tao-train-mask-grounding-dino

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Mask Grounding DINO

Mask Grounding DINO for grounded instance segmentation. Extends Grounding DINO with mask prediction head for open-set segmentation guided by text prompts.

Set train.pretrained_model_path for full model weights.

For TAO Deploy TensorRT actions (

gen_trt_engine

, TensorRT

evaluate

, and TensorRT

inference

), read

references/tao-deploy-mask-grounding-dino.md

first. Deploy spec templates live in this skill's

references/

folder with the

spec_template_deploy_*.yaml

prefix.

Mask Grounding DINO用于带定位的实例分割。它在Grounding DINO的基础上扩展了掩码预测头，支持由文本提示引导的开放集分割。

设置train.pretrained_model_path以指定完整模型权重路径。

对于TAO Deploy TensorRT动作（

gen_trt_engine

、TensorRT

evaluate

和TensorRT

inference

），请先阅读

references/tao-deploy-mask-grounding-dino.md

。部署规格模板存放在本技能的

references/

文件夹中，前缀为

spec_template_deploy_*.yaml

。

Dataclass Schemas

数据类模式

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 still requires

schemas/train.schema.json

and

references/spec_template_train.yaml

to exist and parse. Use the packaged train 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.

生成的TAO Core模式打包在

schemas/<action>.schema.json

中，

schemas/manifest.json

会列出所有可用动作。每个生成的模式还会从模式顶层的

default

字段生成

references/spec_template_<action>.yaml

。AutoML支持在

references/skill_info.yaml

的模型层通过

automl_enabled

声明。可运行的AutoML仍要求

schemas/train.schema.json

和

references/spec_template_train.yaml

存在且可解析。使用打包的训练模式来配置

automl_default_parameters

、

automl_disabled_parameters

、默认值、最小/最大边界、枚举值、选项权重、数学条件、依赖关系和常用参数。运行时不要依赖

~/tao-core

；维护人员会在打包技能库前重新生成模式/模板。

Train Action Policy

训练动作策略

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. Treat phrases like "turn off AutoML", "disable AutoML", "no HPO", or "plain training" as

automl_policy: off

for this run only; otherwise default to

auto

. When

automl_policy: auto

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.

该模型在模型层支持AutoML。在处理任何训练阶段请求之前，请阅读

references/skill_info.yaml

，并通过显式的

automl_policy

值或用户的工作流请求确定运行覆盖配置。将“turn off AutoML”、“disable AutoML”、“no HPO”或“plain training”这类短语视为本次运行的

automl_policy: off

；否则默认使用

auto

。当

automl_policy: auto

、

automl_enabled: true

且

schemas/train.schema.json

和

references/spec_template_train.yaml

已打包时，默认将训练动作通过

tao-skill-bank:tao-run-automl

路由，并传入该模型的

skill_dir

。保留数据集、规格、输出目录、GPU/平台设置、父检查点和

automl_policy

的工作流/应用覆盖配置。仅当

automl_policy: off

或打包的训练模式/模板缺失时，才使用直接模型训练；若模式缺失，需报告该模型已启用AutoML但无法运行，直到生成模式为止。

非训练动作（如

evaluate

、

inference

、

export

和部署流程）仍在本模型技能中处理。每次运行的

automl_policy

覆盖配置不会更改模型元数据。

Training Requirements

训练要求

Dataset type: segmentation
Formats: odvg, coco, coco_raw
Monitoring metric: [bbox] val_mAP@50

