Tao Train Deformable Detr

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

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.