You've already forked DataMate
feat(annotation): 自动标注任务支持非图像类型数据集（TEXT/AUDIO/VIDEO）
移除自动标注任务创建流程中的 IMAGE-only 限制，使 TEXT、AUDIO、VIDEO 类型数据集均可用于自动标注任务。 - 新增数据库迁移：t_dm_auto_annotation_tasks 表添加 dataset_type 列 - 后端 schema/API/service 全链路传递 dataset_type - Worker 动态构建 sample key（image/text/audio/video）和输出目录 - 前端移除数据集类型校验，下拉框显示数据集类型标识 - 输出数据集继承源数据集类型，不再硬编码为 IMAGE - 保持向后兼容：默认值为 IMAGE，worker 有元数据回退和目录 fallback Co-Authored-By: Claude Opus 4.6 <noreply@anthropic.com>
This commit is contained in:
@@ -197,7 +197,7 @@ class AnnotationResult(Base):
|
||||
return f"<AnnotationResult(id={self.id}, project_id={self.project_id}, file_id={self.file_id})>"
|
||||
|
||||
|
||||
class AutoAnnotationTask(Base):
|
||||
class AutoAnnotationTask(Base):
|
||||
"""自动标注任务模型，对应表 t_dm_auto_annotation_tasks"""
|
||||
|
||||
__tablename__ = "t_dm_auto_annotation_tasks"
|
||||
@@ -206,94 +206,98 @@ class AutoAnnotationTask(Base):
|
||||
String(36), primary_key=True, default=lambda: str(uuid.uuid4()), comment="UUID"
|
||||
)
|
||||
name = Column(String(255), nullable=False, comment="任务名称")
|
||||
dataset_id = Column(String(36), nullable=False, comment="数据集ID")
|
||||
dataset_name = Column(
|
||||
String(255), nullable=True, comment="数据集名称（冗余字段，方便查询）"
|
||||
)
|
||||
created_by = Column(String(255), nullable=True, comment="任务创建人")
|
||||
config = Column(JSON, nullable=False, comment="任务配置（模型规模、置信度等）")
|
||||
file_ids = Column(
|
||||
JSON, nullable=True, comment="要处理的文件ID列表，为空则处理数据集所有图像"
|
||||
)
|
||||
status = Column(
|
||||
String(50),
|
||||
nullable=False,
|
||||
default="pending",
|
||||
comment="任务状态: pending/running/completed/failed/stopped",
|
||||
)
|
||||
task_mode = Column(
|
||||
String(32),
|
||||
nullable=False,
|
||||
default="legacy_yolo",
|
||||
comment="任务模式: legacy_yolo/pipeline",
|
||||
)
|
||||
executor_type = Column(
|
||||
String(32),
|
||||
nullable=False,
|
||||
default="annotation_local",
|
||||
comment="执行器类型",
|
||||
)
|
||||
pipeline = Column(JSON, nullable=True, comment="算子编排定义")
|
||||
progress = Column(Integer, default=0, comment="任务进度 0-100")
|
||||
stop_requested = Column(Boolean, default=False, comment="是否请求停止")
|
||||
total_images = Column(Integer, default=0, comment="总图片数")
|
||||
processed_images = Column(Integer, default=0, comment="已处理图片数")
|
||||
detected_objects = Column(Integer, default=0, comment="检测到的对象总数")
|
||||
output_path = Column(String(500), nullable=True, comment="输出路径")
|
||||
output_dataset_id = Column(String(36), nullable=True, comment="输出数据集ID")
|
||||
error_message = Column(Text, nullable=True, comment="错误信息")
|
||||
created_at = Column(
|
||||
TIMESTAMP, server_default=func.current_timestamp(), comment="创建时间"
|
||||
)
|
||||
dataset_id = Column(String(36), nullable=False, comment="数据集ID")
|
||||
dataset_name = Column(
|
||||
String(255), nullable=True, comment="数据集名称（冗余字段，方便查询）"
|
||||
)
|
||||
dataset_type = Column(
|
||||
String(50), nullable=False, default="IMAGE",
|
||||
comment="数据集类型: IMAGE/TEXT/AUDIO/VIDEO",
|
||||
)
|
||||
created_by = Column(String(255), nullable=True, comment="任务创建人")
|
||||
config = Column(JSON, nullable=False, comment="任务配置（模型规模、置信度等）")
