformable DETR for 2D object detection. Uses deformable attention for efficient multi-scale feature processing, lighter than DINO with competitive accuracy. Use when training, evaluating, exporting, quantizing, or running inference for a TAO Deformable-DETR model. Trigger phrases include "train deformable-detr", "Deformable DETR object detection", "lightweight DETR detector".

— the description by NVIDIA Corporation

AutoGineer summary

Written by AutoGineer from the skill’s own files, not by the author

This skill provides a structured interface for training, evaluating, exporting, and quantizing Deformable DETR models for 2D object detection. It leverages deformable attention mechanisms for efficient multi-scale feature processing and is designed to integrate with TAO Toolkit workflows. The skill supports AutoML for training optimization and provides clear paths for model deployment, including TensorRT engine generation via the TAO Deploy container.

What it does

Trains Deformable DETR models using COCO or COCO-raw datasets.
Evaluates model performance using mAP metrics.
Exports trained models to ONNX format for deployment.
Quantizes models to optimize for inference performance.
Supports AutoML policies to automate hyperparameter tuning during training.
Provides templates for generating TensorRT engines.

When to use it

When you need to perform 2D object detection using the Deformable DETR architecture.
When you are building a computer vision pipeline within the NVIDIA TAO Toolkit.
When you need to optimize a model for inference using quantization or TensorRT engine generation.
When you want to automate the training process using AutoML.

Advantages

Efficient multi-scale feature processing using deformable attention.
Lighter architecture compared to standard DINO models.
Integrated support for the full TAO model lifecycle.
Flexible configuration for custom datasets and training parameters.

Usage examples

“Train a Deformable DETR model with my custom dataset.”: The agent initiates the training process using the provided dataset paths and default configurations, applying AutoML if enabled.
“Export my trained Deformable DETR model to ONNX.”: The agent executes the export action, generating an ONNX file suitable for subsequent TensorRT engine conversion.

Install

Download the skill as a ZIP:
https://mp-staging.autogineer.com/agent-skills/nvidia/tao-train-deformable-detr/download

Unzip it into the cross-client skills folder of your project:

mkdir -p .agents/skills && unzip tao-train-deformable-detr.zip -d .agents/skills

Documentation by NVIDIA Corporation

Deformable DETR

Standalone install? If this session was not initialized by the TAO skill bank plugin, run the tao-setup skill first (host preflight, credentials, cross-skill discovery).

Deformable DETR for 2D object detection. Uses deformable attention for efficient multi-scale feature processing. Lighter than DINO with competitive accuracy.

Uses pretrained weights. Set model.pretrained_backbone_path for backbone-only loading or train.pretrained_model_path for full model initialization.

Supported parent model actions are train, evaluate, inference, export, and quantize. The PyT model container does not support a native gen_trt_engine subtask for this network. The gen_trt_engine action declared in references/skill_info.yaml must run with the TAO Deploy container. Deploy spec templates live in this skill's references/ folder with the spec_template_deploy_*.yaml prefix.

Dataclass Schemas

Generated TAO Core schemas are packaged in schemas/<action>.schema.json, with schemas/manifest.json listing available actions. Each generated schema also emits references/spec_template_<action>.yaml from the schema top-level default field. AutoML enablement is declared at the model layer in references/skill_info.yaml via automl_enabled. Runnable AutoML for an action requires schemas/<action>.schema.json and references/spec_template_<action>.yaml to exist and parse. Use the packaged selected-action schema for automl_default_parameters, automl_disabled_parameters, defaults, min/max bounds, enums, option weights, math conditions, dependencies, and popular parameters. Do not expect ~/tao-core at runtime; maintainers regenerate schemas/templates before packaging the skill bank.

Train Action Policy

This model is AutoML-enabled at the model layer. Before handling any train-stage request, read references/skill_info.yaml and resolve the run override from either an explicit automl_policy value or the user's workflow request. Use automl_policy: on by default and only expose on / off in new launch prompts. Treat phrases like "turn off AutoML", "disable AutoML", "no HPO", or "plain training" as automl_policy: off for this run only. When automl_policy: on, automl_enabled: true, and both schemas/train.schema.json and references/spec_template_train.yaml are packaged, route the train action through tao-skill-bank:tao-run-automl by default with this model's skill_dir. Preserve workflow/application overrides for datasets, specs, output directories, GPU/platform settings, parent checkpoints, and automl_policy. Use direct model training only when automl_policy: off or the packaged train schema/template is missing; in the missing-schema case, report that AutoML is enabled but not runnable for this model until schemas are generated.

Non-train actions such as evaluate, inference, export, and deploy flows stay in this model skill. The per-run automl_policy override does not change model metadata.

Training Requirements

Dataset type: object_detection
Formats: coco, coco_raw
AutoML metric contract: for evaluation-backed selection, use test_mAP50 with maximize direction. Use val_mAP50 only for training-log-only AutoML workflows.
Training monitoring metrics: val_mAP50 for AP50; val_mAP for COCO/paper-style benchmark comparisons.
Evaluate action metrics: test_mAP50 for AP50; test_mAP for COCO/paper-style benchmark comparisons. AutoML trials compared through the evaluate action must use the corresponding test_* KPI rather than looking for a val_* KPI in evaluator output.

Per-Action Dataset Requirements

Action	Spec Key	Source	Files	List?
evaluate	dataset.test_data_sources.image_dir	eval_dataset	images.tar.gz	No
evaluate	dataset.test_data_sources.json_file	eval_dataset	annotations.json	No
export	dataset.train_data_sources	train_datasets	image_dir: images.tar.gz, json_file: annotations.json	Yes
export	dataset.val_data_sources	train_datasets	image_dir: images.tar.gz, json_file: annotations.json	Yes
inference	dataset.infer_data_sources.image_dir	inference_dataset	images.tar.gz	Yes
inference	dataset.infer_data_sources.classmap	inference_dataset	label_map.txt	No
quantize	dataset.train_data_sources	train_datasets	image_dir: images.tar.gz, json_file: annotations.json	Yes
quantize	dataset.val_data_sources	train_datasets	image_dir: images.tar.gz, json_file: annotations.json	Yes
quantize	dataset.quant_calibration_data_sources	train_datasets	image_dir: images.tar.gz, json_file: annotations.json	No
train	dataset.train_data_sources	train_datasets	image_dir: images.tar.gz, json_file: annotations.json	Yes
train	dataset.val_data_sources	train_datasets	image_dir: images.tar.gz, json_file: annotations.json	Yes

Typical Spec Overrides

Data source overrides are mandatory for every action — the agent MUST construct data source paths from the Per-Action Dataset Requirements table above and include them in spec_overrides.

