Tao Train Ocdnet

OCDNet

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).

OCDNet for scene text detection. Detects arbitrary-oriented text regions in natural images using a differentiable binarization approach.

Set model.pretrained_model_path for pretrained weights.

For TAO Deploy TensorRT actions (gen_trt_engine, TensorRT evaluate, and TensorRT inference), read references/tao-deploy-ocdnet.md first. Deploy spec templates live in this skill's references/ folder with the spec_template_deploy_*.yaml prefix.

The PyT OCDNet CLI supports train, evaluate, export, inference, prune, quantize, and default_specs. It does not expose PyT-side retrain or gen_trt_engine subcommands. The model skill exposes retrain by running ocdnet train with model.load_pruned_graph: true and model.pruned_graph_path. Resume from an epoch checkpoint uses ocdnet train plus train.resume_training_checkpoint_path. TensorRT engine generation is owned by the deploy workflow.

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.

For AutoML train, use train_loss_epoch or train_loss as the optimization metric with direction=minimize. The Lightning progress log emits train_loss_epoch, and TAO status.json records the same final value under train_loss. For one-epoch local AutoML smoke runs, set train.lr_scheduler.args.warmup_epoch: 0; leaving warmup equal to the epoch budget causes the trainer to fail before a recommendation can report a metric. 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: ocdnet
• Formats: default
• AutoML training metric: train_loss (the status logger's final train_loss_epoch value), with direction=minimize
• AutoML metric contract: Use train_loss emitted during training and minimize it. Treat train_loss_epoch as a log fallback alias only; use standalone hmean solely to validate the selected checkpoint.
• Standalone evaluation metric: hmean, with direction=maximize

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. OCDNet does not unpack dataset archives at runtime. If the source is train.tar.gz, test.tar.gz, or img.tar.gz, extract it first and pass the split folder or image folder into the spec. The split folder must contain img/ and gt/; alternatively, pass a UTF-8 datalist text file whose lines map image paths to label paths.

TRAIN_ROOT = "/path/to/extracted/train"
EVAL_ROOT = "/path/to/extracted/test"
INFER_IMG_DIR = "/path/to/extracted/test/img"
CALIB_IMG_DIR = "/path/to/extracted/train/img"

train (mandatory data sources):

{
    "train.num_epochs": 30,
    "train.checkpoint_interval": 10,
    "train.validation_interval": 10,
    "train.num_gpus": 1,
    "dataset.train_dataset.loader.batch_size": 16,
    "dataset.train_dataset.data_path": [TRAIN_ROOT],
    "dataset.validate_dataset.data_path": [EVAL_ROOT],
}

evaluate (mandatory data sources):

{
    "evaluate.checkpoint": "<selected train/AutoML checkpoint>",
    "dataset.validate_dataset.data_path": [EVAL_ROOT],
}

inference (mandatory data sources):

{
    "inference.checkpoint": "<selected train/AutoML checkpoint>",
    "inference.input_folder": INFER_IMG_DIR,
}

prune (mandatory data sources):

{
    "prune.checkpoint": "<selected train/AutoML checkpoint>",
    "dataset.validate_dataset.data_path": [EVAL_ROOT],
}

quantize (mandatory data sources):

{
    "quantize.model_path": "<selected train checkpoint or exported ONNX>",
    "dataset.train_dataset.data_path": [TRAIN_ROOT],
    "dataset.validate_dataset.data_path": [EVAL_ROOT],
    "dataset.quant_calibration_dataset.images_dir": CALIB_IMG_DIR,
}

resume training (mandatory data sources):

{
    "train.resume_training_checkpoint_path": "<exact model_epoch checkpoint>",
    "dataset.train_dataset.data_path": [TRAIN_ROOT],
    "dataset.validate_dataset.data_path": [EVAL_ROOT],
}

retrain from prune output (mandatory data sources):

{
    "model.load_pruned_graph": True,
    "model.pruned_graph_path": "<selected prune output>",
    "dataset.train_dataset.data_path": [TRAIN_ROOT],
    "dataset.validate_dataset.data_path": [EVAL_ROOT],
}

default_specs:

{
    "results_dir": "<writable output directory>",
}

Eval Dataset

Optional. Test dataset provided as separate tarball.

Important Parameters

• model.backbone: Default deformable_resnet18. Deformable convolutions improve text region detection for irregular text.
• train.optimizer.args.lr: Learning rate. Default 0.001 (Adam).
• postprocess.thresh: Binarization threshold for text region extraction.
• postprocess.box_thresh: Box confidence threshold for filtering detections.

Multi-GPU / Multi-Node

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

• ddp with activation checkpointing: find_unused_parameters=False
• ddp without: find_unused_parameters=True
• fsdp forces FP16
• deepspeed_stage_3_offload is uniquely supported for OCDNet (forces FP16)
• FAN backbones auto-enable sync_batchnorm