tao-train-optical-inspection

Compare original and translation side by side

🇺🇸

Original

English

🇨🇳

Translation

Chinese

Optical Inspection

光学检测

Optical inspection for defect detection using Siamese networks. Compares image pairs to detect manufacturing defects, anomalies, or quality issues.

Set train.pretrained_model_path for pretrained Siamese weights.

For TAO Deploy TensorRT actions (

gen_trt_engine

, TensorRT

evaluate

, and TensorRT

inference

), read

references/tao-deploy-optical-inspection.md

first. Deploy spec templates live in this skill's

references/

folder with the

spec_template_deploy_*.yaml

prefix.

使用Siamese网络进行缺陷检测的光学检测方案。通过对比图像对来检测制造缺陷、异常或质量问题。

设置train.pretrained_model_path以加载预训练的Siamese权重。

对于TAO Deploy TensorRT操作（

gen_trt_engine

、TensorRT

evaluate

和TensorRT

inference

），请先阅读

references/tao-deploy-optical-inspection.md

。部署规格模板位于本技能的

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

列出了可用操作。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、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

；维护人员在打包技能库前会重新生成模式/模板。

Train Action Policy

训练操作策略

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。处理任何训练阶段请求前，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来解析运行覆盖配置。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，默认通过

tao-skill-bank:tao-run-automl

结合本模型的

skill_dir

来路由训练操作。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，请提示用户该模型已启用AutoML但无法运行，需先生成模式。

非训练操作（如

evaluate

、

inference

、

export

和部署流程）仍在本模型技能中执行。每次运行的

automl_policy

覆盖配置不会改变模型元数据。

Training Requirements

训练要求

Dataset type: optical_inspection
Formats: default
Monitoring metric: val_acc

数据集类型： optical_inspection
格式： default
监控指标： val_acc

Per-Action Dataset Requirements

各操作的数据集要求

Action	Spec Key	Source	Files	List?
evaluate	dataset.test_dataset.images_dir	eval_dataset	images.tar.gz	No
evaluate	dataset.test_dataset.csv_path	eval_dataset	dataset.csv	No
gen_trt_engine	gen_trt_engine.tensorrt.calibration.cal_image_dir	calibration_dataset	images.tar.gz	Yes
inference	dataset.infer_dataset.images_dir	inference_dataset	images.tar.gz	No
inference	dataset.infer_dataset.csv_path	inference_dataset	dataset.csv	No
train	dataset.train_dataset.images_dir	train_datasets	images.tar.gz	No
train	dataset.train_dataset.csv_path	train_datasets	dataset.csv	No
train	dataset.validation_dataset.images_dir	eval_dataset	images.tar.gz	No
train	dataset.validation_dataset.csv_path	eval_dataset	dataset.csv	No
train	dataset.test_dataset.images_dir	eval_dataset	images.tar.gz	No
train	dataset.test_dataset.csv_path	eval_dataset	dataset.csv	No

操作	规格键	来源	文件	是否为列表？
evaluate	dataset.test_dataset.images_dir	eval_dataset	images.tar.gz	No
evaluate	dataset.test_dataset.csv_path	eval_dataset	dataset.csv	No
gen_trt_engine	gen_trt_engine.tensorrt.calibration.cal_image_dir	calibration_dataset	images.tar.gz	Yes
inference	dataset.infer_dataset.images_dir	inference_dataset	images.tar.gz	No
inference	dataset.infer_dataset.csv_path	inference_dataset	dataset.csv	No
train	dataset.train_dataset.images_dir	train_datasets	images.tar.gz	No
train	dataset.train_dataset.csv_path	train_datasets	dataset.csv	No
train	dataset.validation_dataset.images_dir	eval_dataset	images.tar.gz	No
train	dataset.validation_dataset.csv_path	eval_dataset	dataset.csv	No
train	dataset.test_dataset.images_dir	eval_dataset	images.tar.gz	No
train	dataset.test_dataset.csv_path	eval_dataset	dataset.csv	No

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_epochs": 30,
    "train.checkpoint_interval": 10,
    "train.validation_interval": 10,
    "train.num_gpus": 1,
    "dataset.train_dataset.images_dir": f"{S3_TRAIN}/images.tar.gz",
    "dataset.train_dataset.csv_path": f"{S3_TRAIN}/dataset.csv",
    "dataset.validation_dataset.images_dir": f"{S3_EVAL}/images.tar.gz",
    "dataset.validation_dataset.csv_path": f"{S3_EVAL}/dataset.csv",
    "dataset.test_dataset.images_dir": f"{S3_EVAL}/images.tar.gz",
    "dataset.test_dataset.csv_path": f"{S3_EVAL}/dataset.csv",
}

gen_trt_engine (mandatory data sources):

python

{
    "gen_trt_engine.tensorrt.data_type": "fp16",
    "gen_trt_engine.tensorrt.calibration.cal_image_dir": [f"{S3_TRAIN}/images.tar.gz"],
}

evaluate (mandatory data sources):

python

{
    "dataset.test_dataset.images_dir": f"{S3_EVAL}/images.tar.gz",
    "dataset.test_dataset.csv_path": f"{S3_EVAL}/dataset.csv",
}

inference (mandatory data sources):

python

{
    "dataset.infer_dataset.images_dir": f"{S3_EVAL}/images.tar.gz",
    "dataset.infer_dataset.csv_path": f"{S3_EVAL}/dataset.csv",
}