S3_TRAIN = "s3://bucket/data/train"
S3_EVAL = "s3://bucket/data/eval"

train (mandatory data sources):

{
    "train.num_epochs": 10,
    "train.checkpoint_interval": 10,
    "train.validation_interval": 10,
    "train.num_gpus": 1,
    "train.gpu_ids": [0],
    "dataset.num_classes": "<object classes> + 1",
    "dataset.eval_class_ids": [1, 2, "..."],
    "dataset.train_data_sources": [{"image_dir": f"{S3_TRAIN}/images.tar.gz", "json_file": f"{S3_TRAIN}/annotations.json"}],
    "dataset.val_data_sources": [{"image_dir": f"{S3_TRAIN}/images.tar.gz", "json_file": f"{S3_TRAIN}/annotations.json"}],
}

evaluate (mandatory data sources):

{
    "dataset.num_classes": "<object classes> + 1",
    "dataset.eval_class_ids": [1, 2, "..."],
    "dataset.test_data_sources.image_dir": f"{S3_EVAL}/images.tar.gz",
    "dataset.test_data_sources.json_file": f"{S3_EVAL}/annotations.json",
}

If the train or AutoML run changed architecture-affecting fields such as model.enc_layers, model.dec_layers, model.num_queries, or model.num_select, carry the same values into evaluate, export, inference, and deploy actions with the selected checkpoint. In addition to the fields above, carry model.num_feature_levels, model.dim_feedforward, input image dimensions, and dataset class metadata when they were changed. Loading a checkpoint into the default architecture can fail with tensor shape mismatches, especially when smoke-test runs shrink the transformer for speed.

export (mandatory data sources):

{
    "dataset.num_classes": "<object classes> + 1",
    "dataset.eval_class_ids": [1, 2, "..."],
    "dataset.train_data_sources": [{"image_dir": f"{S3_TRAIN}/images.tar.gz", "json_file": f"{S3_TRAIN}/annotations.json"}],
    "dataset.val_data_sources": [{"image_dir": f"{S3_TRAIN}/images.tar.gz", "json_file": f"{S3_TRAIN}/annotations.json"}],
}

TensorRT engine generation:

Use the deploy spec templates after export. Do not call deformable_detr gen_trt_engine from the parent PyT model container; that CLI advertises convert, evaluate, export, inference, quantize, train, and default_specs, but not gen_trt_engine. The model action metadata selects the TAO Deploy container for engine generation.

Deploy engine generation needs the exported ONNX file as input and creates the engine at gen_trt_engine.trt_engine.

{
    "gen_trt_engine.tensorrt.data_type": "FP16",
    "dataset.num_classes": "<object classes> + 1",
    "gen_trt_engine.tensorrt.calibration.cal_image_dir": [f"{S3_TRAIN}/images.tar.gz"],
}

inference (mandatory data sources):

{
    "dataset.num_classes": "<object classes> + 1",
    "dataset.infer_data_sources.image_dir": [f"{S3_EVAL}/images.tar.gz"],
    "dataset.infer_data_sources.classmap": f"{S3_EVAL}/label_map.txt",
}

quantize (mandatory data sources):

{
    "dataset.train_data_sources": [{"image_dir": f"{S3_TRAIN}/images.tar.gz", "json_file": f"{S3_TRAIN}/annotations.json"}],
    "dataset.val_data_sources": [{"image_dir": f"{S3_TRAIN}/images.tar.gz", "json_file": f"{S3_TRAIN}/annotations.json"}],
    "dataset.quant_calibration_data_sources": {"image_dir": f"{S3_TRAIN}/images.tar.gz", "json_file": f"{S3_TRAIN}/annotations.json"},
}

Eval Dataset

Optional. If provided, validation mAP is computed at each checkpoint interval.

Checkpoint Handling

Training emits epoch-and-step checkpoints using the pattern model_epoch_<epoch>_step_<step>.pth, plus a dd_model_latest.pth symlink. For dependent actions, use the model-specific or SDK-provided checkpoint resolver to select the intended artifact. Evaluation, inference, export, and quantize should receive the selected exact checkpoint path, not the dd_model_latest.pth symlink, unless the user explicitly asked for latest. Resume/retrain should set train.resume_training_checkpoint_path to the exact checkpoint being resumed from.

Important Parameters

dataset.num_classes: Number of object classes plus the background class. Default 91 (COCO). Must match annotations.
dataset.eval_class_ids: Foreground category ids to include in COCO metrics. Set this to every object category id in custom datasets; the template default evaluates class id 1 only.
model.backbone: Default resnet_50. Supported: resnet_50, gcvit_tiny, gcvit_small, gcvit_base, gcvit_large, gcvit_large_384 (more limited than DINO).
train.optim.lr: Learning rate. Default 2e-4 (AdamW). lr_backbone is 2e-5.
train.optim.lr_steps: MultiStep LR schedule. Default [40]. For short runs, set to match ~80% of total epochs.
model.num_queries: Number of object queries. Default 300. Valid range 100-900.
model.dropout_ratio: Dropout in transformer layers. Default 0.3 (higher than DINO's 0.0). Reduce for large datasets, increase for small datasets.
model.dim_feedforward: FFN hidden dim. Default 1024 (vs DINO's 2048). Increasing improves capacity but costs memory.

Multi-GPU / Multi-Node

Launch method: Lightning-managed (single python process, Lightning spawns workers).

Spec Key	Description	Default
`train.num_gpus`	Number of GPUs	1
`train.gpu_ids`	GPU device indices	[0]
`train.num_nodes`	Number of nodes	1
`train.distributed_strategy`	`ddp` or `fsdp`	`ddp`

Same DDP/FSDP behavior as DINO. Multi-node requires WORLD_SIZE, NODE_RANK, MASTER_ADDR, MASTER_PORT env vars set by orchestrator.

When increasing train.num_gpus, also set train.gpu_ids to the same visible device range. For example, an 8-GPU single-node Slurm run must include both "train.num_gpus": 8 and "train.gpu_ids": [0, 1, 2, 3, 4, 5, 6, 7].

Export / TRT Defaults

Export input: 640x640, opset 17
TRT data types: FP32, FP16, INT8
TRT workspace: 1024 MB
TRT max_batch_size: 1

Hardware

Minimum 1 GPU(s), recommended 4 GPU(s). 16GB+ (V100 or A100) VRAM per GPU. Slightly lighter than DINO due to smaller FFN. batch_size=4 fits on most 16GB+ GPUs.

Error Patterns

CUDA out of memory: Reduce batch_size (4 -> 2 -> 1).

num_select must be < num_queries * num_classes: Same constraint as DINO.

return_interm_indices length must match num_feature_levels: Default [1,2,3,4] with num_feature_levels=4.

Dataset size smaller than total batch size: Reduce batch_size or num_gpus.

AutoML metric extraction: Deformable DETR emits val_mAP and val_mAP50 in structured training status, while the standalone evaluate action emits test_mAP and test_mAP50. For COCO/paper-style training-only comparisons, optimize val_mAP; for explicit AP50 training-only workflows, optimize val_mAP50. When AutoML scores each recommendation with the evaluate action, use the corresponding test_mAP or test_mAP50 KPI. Prefer results_dir/train/status.json or AutoML result state before parsing raw logs. Do not optimize val_loss for default detection model invocations.

Spec Param / Parent Model Inference

Model-specific inference mappings belong in this MD file, not in config.json. Generated runners should read this section and apply the mappings with SDK helpers before create_job(). This mirrors the old microservices infer_params.py flow.