数据集类型： 分割
格式： odvg, coco, coco_raw
监控指标： [bbox] val_mAP@50

Per-Action Dataset Requirements

各动作的数据集要求

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

动作	规格键	来源	文件	是否为列表？
evaluate	dataset.test_data_sources	eval_dataset	image_dir: images.tar.gz, json_file: annotations.json	否
inference	dataset.infer_data_sources	inference_dataset	image_dir: images.tar.gz, classmap: label_map.txt, json_file: inference.jsonl, captions: inference.jsonl	否
quantize	dataset.train_data_sources	train_datasets	image_dir: images.tar.gz, json_file: annotations_odvg.jsonl, label_map: annotations_odvg_labelmap.json	是
quantize	dataset.val_data_sources	eval_dataset	image_dir: images.tar.gz, json_file: annotations.json	否
quantize	dataset.quant_calibration_data_sources	train_datasets	image_dir: images.tar.gz, json_file: annotations_odvg.jsonl, label_map: annotations_odvg_labelmap.json	否
train	dataset.train_data_sources	train_datasets	image_dir: images.tar.gz, json_file: annotations_odvg.jsonl, label_map: annotations_odvg_labelmap.json	是
train	dataset.val_data_sources	eval_dataset	image_dir: images.tar.gz, json_file: annotations.json	否

Typical Spec Overrides

典型规格覆盖配置

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

python

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

train (mandatory data sources):

python

{
    "train.num_gpus": 1,
    "train.num_epochs": 10,
    "train.checkpoint_interval": 10,
    "train.validation_interval": 10,
    "val_data_sources.data_type": "OD",
    "model.num_region_queries": 100,
    "dataset.train_data_sources": [{"image_dir": f"{S3_TRAIN}/images.tar.gz", "json_file": f"{S3_TRAIN}/annotations_odvg.jsonl", "label_map": f"{S3_TRAIN}/annotations_odvg_labelmap.json"}],
    "dataset.val_data_sources": {"image_dir": f"{S3_EVAL}/images.tar.gz", "json_file": f"{S3_EVAL}/annotations.json"},
}

evaluate (mandatory data sources):

python

{
    "test_data_sources.data_type": "OD",
    "dataset.test_data_sources": {"image_dir": f"{S3_EVAL}/images.tar.gz", "json_file": f"{S3_EVAL}/annotations.json"},
}

inference (mandatory data sources):

python

{
    "infer_data_sources.data_type": "OD",
    "dataset.infer_data_sources": {"image_dir": f"{S3_EVAL}/images.tar.gz", "classmap": f"{S3_EVAL}/label_map.txt", "json_file": f"{S3_EVAL}/inference.jsonl", "captions": f"{S3_EVAL}/inference.jsonl"},
}

quantize (mandatory data sources):

python

{
    "dataset.train_data_sources": [{"image_dir": f"{S3_TRAIN}/images.tar.gz", "json_file": f"{S3_TRAIN}/annotations_odvg.jsonl", "label_map": f"{S3_TRAIN}/annotations_odvg_labelmap.json"}],
    "dataset.val_data_sources": {"image_dir": f"{S3_EVAL}/images.tar.gz", "json_file": f"{S3_EVAL}/annotations.json"},
    "dataset.quant_calibration_data_sources": {"image_dir": f"{S3_TRAIN}/images.tar.gz", "json_file": f"{S3_TRAIN}/annotations_odvg.jsonl", "label_map": f"{S3_TRAIN}/annotations_odvg_labelmap.json"},
}

数据源覆盖配置对每个动作都是必填项 —— 智能体必须根据上述各动作数据集要求表构建数据源路径，并将其包含在

spec_overrides

中。

python

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

train（必填数据源）：

python

{
    "train.num_gpus": 1,
    "train.num_epochs": 10,
    "train.checkpoint_interval": 10,
    "train.validation_interval": 10,
    "val_data_sources.data_type": "OD",
    "model.num_region_queries": 100,
    "dataset.train_data_sources": [{"image_dir": f"{S3_TRAIN}/images.tar.gz", "json_file": f"{S3_TRAIN}/annotations_odvg.jsonl", "label_map": f"{S3_TRAIN}/annotations_odvg_labelmap.json"}],
    "dataset.val_data_sources": {"image_dir": f"{S3_EVAL}/images.tar.gz", "json_file": f"{S3_EVAL}/annotations.json"},
}

evaluate（必填数据源）：

python

{
    "test_data_sources.data_type": "OD",
    "dataset.test_data_sources": {"image_dir": f"{S3_EVAL}/images.tar.gz", "json_file": f"{S3_EVAL}/annotations.json"},
}