数据源覆盖配置对每个操作都是必填项——Agent必须根据上述“各操作的数据集要求”表格构建数据源路径，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_epochs": 30,
    "train.checkpoint_interval": 10,
    "train.validation_interval": 10,
    "train.num_gpus": 1,
    "dataset.train_dataset.images_dir": f"{S3_TRAIN}/images.tar.gz",
    "dataset.train_dataset.csv_path": f"{S3_TRAIN}/dataset.csv",
    "dataset.validation_dataset.images_dir": f"{S3_EVAL}/images.tar.gz",
    "dataset.validation_dataset.csv_path": f"{S3_EVAL}/dataset.csv",
    "dataset.test_dataset.images_dir": f"{S3_EVAL}/images.tar.gz",
    "dataset.test_dataset.csv_path": f"{S3_EVAL}/dataset.csv",
}

gen_trt_engine（必填数据源）：

python

{
    "gen_trt_engine.tensorrt.data_type": "fp16",
    "gen_trt_engine.tensorrt.calibration.cal_image_dir": [f"{S3_TRAIN}/images.tar.gz"],
}

evaluate（必填数据源）：

python

{
    "dataset.test_dataset.images_dir": f"{S3_EVAL}/images.tar.gz",
    "dataset.test_dataset.csv_path": f"{S3_EVAL}/dataset.csv",
}

inference（必填数据源）：

python

{
    "dataset.infer_dataset.images_dir": f"{S3_EVAL}/images.tar.gz",
    "dataset.infer_dataset.csv_path": f"{S3_EVAL}/dataset.csv",
}

Eval Dataset

评估数据集

Optional. Eval dataset uses same format (images + CSV).

可选。评估数据集使用相同格式（图像+CSV）。

Important Parameters

重要参数

model.model_type: Siamese variant. Options include Siamese, Siamese_3.
model.model_backbone: Default custom.
model.embedding_vectors: Number of embedding dimensions. Default 5.
train.optim.lr: Learning rate. Default 5e-4.
dataset.num_input: Number of input images per comparison.
dataset.input_map: Mapping of input channels / image pairs.

model.model_type： Siamese变体。选项包括Siamese、Siamese_3。
model.model_backbone： 默认值为custom。
model.embedding_vectors： 嵌入维度数量。默认值为5。
train.optim.lr： 学习率。默认值为5e-4。
dataset.num_input： 每次对比的输入图像数量。
dataset.input_map： 输入通道/图像对的映射。

Multi-GPU / Multi-Node

多GPU/多节点

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]

Strategy:
```
auto
```
(Lightning picks best strategy automatically)
No explicit
```
num_nodes
```
or
```
distributed_strategy
```
config — single-node only
Lightweight Siamese network, single GPU typically sufficient

启动方式： Lightning托管（单个

python

进程，Lightning生成工作线程）。

规格键	描述	默认值
`train.num_gpus`	GPU数量	1
`train.gpu_ids`	GPU设备索引	[0]

策略：
```
auto
```
（Lightning自动选择最佳策略）
无明确的
```
num_nodes
```
或
```
distributed_strategy
```
配置——仅支持单节点
Siamese网络轻量化，通常单GPU即可满足需求

Hardware

硬件要求

Minimum 1 GPU(s), recommended 1 GPU(s). 8GB+ VRAM per GPU. Siamese networks for inspection are lightweight. Single GPU sufficient.

最少1块GPU，推荐1块GPU。每块GPU需8GB以上显存。用于检测的Siamese网络轻量化，单GPU足够。

Error Patterns

错误模式

CSV format error: Ensure dataset.csv has the correct column format for image pair paths and labels.

CSV格式错误： 确保dataset.csv具有正确的列格式，包含图像对路径和标签。

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

optical_inspection.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	`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.tensorrt.calibration.cal_cache_file`	`create_cal_cache`	calibration cache path
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
train	`encryption_key`	`key`	encryption key
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

optical_inspection.config.json

的推理映射：

操作	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	`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.tensorrt.calibration.cal_cache_file`	`create_cal_cache`	校准缓存路径
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
train	`encryption_key`	`key`	加密密钥
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

，将上游训练/导出/AutoML子任务ID作为

parent_job_id

传入。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以猜测检查点路径。

Deployment

部署

tao-deploy-optical-inspection — Optical Inspection deploy workflow for TensorRT engine generation, TensorRT evaluation, and TensorRT inference using TAO Deploy.

tao-deploy-optical-inspection — 使用TAO Deploy进行TensorRT引擎生成、TensorRT评估和TensorRT推理的光学检测部署工作流。