Inference mappings from TAO Core deformable_detr.config.json:

Action	Spec Field	Inference Function	Meaning
evaluate	`encryption_key`	`key`	encryption key
evaluate	`evaluate.checkpoint`	`parent_model`	model file inferred from the parent job results folder
evaluate	`evaluate.trt_engine`	`parent_model`	model file inferred from the parent job results folder
evaluate	`results_dir`	`output_dir`	current job results directory
export	`encryption_key`	`key`	encryption key
export	`export.checkpoint`	`parent_model`	model file inferred from the parent job results folder
export	`export.onnx_file`	`create_onnx_file`	output ONNX path
export	`results_dir`	`output_dir`	current job results directory
inference	`encryption_key`	`key`	encryption key
inference	`inference.checkpoint`	`parent_model`	model file inferred from the parent job results folder
inference	`inference.trt_engine`	`parent_model`	model file inferred from the parent job results folder
inference	`results_dir`	`output_dir`	current job results directory
quantize	`encryption_key`	`key`	encryption key
quantize	`quantize.model_path`	`parent_model`	model file inferred from the parent job results folder
quantize	`results_dir`	`output_dir`	current job results directory
train	`encryption_key`	`key`	encryption key
train	`model.pretrained_backbone_path`	`ptm_if_no_resume_model`	PTM when no resume checkpoint exists
train	`results_dir`	`output_dir`	current job results directory
train	`train.pretrained_model_path`	`ptm_if_no_resume_model`	full model PTM when no resume checkpoint exists
train	`train.resume_training_checkpoint_path`	`resume_model`	model file inferred from the current job results folder

For parent_model or parent_model_folder, pass the upstream train/export/AutoML child job id as parent_job_id. The SDK lists the parent result folder, filters checkpoint artifacts, and returns the selected model file or folder. Do not add these mappings back to config.json and do not patch generated runner scripts to guess checkpoint paths.

Deployment

tao-deploy-deformable-detr

Files

ATTRIBUTION.mdAdded by AutoGineer945 B
BENCHMARK.md7.0 KiB
LICENSELicence file added by AutoGineer11.2 KiB
SKILL.md15.1 KiB
config/skillspector-baseline.yaml834 B
evals/evals.json804 B
references/skill_info.yaml4.6 KiB
references/spec_template_deploy_evaluate.yaml438 B
references/spec_template_deploy_gen_trt_engine.yaml698 B
references/spec_template_deploy_inference.yaml449 B
references/spec_template_evaluate.yaml2.8 KiB
references/spec_template_export.yaml2.9 KiB
references/spec_template_gen_trt_engine.yaml3.1 KiB
references/spec_template_inference.yaml2.9 KiB
references/spec_template_quantize.yaml2.7 KiB
references/spec_template_train.yaml2.7 KiB
references/tao-deploy-deformable-detr.md5.5 KiB
references/tao-deploy-deformable-detr.skill_info.yaml2.4 KiB
schemas/evaluate.schema.json49.5 KiB
schemas/export.schema.json50.0 KiB
schemas/gen_trt_engine.schema.json54.6 KiB
schemas/inference.schema.json50.4 KiB
schemas/manifest.json15.2 KiB
schemas/quantize.schema.json46.2 KiB
schemas/train.schema.json46.2 KiB
skill-card.md4.4 KiB
skill.oms.sig9.4 KiB