inference（必填数据源）：

python

{
    "infer_data_sources.data_type": "OD",
    "dataset.infer_data_sources": {"image_dir": f"{S3_EVAL}/images.tar.gz", "classmap": f"{S3_EVAL}/label_map.txt", "json_file": f"{S3_EVAL}/inference.jsonl", "captions": f"{S3_EVAL}/inference.jsonl"},
}

quantize（必填数据源）：

python

{
    "dataset.train_data_sources": [{"image_dir": f"{S3_TRAIN}/images.tar.gz", "json_file": f"{S3_TRAIN}/annotations_odvg.jsonl", "label_map": f"{S3_TRAIN}/annotations_odvg_labelmap.json"}],
    "dataset.val_data_sources": {"image_dir": f"{S3_EVAL}/images.tar.gz", "json_file": f"{S3_EVAL}/annotations.json"},
    "dataset.quant_calibration_data_sources": {"image_dir": f"{S3_TRAIN}/images.tar.gz", "json_file": f"{S3_TRAIN}/annotations_odvg.jsonl", "label_map": f"{S3_TRAIN}/annotations_odvg_labelmap.json"},
}

Eval Dataset

评估数据集

Optional. Validation uses COCO-format annotations even when training uses ODVG.

可选。即使训练使用ODVG格式，验证仍使用COCO格式的标注。

Important Parameters

重要参数

model.backbone: Default swin_tiny_224_1k. Same backbone options as Grounding DINO.
train.optim.lr: Learning rate. Default 2e-4. lr_backbone 2e-5. Reuses GDINOTrainExpConfig — same training setup as Grounding DINO.
model.num_queries: Object queries. Default 900.
model.has_mask: Enables mask prediction head. Default True. Adds mask/dice/rela loss coefficients.
model.num_region_queries: Number of region queries for mask prediction. Default 100.
model.loss_types: Loss components. Default [labels, boxes, masks]. Includes mask_loss_coef, dice_loss_coef, rela_loss_coef.
evaluate.ioi_threshold: IoI threshold for mask evaluation. Default 0.5.
evaluate.nms_threshold: NMS threshold. Default 0.2.
evaluate.text_threshold: Text matching threshold. Default 0.3.
dataset.has_mask: Dataset includes mask annotations. Default True. val_data_sources default data_type is "VG".

model.backbone: 默认值为swin_tiny_224_1k。与Grounding DINO的骨干网络选项相同。
train.optim.lr: 学习率。默认值为2e-4。lr_backbone为2e-5。复用GDINOTrainExpConfig —— 与Grounding DINO的训练设置相同。
model.num_queries: 对象查询数。默认值为900。
model.has_mask: 启用掩码预测头。默认值为True。添加掩码/骰子/关系损失系数。
model.num_region_queries: 掩码预测的区域查询数。默认值为100。
model.loss_types: 损失组件。默认值为[labels, boxes, masks]。包含mask_loss_coef、dice_loss_coef、rela_loss_coef。
evaluate.ioi_threshold: 掩码评估的IoI阈值。默认值为0.5。
evaluate.nms_threshold: NMS阈值。默认值为0.2。
evaluate.text_threshold: 文本匹配阈值。默认值为0.3。
dataset.has_mask: 数据集包含掩码标注。默认值为True。val_data_sources默认数据类型为"VG"。

Multi-GPU / Multi-Node

多GPU / 多节点

Launch method: Lightning-managed. Same DDP/FSDP behavior as Grounding DINO.

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`

启动方式： Lightning管理。与Grounding DINO的DDP/FSDP行为相同。

规格键	描述	默认值
`train.num_gpus`	GPU数量	1
`train.gpu_ids`	GPU设备索引	[0]
`train.num_nodes`	节点数量	1
`train.distributed_strategy`	`ddp` 或 `fsdp`	`ddp`

Hardware

硬件要求

Minimum 1 GPU(s), recommended 4 GPU(s). 24GB+ (A100 recommended) VRAM per GPU. Heavier than Grounding DINO due to mask prediction head. 24GB+ GPU memory recommended.