schemas/train.schema.json

{
  "automl_default_parameters": [
    "train.optim.lr_step_size",
    "model.enc_layers",
    "dataset.augmentation.train_random_crop_min",
    "model.dec_layers",
    "dataset.batch_size",
    "train.optim.lr_linear_proj_mult",
    "train.optim.weight_decay",
    "train.optim.lr_decay",
    "dataset.workers",
    "train.optim.lr_backbone",
    "train.optim.momentum",
    "dataset.augmentation.train_random_crop_max",
    "model.num_queries",
    "train.optim.lr",
    "dataset.augmentation.horizontal_flip_prob",
    "model.num_select"
  ],
  "automl_disabled_parameters": [
    "quantize",
    "train.cudnn",
    "gen_trt_engine.tensorrt.calibration.cal_image_dir",
    "quantize.backend_kwargs",
    "train.gpu_ids",
    "model.return_interm_indices",
    "dataset.train_data_sources",
    "wandb.tags",
    "dataset.eval_class_ids",
    "quantize.skip_names",
    "inference.color_map",
    "evaluate",
    "inference",
    "train",
    "model.loss_types",
    "dataset.val_data_sources",
    "dataset.augmentation",
    "gen_trt_engine",
    "gen_trt_engine.tensorrt.layers_precision",
    "dataset",
    "gen_trt_engine.tensorrt",
    "quantize.layers",
    "dataset.augmentation.input_mean",
    "model.backbone_names",
    "model",
    "train.optim.lr_steps",
    "train.freeze",
    "dataset.augmentation.input_std",
    "train.optim",
    "evaluate.gpu_ids",
    "dataset.augmentation.train_random_resize",
    "gen_trt_engine.tensorrt.calibration",
    "model.hidden_dim",
    "model.linear_proj_names",
    "export",
    "dataset.augmentation.test_random_resize",
    "wandb",
    "dataset.infer_data_sources",
    "dataset.augmentation.scales",
    "inference.gpu_ids",
    "dataset.test_data_sources",
    "dataset.quant_calibration_data_sources"
  ],
  "default": {
    "dataset": {
      "augmentation": {
        "fixed_padding": true,
        "fixed_random_crop": 1024,
        "horizontal_flip_prob": 0.5,
        "input_mean": [
          0.485,
          0.456,
          0.406
        ],
        "input_std": [
          0.229,
          0.224,
          0.225
        ],
        "random_resize_max_size": 1333,
        "scales": [
          480,
          512,
          544,
          576,
          608,
          640,
          672,
          704,
          736,
          768,
          800
        ],
        "test_random_resize": 800,
        "train_random_crop_max": 600,
        "train_random_crop_min": 384,
        "train_random_resize": [
          400,
          500,
          600
        ]
      },
      "batch_size": 4,
      "dataset_type": "serialized",
      "eval_class_ids": [
        1
      ],
      "infer_data_sources": {
        "classmap": "",
        "image_dir": [
          ""
        ]
      },
      "num_classes": 91,
      "pin_memory": true,
      "quant_calibration_data_sources": {
        "image_dir": "",
        "json_file": ""
      },
      "test_data_sources": {
        "image_dir": "",
        "json_file": ""
      },
      "train_data_sources": [
        {
          "image_dir": "",
          "json_file": ""
        }
      ],
      "train_sampler": "default_sampler",
      "val_data_sources": [
        {
          "image_dir": "",
          "json_file": ""
        }
      ],
      "workers": 8
    },
    "encryption_key": "",
    "model": {
      "aux_loss": true,
      "backbone": "resnet_50",
      "backbone_names": [
        "backbone.0"
      ],
      "bbox_loss_coef": 5.0,
      "clip_max_norm": 0.1,
      "cls_loss_coef": 2.0,
      "dec_layers": 6,
      "dec_n_points": 4,
      "dilation": false,
      "dim_feedforward": 1024,
      "dld_model_dir_path": "",
      "dropout_ratio": 0.3,
      "enc_layers": 6,
      "enc_n_points": 4,
      "focal_alpha": 0.25,
      "giou_loss_coef": 2.0,
      "hidden_dim": 256,
      "linear_proj_names": [
        "reference_points",
        "sampling_offsets"
      ],
      "loss_types": [
        "labels",
        "boxes"
      ],
      "nheads": 8,
      "num_feature_levels": 4,
      "num_queries": 300,
      "num_select": 300,
      "pretrained_backbone_path": "",
      "return_interm_indices": [
        1,
        2,
        3,
        4
      ],
      "train_backbone": true,
      "with_box_refine": true
    },
    "model_name": "",
    "quantize": {
      "algorithm": "minmax",
      "backend": "torchao",
      "backend_kwargs": {},
      "device": "cuda",
      "layers": [],
      "mode": "weight_only_ptq",
      "model_path": "",
      "results_dir": "",
      "skip_names": []
    },
    "results_dir": "",
    "train": {
      "activation_checkpoint": true,
      "checkpoint_interval": 1,
      "checkpoint_interval_unit": "epoch",
      "clip_grad_norm": 0.1,
      "cudnn": {
        "benchmark": false,
        "deterministic": true
      },
      "distributed_strategy": "ddp",
      "freeze": [],
      "gpu_ids": [
        0
      ],
      "is_dry_run": false,
      "num_epochs": 10,
      "num_gpus": 1,
      "num_nodes": 1,
      "optim": {
        "lr": 0.0002,
        "lr_backbone": 2e-05,
        "lr_decay": 0.1,
        "lr_linear_proj_mult": 0.1,
        "lr_scheduler": "MultiStep",
        "lr_step_size": 40,
        "lr_steps": [
          40
        ],
        "momentum": 0.9,
        "monitor_name": "val_loss",
        "optimizer": "AdamW",
        "weight_decay": 0.0001
      },
      "precision": "fp32",
      "pretrained_model_path": "",
      "results_dir": "",
      "resume_training_checkpoint_path": "",
      "seed": 1234,
      "validation_interval": 1,
      "verbose": false
    },
    "wandb": {
      "enable": true,
      "entity": "",
      "group": "",
      "name": "TAO Toolkit Training",
      "project": "TAO Toolkit",
      "reinit": false,
      "run_id": "",
      "save_code": false,
      "sync_tensorboard": false,
      "tags": [
        "tao-toolkit"
      ]
    }
  },
  "popular": {
    "evaluate": {
      "gpu_ids": [
        0
      ],
      "num_gpus": 1,
      "num_nodes": 1
    },
    "gen_trt_engine": {
      "batch_size": -1,
      "gpu_id": 0,
      "tensorrt": {
        "calibration": {
          "cal_batch_size": 1,
          "cal_batches": 1
        },
        "max_batch_size": 1,
        "min_batch_size": 1,
        "opt_batch_size": 1
      }
    },
    "inference": {
      "gpu_ids": [
        0
      ],
      "num_gpus": 1,
      "num_nodes": 1
    },
    "train": {
      "checkpoint_interval": 1,
      "gpu_ids": [
        0
      ],
      "num_epochs": 10,
      "num_gpus": 1,
      "num_nodes": 1,
      "validation_interval": 1
    }
  },
  "properties": {
    "automl_disabled_parameters": [
      "wandb",
      "model",
      "dataset",
      "train",
      "evaluate",
      "inference",
      "export",
      "gen_trt_engine",
      "quantize"
    ],
    "dataset": {
      "automl_default_parameters": [
        "dataset.batch_size",
        "dataset.workers"
      ],
      "automl_disabled_parameters": [
        "dataset.train_data_sources",
        "dataset.val_data_sources",
        "dataset.test_data_sources",
        "dataset.infer_data_sources",
        "dataset.quant_calibration_data_sources",
        "dataset.eval_class_ids",
        "dataset.augmentation"
      ],
      "automl_enabled": false,
      "default": {
        "augmentation": {
          "fixed_padding": true,
          "fixed_random_crop": 1024,
          "horizontal_flip_prob": 0.5,
          "input_mean": [
            0.485,
            0.456,
            0.406
          ],
          "input_std": [
            0.229,
            0.224,
            0.225
          ],
          "random_resize_max_size": 1333,
          "scales": [
            480,
            512,
            544,
            576,
            608,
            640,
            672,
            704,
            736,
            768,
            800
          ],
          "test_random_resize": 800,
          "train_random_crop_max": 600,
          "train_random_crop_min": 384,
          "train_random_resize": [
            400,
            500,
            600
          ]
        },
        "batch_size": 4,
        "dataset_type": "serialized",
        "eval_class_ids": [
          1
        ],
        "infer_data_sources": {
          "classmap": "",
          "image_dir": [
            ""
          ]
        },
        "num_classes": 91,
        "pin_memory": true,
        "quant_calibration_data_sources": {
          "image_dir": "",
          "json_file": ""
        },
        "test_data_sources": {
          "image_dir": "",
          "json_file": ""
        },
        "train_data_sources": [
          {
            "image_dir": "",
            "json_file": ""
          }
        ],
        "train_sampler": "default_sampler",
        "val_data_sources": [
          {
            "image_dir": "",
            "json_file": ""
          }
        ],
        "workers": 8
      },
      "description": "Configurable parameters to construct the dataset for a Deformable DETR experiment.",
      "properties": {
        "augmentation": {
          "automl_default_parameters": [
            "dataset.augmentation.horizontal_flip_prob",
            "dataset.augmentation.train_random_crop_min",
            "dataset.augmentation.train_random_crop_max"
          ],
          "automl_disabled_parameters": [
            "dataset.augmentation.scales",
            "dataset.augmentation.input_mean",
            "dataset.augmentation.input_std",
            "dataset.augmentation.train_random_resize",
            "dataset.augmentation.test_random_resize"
          ],
          "automl_enabled": false,
          "default": {
            "fixed_padding": true,
            "fixed_random_crop": 1024,
            "horizontal_flip_prob": 0.5,
            "input_mean": [
              0.485,
              0.456,
              0.406
            ],
            "input_std": [
              0.229,
              0.224,
              0.225
            ],
            "random_resize_max_size": 1333,
            "scales": [
              480,
              512,
              544,
              576,
              608,
              640,
              672,
              704,
              736,
              768,
              800
            ],
            "test_random_resize": 800,
            "train_random_crop_max": 600,
            "train_random_crop_min": 384,
            "train_random_resize": [
              400,
              500,
              600
            ]
          },
          "description": "Configuration parameters for data augmentation",
          "properties": {
            "fixed_padding": {
              "default": true,
              "description": "A flag specifying whether to resize the image (with no padding) to (sorted(scales[-1]), random_resize_max_size) to prevent a CPU memory leak.",
              "title": "fixed padding",
              "type": "bool"
            },
            "fixed_random_crop": {
              "default": 1024,
              "description": "A flag to enable Large Scale Jittering, which is used for ViT backbones. The resulting image resolution is fixed to fixed_random_crop.",
              "maximum": Infinity,
              "minimum": 1,
              "title": "fixed random crop",
              "type": "int"
            },
            "horizontal_flip_prob": {
              "automl_enabled": true,
              "default": 0.5,
              "description": "The probability for horizonal flip during training",
              "maximum": 1.0,
              "minimum": 0.0,
              "title": "horizontal flip probability",
              "type": "float"
            },
            "input_mean": {
              "automl_enabled": false,
              "default": [
                0.485,
                0.456,
                0.406
              ],
              "description": "The input mean for RGB frames",
              "title": "input mean per pixel",
              "type": "list"
            },
            "input_std": {
              "automl_enabled": false,
              "default": [
                0.229,
                0.224,
                0.225
              ],
              "description": "The input standard deviation per pixel for RGB frames",
              "title": "input std per pixel",
              "type": "list"
            },
            "random_resize_max_size": {
              "default": 1333,
              "description": "The maximum random resize size for training data",
              "maximum": Infinity,
              "minimum": 1,
              "title": "random resize max size",
              "type": "int"
            },
            "scales": {
              "automl_enabled": false,
              "default": [
                480,
                512,
                544,
                576,
                608,
                640,
                672,
                704,
                736,
                768,
                800
              ],
              "description": "A list of sizes to perform random resize.",
              "title": "scales",
              "type": "list_2"
            },
            "test_random_resize": {
              "automl_enabled": false,
              "default": 800,
              "description": "The random resize size for test data",
              "maximum": Infinity,
              "minimum": 32,
              "title": "random resize max size",
              "type": "int"
            },
            "train_random_crop_max": {
              "automl_enabled": true,
              "default": 600,
              "depends_on": "dataset.augmentation.train_random_crop_min",
              "description": "The maximum random crop size for training data. Must be > train_random_crop_min",
              "math_cond": "> depends_on",
              "maximum": 1333,
              "minimum": 32,
              "title": "Maximum random crop size",
              "type": "int"
            },
            "train_random_crop_min": {
              "automl_enabled": true,
              "default": 384,
              "description": "The minimum random crop size for training data",
              "maximum": Infinity,
              "minimum": 32,
              "parent_param": "TRUE",
              "title": "minumum random crop size",
              "type": "int"
            },
            "train_random_resize": {
              "automl_enabled": false,
              "default": [
                400,
                500,
                600
              ],
              "description": "A list of sizes to perform random resize for training data",
              "title": "train random resize dimensions",
              "type": "list"
            }
          },
          "title": "augmentation",
          "type": "collection"
        },
        "batch_size": {
          "automl_enabled": true,
          "default": 4,
          "description": "The batch size for training and validation",
          "maximum": Infinity,
          "minimum": 1,
          "title": "batch size",
          "type": "int"
        },
        "dataset_type": {
          "default": "serialized",
          "description": "If set to default, we follow the standard CocoDetection` dataset structure from the torchvision which loads COCO annotation in every subprocess. This leads to redudant copy of data and can cause RAM to explod if workers` is high. If set to serialized, the data is serialized through pickle and torch.Tensor` that allows the data to be shared across subprocess. As a result, RAM usage can be greatly improved.",
          "enum": [
            "serialized",
            "default"
          ],
          "title": "dataset type",
          "type": "categorical"
        },
        "eval_class_ids": {
          "automl_enabled": false,
          "default": [
            1
          ],
          "description": "IDs of the classes for evaluation.",
          "title": "eval class ids",
          "type": "list"
        },
        "infer_data_sources": {
          "automl_enabled": false,
          "default": {
            "classmap": "",
            "image_dir": [
              ""
            ]
          },
          "description": "The data source for inference:\n                    * image_dir : The list of directories that contains the inference images\n                    * classmap : The path of the .txt file that contains class names",
          "title": "infer data sources",
          "type": "collection"
        },
        "num_classes": {
          "default": 91,
          "description": "The number of classes in the training data",
          "math_cond": ">0",
          "maximum": Infinity,
          "minimum": 1,
          "title": "num classes",
          "type": "int"
        },
        "pin_memory": {
          "default": true,
          "description": "Flag to enable the dataloader to allocated pagelocked memory for faster of data between the CPU and GPU.",
          "title": "pin_memory",
          "type": "bool"
        },
        "quant_calibration_data_sources": {
          "automl_enabled": false,
          "default": {
            "image_dir": "",
            "json_file": ""
          },
          "description": "The data source for quantization calibration:\n                    * image_dir : The directory that contains the quantization calibration images\n                    * json_file(optional) : The path of the JSON file, which uses quantization calibration-                        annotation COCO format",
          "title": "quantization calibration data sources",
          "type": "collection"
        },
        "test_data_sources": {
          "automl_enabled": false,
          "default": {
            "image_dir": "",
            "json_file": ""
          },
          "description": "The data source for testing:\n                    * image_dir : The directory that contains the test images\n                    * json_file : The path of the JSON file, which uses test-annotation COCO format",
          "title": "test data sources",
          "type": "collection"
        },
        "train_data_sources": {
          "automl_enabled": false,
          "default": [
            {
              "image_dir": "",
              "json_file": ""
            }
          ],
          "description": "The list of data sources for training:\n                    * image_dir : The directory that contains the training images\n                    * json_file : The path of the JSON file, which uses training-annotation COCO format",
          "title": "train data sources",
          "type": "list"
        },
        "train_sampler": {
          "default": "default_sampler",
          "description": "The minibatch sampling method. Non-default sampling methods can be enabled for multi-node jobs. The config doesn't have any effect if the :code:`dataset_type` isn't set to `default`.",
          "enum": [
            "default_sampler",
            "non_uniform_sampler",
            "uniform_sampler"
          ],
          "title": "train sampler",
          "type": "categorical"
        },
        "val_data_sources": {
          "automl_enabled": false,
          "default": [
            {
              "image_dir": "",
              "json_file": ""
            }
          ],
          "description": "The list of data sources for validation:\n                    * image_dir : The directory that contains the validation images\n                    * json_file : The path of the JSON file, which uses validation-annotation COCO format",
          "title": "validation data sources",
          "type": "list"
        },
        "workers": {
          "automl_enabled": true,
          "default": 8,
          "description": "The number of parallel workers processing data",
          "maximum": Infinity,
          "minimum": 1,
          "title": "batch size",
          "type": "int"
        }
      },
      "type": "collection"
    },
    "encryption_key": {
      "default": "",
      "description": "Key for encrypting model checkpoints",
      "title": "Encryption key",
      "type": "string"
    },
    "model": {
      "automl_default_parameters": [
        "model.num_queries",
        "model.num_select",
        "model.enc_layers",
        "model.dec_layers"
      ],
      "automl_disabled_parameters": [
        "model.return_interm_indices",
        "model.hidden_dim",
        "model.loss_types",
        "model.backbone_names",
        "model.linear_proj_names"
      ],
      "automl_enabled": false,
      "default": {
        "aux_loss": true,
        "backbone": "resnet_50",
        "backbone_names": [
          "backbone.0"
        ],
        "bbox_loss_coef": 5.0,
        "clip_max_norm": 0.1,
        "cls_loss_coef": 2.0,
        "dec_layers": 6,
        "dec_n_points": 4,
        "dilation": false,
        "dim_feedforward": 1024,
        "dld_model_dir_path": "",
        "dropout_ratio": 0.3,
        "enc_layers": 6,
        "enc_n_points": 4,
        "focal_alpha": 0.25,
        "giou_loss_coef": 2.0,
        "hidden_dim": 256,
        "linear_proj_names": [
          "reference_points",
          "sampling_offsets"
        ],
        "loss_types": [
          "labels",
          "boxes"
        ],
        "nheads": 8,
        "num_feature_levels": 4,
        "num_queries": 300,
        "num_select": 300,
        "pretrained_backbone_path": "",
        "return_interm_indices": [
          1,
          2,
          3,
          4
        ],
        "train_backbone": true,
        "with_box_refine": true
      },
      "description": "Configurable parameters to construct the model for a Deformable DETR experiment.",
      "properties": {
        "aux_loss": {
          "default": true,
          "description": "A flag specifying whether to use auxiliary decoding losses (loss at each decoder layer)",
          "title": "Train backbone",
          "type": "bool"
        },
        "backbone": {
          "default": "resnet_50",
          "description": "The backbone name of the model. TAO implementation of Deformable DETR support GCViT and ResNet50.",
          "enum": [
            "gc_vit_xxtiny",
            "gc_vit_xtiny",
            "gc_vit_tiny",
            "gc_vit_small",
            "gc_vit_base",
            "gc_vit_large",
            "gc_vit_large_384",
            "resnet_50"
          ],
          "title": "backbone",
          "type": "categorical"
        },
        "backbone_names": {
          "automl_enabled": false,
          "default": [
            "backbone.0"
          ],
          "description": "Prefix of the tensor names corresponding to the backbone.",
          "title": "Backbone tensor name prefix",
          "type": "list"
        },
        "bbox_loss_coef": {
          "default": 5.0,
          "description": "The relative weight of the L1 error of the bounding box coordinates in the matching cost.",
          "maximum": Infinity,
          "minimum": 0.0,
          "title": "BBox loss coefficient",
          "type": "float"
        },
        "clip_max_norm": {
          "default": 0.1,
          "title": "clip max norm",
          "type": "float"
        },
        "cls_loss_coef": {
          "default": 2.0,
          "description": "The relative weight of the classification error in the matching cost.",
          "maximum": Infinity,
          "minimum": 0.0,
          "title": "Class loss coefficient",
          "type": "float"
        },
        "dec_layers": {
          "automl_enabled": true,
          "default": 6,
          "description": "Numer of decoder layers in the transformer",