最少1块GPU，推荐4块GPU。每块GPU需24GB以上显存（推荐A100）。由于新增了掩码预测头，其资源消耗比Grounding DINO更高。推荐使用24GB以上显存的GPU。

Error Patterns

错误模式

CUDA out of memory: Reduce batch_size. Mask prediction adds overhead on top of Grounding DINO.

CUDA内存不足：减小batch_size。掩码预测会在Grounding DINO的基础上增加额外开销。

Spec Param / Parent Model Inference

规格参数 / 父模型推理

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

mask_grounding_dino.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
gen_trt_engine	`encryption_key`	`key`	encryption key
gen_trt_engine	`gen_trt_engine.onnx_file`	`parent_model`	model file inferred from the parent job results folder
gen_trt_engine	`gen_trt_engine.trt_engine`	`create_engine_file`	output TensorRT engine path
gen_trt_engine	`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`	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

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.

模型特定的推理映射应放在此MD文件中，而非

config.json

。生成的运行器应读取本节内容，并在

create_job()

前使用SDK助手应用映射。这与旧微服务的

infer_params.py

流程一致。

来自TAO Core

mask_grounding_dino.config.json

的推理映射：

动作	规格字段	推理函数	含义
evaluate	`encryption_key`	`key`	加密密钥
evaluate	`evaluate.checkpoint`	`parent_model`	从父任务结果文件夹推断出的模型文件
evaluate	`evaluate.trt_engine`	`parent_model`	从父任务结果文件夹推断出的模型文件
evaluate	`results_dir`	`output_dir`	当前任务结果目录
export	`encryption_key`	`key`	加密密钥
export	`export.checkpoint`	`parent_model`	从父任务结果文件夹推断出的模型文件
export	`export.onnx_file`	`create_onnx_file`	输出ONNX路径
export	`results_dir`	`output_dir`	当前任务结果目录
gen_trt_engine	`encryption_key`	`key`	加密密钥
gen_trt_engine	`gen_trt_engine.onnx_file`	`parent_model`	从父任务结果文件夹推断出的模型文件
gen_trt_engine	`gen_trt_engine.trt_engine`	`create_engine_file`	输出TensorRT引擎路径
gen_trt_engine	`results_dir`	`output_dir`	当前任务结果目录
inference	`encryption_key`	`key`	加密密钥
inference	`inference.checkpoint`	`parent_model`	从父任务结果文件夹推断出的模型文件
inference	`inference.trt_engine`	`parent_model`	从父任务结果文件夹推断出的模型文件
inference	`results_dir`	`output_dir`	当前任务结果目录
quantize	`encryption_key`	`key`	加密密钥
quantize	`quantize.model_path`	`parent_model`	从父任务结果文件夹推断出的模型文件
quantize	`results_dir`	`output_dir`	当前任务结果目录
train	`encryption_key`	`key`	加密密钥
train	`model.pretrained_backbone_path`	`ptm_if_no_resume_model`	无恢复检查点时的预训练模型
train	`results_dir`	`output_dir`	当前任务结果目录
train	`train.pretrained_model_path`	`ptm_if_no_resume_model`	无恢复检查点时的预训练模型
train	`train.resume_training_checkpoint_path`	`resume_model`	从当前任务结果文件夹推断出的模型文件

对于

parent_model

或

parent_model_folder

，传入上游训练/导出/AutoML子任务ID作为

parent_job_id

。SDK会列出父任务结果文件夹，过滤检查点工件，并返回选中的模型文件或文件夹。请勿将这些映射添加回

config.json

，也不要修改生成的运行器脚本来猜测检查点路径。

Deployment

部署

tao-deploy-mask-grounding-dino — Mask Grounding DINO deploy workflow for TensorRT engine generation, TensorRT evaluation, and TensorRT inference using TAO Deploy.

tao-deploy-mask-grounding-dino —— Mask Grounding DINO的部署工作流，用于使用TAO Deploy生成TensorRT引擎、进行TensorRT评估和TensorRT推理。