          "maximum": 12,
          "minimum": 1,
          "title": "decoder layers",
          "type": "int"
        },
        "dec_n_points": {
          "default": 4,
          "description": "Number of reference points in the decoder.",
          "minimum": 1,
          "title": "decoder n points",
          "type": "int"
        },
        "dilation": {
          "default": false,
          "description": "A flag specifying whether enable dilation or not in the backbone.",
          "title": "Dilation enabled.",
          "type": "bool"
        },
        "dim_feedforward": {
          "default": 1024,
          "description": "Dimension of the feedforward network",
          "minimum": 1,
          "title": "dim feedforward",
          "type": "int"
        },
        "dld_model_dir_path": {
          "default": "",
          "description": "Path to the directory exported by DLD for an edited model",
          "title": "DLD model directory path",
          "type": "string"
        },
        "dropout_ratio": {
          "default": 0.3,
          "description": "The probability to drop hidden units.",
          "maximum": 1.0,
          "minimum": 0.0,
          "title": "drop out ratio",
          "type": "float"
        },
        "enc_layers": {
          "automl_enabled": true,
          "default": 6,
          "description": "Numer of encoder layers in the transformer",
          "maximum": 12,
          "minimum": 1,
          "title": "encoder layers",
          "type": "int"
        },
        "enc_n_points": {
          "default": 4,
          "description": "Number of reference points in the encoder.",
          "minimum": 1,
          "title": "encoder n points",
          "type": "int"
        },
        "focal_alpha": {
          "default": 0.25,
          "description": "The alpha value in the focal loss.",
          "math_cond": "> 0.0",
          "title": "focal alpha",
          "type": "float"
        },
        "giou_loss_coef": {
          "default": 2.0,
          "description": "The relative weight of the GIoU loss of the bounding box in the matching cost.",
          "maximum": Infinity,
          "minimum": 0.0,
          "title": "GIoU loss coefficient",
          "type": "float"
        },
        "hidden_dim": {
          "automl_enabled": false,
          "default": 256,
          "description": "Dimension of the hidden units.",
          "type": "int"
        },
        "linear_proj_names": {
          "automl_enabled": false,
          "default": [
            "reference_points",
            "sampling_offsets"
          ],
          "description": "Linear projection layer names.",
          "title": "linear projection names",
          "type": "list"
        },
        "loss_types": {
          "automl_enabled": false,
          "default": [
            "labels",
            "boxes"
          ],
          "description": "Losses to be used during training",
          "title": "loss_types",
          "type": "list"
        },
        "nheads": {
          "default": 8,
          "description": "Number of heads",
          "title": "nheads",
          "type": "int"
        },
        "num_feature_levels": {
          "default": 4,
          "description": "The number of feature levels to use in the model",
          "maximum": 5,
          "minimum": 1,
          "title": "number of feature levels",
          "type": "int"
        },
        "num_queries": {
          "automl_enabled": true,
          "default": 300,
          "description": "The number of queries",
          "maximum": 900,
          "minimum": 100,
          "parent_param": "TRUE",
          "title": "number of queries",
          "type": "int"
        },
        "num_select": {
          "automl_enabled": true,
          "default": 300,
          "depends_on": "model.num_queries",
          "description": "The number of top-K predictions selected during post-process. Must be < num_queries * num_classes",
          "maximum": 1000,
          "minimum": 1,
          "title": "num select",
          "type": "int"
        },
        "pretrained_backbone_path": {
          "default": "",
          "description": "[Optional] Path to a pretrained backbone file.",
          "title": "pretrained backbone path",
          "type": "string"
        },
        "return_interm_indices": {
          "automl_enabled": false,
          "default": [
            1,
            2,
            3,
            4
          ],
          "description": "The index of feature levels to use in the model. The length must match `num_feature_levels`.",
          "title": "return interim indices",
          "type": "list"
        },
        "train_backbone": {
          "default": true,
          "description": "Flag to set backbone weights as trainable or frozen. When set to `False`, the backbone weights will be frozen.",
          "title": "Train backbone",
          "type": "bool"
        },
        "with_box_refine": {
          "default": true,
          "description": "A flag specifying whether to enbable the Iterative Bounding Box Refinement",
          "title": "With box refine",
          "type": "bool"
        }
      },
      "type": "collection"
    },
    "model_name": {
      "default": "",
      "description": "Name of model if invoking task via :code:`model_agnostic`",
      "title": "Model name",
      "type": "string"
    },
    "quantize": {
      "automl_disabled_parameters": [
        "quantize.layers",
        "quantize.skip_names",
        "quantize.backend_kwargs"
      ],
      "automl_enabled": false,
      "default": {
        "algorithm": "minmax",
        "backend": "torchao",
        "backend_kwargs": {},
        "device": "cuda",
        "layers": [],
        "mode": "weight_only_ptq",
        "model_path": "",
        "results_dir": "",
        "skip_names": []
      },
      "description": "Configurable parameters to run model quantization for a Deformable DETR experiment.",
      "properties": {
        "algorithm": {
          "default": "minmax",
          "description": "Calibration/optimization algorithm. Used by ModelOpt backends (modelopt.pytorch and modelopt.onnx). Ignored by torchao backend.",
          "enum": [
            "minmax",
            "max",
            "entropy",
            "awq_clip",
            "awq_lite",
            "awq_full",
            "rtn_dq"
          ],
          "title": "Calibration algorithm",
          "type": "categorical"
        },
        "backend": {
          "default": "torchao",
          "description": "The quantization backend to use",
          "enum": [
            "modelopt.pytorch",
            "torchao",
            "modelopt.onnx"
          ],
          "title": "Quantization backend",
          "type": "categorical"
        },
        "backend_kwargs": {
          "automl_enabled": false,
          "description": "Additional keyword arguments to pass to the backend",
          "title": "Backend kwargs",
          "type": "collection"
        },
        "device": {
          "default": "cuda",
          "description": "Device to use for calibration. Accepts 'cuda' (uses default GPU), 'cpu', 'trt' (TensorRT for ONNX backend), or specific GPU device like 'cuda:0', 'cuda:1', etc. If 'cuda' is specified but no GPU is available, the framework will automatically fall back to 'cpu'. Note: 'trt' is only supported by the modelopt.onnx backend for ONNX Runtime with TensorRT execution provider.",
          "pattern": "^(cuda|cpu|trt|cuda:[0-9]+)$",
          "title": "Calibration device",
          "type": "string"
        },
        "layers": {
          "automl_enabled": false,
          "default": [],
          "description": "List of per-module quantization configurations. Each entry specifies which modules to quantize and their data types. This is the primary way to configure quantization.",
          "title": "Layer quantization configs",
          "type": "list"
        },
        "mode": {
          "default": "weight_only_ptq",
          "description": "The quantization mode to use",
          "enum": [
            "static_ptq",
            "weight_only_ptq"
          ],
          "title": "Quantization mode",
          "type": "categorical"
        },
        "model_path": {
          "default": "",
          "description": "Path to the model to be quantized. For ONNX backend, path to ONNX file.",
          "title": "Model path",
          "type": "string"
        },
        "results_dir": {
          "default": "",
          "description": "Path to where all the assets generated from a task are stored.",
          "title": "Results directory",
          "type": "string"
        },
        "skip_names": {
          "automl_enabled": false,
          "default": [],
          "description": "List of module/layer names or patterns to exclude from quantization",
          "title": "Skip names",
          "type": "list"
        }
      },
      "required": [
        "model_path",
        "results_dir"
      ],
      "type": "collection"
    },
    "results_dir": {
      "default": "",
      "description": "\n        Path to where all the assets generated from a task are stored.\n        ",
      "title": "Results directory",
      "type": "string"
    },
    "train": {
      "automl_disabled_parameters": [
        "train.gpu_ids",
        "train.cudnn",
        "train.freeze",
        "train.optim"
      ],
      "automl_enabled": false,
      "default": {
        "activation_checkpoint": true,
        "checkpoint_interval": 1,
        "checkpoint_interval_unit": "epoch",
        "clip_grad_norm": 0.1,
        "cudnn": {
          "benchmark": false,
          "deterministic": true
        },
        "distributed_strategy": "ddp",
        "freeze": [],
        "gpu_ids": [
          0
        ],
        "is_dry_run": false,
        "num_epochs": 10,
        "num_gpus": 1,
        "num_nodes": 1,
        "optim": {
          "lr": 0.0002,
          "lr_backbone": 2e-05,
          "lr_decay": 0.1,
          "lr_linear_proj_mult": 0.1,
          "lr_scheduler": "MultiStep",
          "lr_step_size": 40,
          "lr_steps": [
            40
          ],
          "momentum": 0.9,
          "monitor_name": "val_loss",
          "optimizer": "AdamW",
          "weight_decay": 0.0001
        },
        "precision": "fp32",
        "pretrained_model_path": "",
        "results_dir": "",
        "resume_training_checkpoint_path": "",
        "seed": 1234,
        "validation_interval": 1,
        "verbose": false
      },
      "description": "Configurable parameters to construct the trainer for a Deformable DETR experiment.",
      "popular": [
        "validation_interval",
        "checkpoint_interval",
        "num_gpus",
        "num_nodes",
        "num_epochs",
        "gpu_ids"
      ],
      "properties": {
        "activation_checkpoint": {
          "default": true,
          "description": "A True value instructs train to recompute in backward pass to save GPU memory, rather than storing activations.",
          "title": "enable activation checkpointing",
          "type": "bool"
        },
        "checkpoint_interval": {
          "default": 1,
          "description": "The interval (in epochs) at which a checkpoint will be saved. Helps resume training.",
          "minimum": 1,
          "popular": true,
          "title": "Checkpoint interval",
          "type": "int"
        },
        "checkpoint_interval_unit": {
          "default": "epoch",
          "description": "The unit of the checkpoint interval.",
          "enum": [
            "epoch",
            "step"
          ],
          "title": "Checkpoint interval unit",
          "type": "categorical"
        },
        "clip_grad_norm": {
          "default": 0.1,
          "description": "Amount to clip the gradient by L2 Norm. A value of 0.0 specifies no clipping.",
          "math_cond": "> 0.0",
          "title": "clip gradient norm",
          "type": "float"
        },
        "cudnn": {
          "automl_enabled": false,
          "default": {
            "benchmark": false,
            "deterministic": true
          },
          "properties": {
            "benchmark": {
              "default": false,
              "type": "bool"
            },
            "deterministic": {
              "default": true,
              "type": "bool"
            }
          },
          "type": "collection"
        },
        "distributed_strategy": {
          "default": "ddp",
          "description": "The multi-GPU training strategy. DDP (Distributed Data Parallel) and Fully Sharded DDP are supported.",
          "enum": [
            "ddp",
            "fsdp"
          ],
          "title": "distributed_strategy",
          "type": "categorical"
        },
        "freeze": {
          "automl_enabled": false,
          "default": [],
          "description": "\n        List of layer names to freeze.\n        Example: [\"backbone\", \"transformer.encoder\", \"input_proj\"].",
          "title": "freeze",
          "type": "list"
        },
        "gpu_ids": {
          "automl_enabled": false,
          "default": [
            0
          ],
          "description": "\n        List of GPU IDs to run the training on. The length of this list\n        must be equal to the number of gpus in train.num_gpus.",
          "popular": true,
          "title": "GPU IDs",
          "type": "list"
        },
        "input_height": {
          "description": "Height of the input image tensor.",
          "minimum": 1,
          "title": "input height",
          "type": "int"
        },
        "input_width": {
          "description": "Width of the input image tensor.",
          "minimum": 1,
          "title": "input width",
          "type": "int"
        },
        "is_dry_run": {
          "default": false,
          "description": "Whether to run the trainer in Dry Run mode. This serves as a good means to validate the spec file and run a sanity check on the trainer without actually initializing and running the trainer.",
          "title": "Is dry run",
          "type": "bool"
        },
        "num_epochs": {
          "default": 10,
          "description": "Number of epochs to run the training.",
          "maximum": Infinity,
          "minimum": 1,
          "popular": true,
          "title": "Number of epochs",
          "type": "int"
        },
        "num_gpus": {
          "default": 1,
          "description": "The number of GPUs to run the train job.",
          "minimum": 1,
          "popular": true,
          "title": "Number of GPUs",
          "type": "int"
        },
        "num_nodes": {
          "default": 1,
          "description": "Number of nodes to run the training on. If > 1, then multi-node is enabled.",
          "minimum": 1,
          "popular": true,
          "title": "Number of nodes",
          "type": "int"
        },
        "optim": {
          "automl_default_parameters": [
            "train.optim.lr",
            "train.optim.lr_backbone",
            "train.optim.lr_linear_proj_mult",
            "train.optim.momentum",
            "train.optim.weight_decay",
            "train.optim.lr_step_size",
            "train.optim.lr_decay"
          ],
          "automl_disabled_parameters": [
            "train.optim.lr_steps"
          ],
          "automl_enabled": false,
          "default": {
            "lr": 0.0002,
            "lr_backbone": 2e-05,
            "lr_decay": 0.1,
            "lr_linear_proj_mult": 0.1,
            "lr_scheduler": "MultiStep",
            "lr_step_size": 40,
            "lr_steps": [
              40
            ],
            "momentum": 0.9,
            "monitor_name": "val_loss",
            "optimizer": "AdamW",
            "weight_decay": 0.0001
          },
          "description": "Hyper parameters to configure the optimizer.",
          "properties": {
            "lr": {
              "automl_enabled": true,
              "default": 0.0002,
              "description": "The initial learning rate for training the model, excluding the backbone.",
              "math_cond": "> 0.0",
              "maximum": 0.01,
              "minimum": 0.0,
              "title": "learning rate",
              "type": "float"
            },
            "lr_backbone": {
              "automl_enabled": true,
              "default": 2e-05,
              "description": "The initial learning rate for training the backbone.",
              "math_cond": "> 0.0",
              "maximum": 0.001,
              "minimum": 0.0,
              "title": "learning rate - backbone",
              "type": "float"
            },
            "lr_decay": {
              "automl_enabled": true,
              "default": 0.1,
              "description": "The decreasing factor for the learning rate scheduler.",
              "math_cond": "> 0.0",
              "maximum": 1.0,
              "minimum": 0.0,
              "title": "learning rate decay",
              "type": "float"
            },
            "lr_linear_proj_mult": {
              "automl_enabled": true,
              "default": 0.1,
              "description": "The initial learning rate for training the linear projection layer.",
              "math_cond": "> 0.0",
              "maximum": 1.0,
              "minimum": 0.0,
              "title": "learning rate - linear projection",
              "type": "float"
            },
            "lr_scheduler": {
              "default": "MultiStep",
              "description": "The learning scheduler: * MultiStep : Decrease the lr by lr_decay from lr_steps * StepLR : Decrease the lr by lr_decay at every lr_step_size.",
              "enum": [
                "MultiStep",
                "StepLR"
              ],
              "title": "learning rate scheduler",
              "type": "categorical"
            },
            "lr_step_size": {
              "automl_enabled": true,
              "default": 40,
              "description": "The number of steps to decrease the learning rate in the StepLR.",
              "math_cond": "> 0",
              "maximum": 10000,
              "minimum": 1,
              "title": "learning rate step size",
              "type": "int"
            },
            "lr_steps": {
              "automl_enabled": false,
              "default": [
                40
              ],
              "description": "The steps at which the learning rate must be decreased. This is applicable only with the MultiStep LR.",
              "title": "learning rate decay steps",
              "type": "list_2"
            },
            "momentum": {
              "automl_enabled": true,
              "default": 0.9,
              "description": "The momentum for the AdamW optimizer.",
              "math_cond": "> 0.0",
              "maximum": 1.0,
              "minimum": 0.0,
              "title": "momentum - AdamW",
              "type": "float"
            },
            "monitor_name": {
              "default": "val_loss",
              "description": "The metric value to be monitored for the :code:`AutoReduce` Scheduler.",
              "enum": [
                "val_loss",
                "train_loss"
              ],
              "title": "monitor_name",
              "type": "categorical"
            },
            "optimizer": {
              "default": "AdamW",
              "description": "Type of optimizer used to train the network.",
              "enum": [
                "AdamW",
                "SGD"
              ],
              "type": "categorical"
            },
            "weight_decay": {
              "automl_enabled": true,
              "default": 0.0001,
              "description": "The weight decay coefficient.",
              "math_cond": "> 0.0",
              "maximum": 0.1,
              "minimum": 0.0,
              "title": "weight decay",
              "type": "float"
            }
          },
          "title": "optimizer",
          "type": "collection"
        },
        "precision": {
          "default": "fp32",
          "description": "Precision to run the training on.",
          "enum": [
            "fp16",
            "fp32"
          ],
          "title": "precision",
          "type": "categorical"
        },
        "pretrained_model_path": {
          "default": "",
          "description": "Path to a pre-trained Deformable DETR model to initialize the current training from.",
          "type": "string"
        },
        "results_dir": {
          "default": "",
          "description": "\n        Path to where all the assets generated from a task are stored.\n        ",
          "title": "Results directory",
          "type": "string"
        },
        "resume_training_checkpoint_path": {
          "default": "",
          "description": "Path to the checkpoint to resume training from.",
          "title": "Resume checkpoint path",
          "type": "string"
        },
        "seed": {
          "default": 1234,
          "description": "The seed for the initializer in PyTorch. If < 0, disable fixed seed.",
          "maximum": Infinity,
          "minimum": -1,
          "title": "Seed for randomization",
          "type": "int"
        },
        "validation_interval": {
          "default": 1,
          "description": "\n        The interval (in epochs) at which a evaluation\n        will be triggered on the validation dataset.",
          "minimum": 1,
          "popular": true,
          "title": "Validation interval",
          "type": "int"
        },
        "verbose": {
          "default": false,
          "description": "Flag to enable printing of detailed learning rate scaling from the optimizer.",
          "title": "enable verbose logs",
          "type": "bool"
        }
      },
      "type": "collection"
    },
    "wandb": {
      "automl_disabled_parameters": [
        "wandb.tags"
      ],
      "automl_enabled": false,
      "default": {
        "enable": true,
        "entity": "",
        "group": "",
        "name": "TAO Toolkit Training",
        "project": "TAO Toolkit",
        "reinit": false,
        "run_id": "",
        "save_code": false,
        "sync_tensorboard": false,
        "tags": [
          "tao-toolkit"
        ]
      },
      "properties": {
        "enable": {
          "default": true,
          "type": "bool"
        },
        "entity": {
          "default": "",
          "type": "string"
        },
        "group": {
          "default": "",
          "type": "string"
        },
        "name": {
          "default": "TAO Toolkit Training",
          "type": "string"
        },
        "project": {
          "default": "TAO Toolkit",
          "type": "string"
        },
        "reinit": {
          "default": false,
          "type": "bool"
        },
        "run_id": {
          "default": "",
          "type": "string"
        },
        "save_code": {
          "default": false,
          "type": "bool"
        },
        "sync_tensorboard": {
          "default": false,
          "type": "bool"
        },
        "tags": {
          "automl_enabled": false,
          "default": [
            "tao-toolkit"
          ],
          "type": "list"
        }
      },
      "type": "collection"
    }
  },
  "required": [
    "quantize"
  ],
  "type": "object",
  "x_tao_schema": {
    "action": "train",
    "core_module": "deformable_detr",
    "model": "deformable-detr",
    "network_arch": "deformable_detr",
    "schema_action": "train",
    "schema_version": 1,
    "source": "tao-core dataclass config"
  }
}

Requirements and compatibility

Works with: Claude Code, Claude apps, OpenAI Codex, GitHub Copilot, Cursor, Gemini CLI, Kiro, OpenCode, Goose, Amp, Roo Code, JetBrains Junie, Factory Droid, Devin (ex-Windsurf), Mistral Vibe, OpenHands, Letta

“Works with” means the tool reads the open Agent Skills format; a skill written for one tool may use features others lack.

Needs: Declares allowed tools, Needs Python, Needs Node.js

The author says: Requires docker + nvidia-container-toolkit.

Security

What our scanner noticed· Medium risk

Large base64-encoded blobs

A static scan is not a guarantee. Skills are third-party content: review a skill before you let an agent use it.

Attribution and licence

Created by

NVIDIA Corporation

Publisher

NVIDIA (Official)

Source

NVIDIA/skills · skills/tao-train-deformable-detr · commit fce3cca

Licence

Apache License 2.0 (redistribution allowed)

LICENSE (added by AutoGineer from LICENSE-APACHE)
ATTRIBUTION.md (written by AutoGineer)

Synced

2026-11-08

AutoGineer is not affiliated with or endorsed by NVIDIA Corporation or NVIDIA.

Download ZIP

The ZIP holds the skill’s files, its licence files and an ATTRIBUTION.md. Download tao-train-deformable-detr.zip