|
||||
file_ids = Column(
|
||||
JSON, nullable=True, comment="要处理的文件ID列表，为空则处理数据集所有图像"
|
||||
)
|
||||
status = Column(
|
||||
String(50),
|
||||
nullable=False,
|
||||
default="pending",
|
||||
comment="任务状态: pending/running/completed/failed/stopped",
|
||||
)
|
||||
task_mode = Column(
|
||||
String(32),
|
||||
nullable=False,
|
||||
default="legacy_yolo",
|
||||
comment="任务模式: legacy_yolo/pipeline",
|
||||
)
|
||||
executor_type = Column(
|
||||
String(32),
|
||||
nullable=False,
|
||||
default="annotation_local",
|
||||
comment="执行器类型",
|
||||
)
|
||||
pipeline = Column(JSON, nullable=True, comment="算子编排定义")
|
||||
progress = Column(Integer, default=0, comment="任务进度 0-100")
|
||||
stop_requested = Column(Boolean, default=False, comment="是否请求停止")
|
||||
total_images = Column(Integer, default=0, comment="总图片数")
|
||||
processed_images = Column(Integer, default=0, comment="已处理图片数")
|
||||
detected_objects = Column(Integer, default=0, comment="检测到的对象总数")
|
||||
output_path = Column(String(500), nullable=True, comment="输出路径")
|
||||
output_dataset_id = Column(String(36), nullable=True, comment="输出数据集ID")
|
||||
error_message = Column(Text, nullable=True, comment="错误信息")
|
||||
created_at = Column(
|
||||
TIMESTAMP, server_default=func.current_timestamp(), comment="创建时间"
|
||||
)
|
||||
updated_at = Column(
|
||||
TIMESTAMP,
|
||||
server_default=func.current_timestamp(),
|
||||
onupdate=func.current_timestamp(),
|
||||
comment="更新时间",
|
||||
)
|
||||
started_at = Column(TIMESTAMP, nullable=True, comment="任务启动时间")
|
||||
heartbeat_at = Column(TIMESTAMP, nullable=True, comment="worker心跳时间")
|
||||
run_token = Column(String(64), nullable=True, comment="运行令牌")
|
||||
completed_at = Column(TIMESTAMP, nullable=True, comment="完成时间")
|
||||
deleted_at = Column(TIMESTAMP, nullable=True, comment="删除时间（软删除）")
|
||||
server_default=func.current_timestamp(),
|
||||
onupdate=func.current_timestamp(),
|
||||
comment="更新时间",
|
||||
)
|
||||
started_at = Column(TIMESTAMP, nullable=True, comment="任务启动时间")
|
||||
heartbeat_at = Column(TIMESTAMP, nullable=True, comment="worker心跳时间")
|
||||
run_token = Column(String(64), nullable=True, comment="运行令牌")
|
||||
completed_at = Column(TIMESTAMP, nullable=True, comment="完成时间")
|
||||
deleted_at = Column(TIMESTAMP, nullable=True, comment="删除时间（软删除）")
|
||||
|
||||
def __repr__(self) -> str: # pragma: no cover - repr 简单返回
|
||||
return f"<AutoAnnotationTask(id={self.id}, name={self.name}, status={self.status})>"
|
||||
|
||||
@property
|
||||
def is_deleted(self) -> bool:
|
||||
"""检查是否已被软删除"""
|
||||
return self.deleted_at is not None
|
||||
|
||||
|
||||
class AnnotationTaskOperatorInstance(Base):
|
||||
"""自动标注任务内算子实例模型，对应表 t_dm_annotation_task_operator_instance"""
|
||||
|
||||
__tablename__ = "t_dm_annotation_task_operator_instance"
|
||||
|
||||
id = Column(BigInteger, primary_key=True, autoincrement=True, comment="自增主键")
|
||||
task_id = Column(String(36), nullable=False, comment="自动标注任务ID")
|
||||
op_index = Column(Integer, nullable=False, comment="算子顺序（从1开始）")
|
||||
operator_id = Column(String(64), nullable=False, comment="算子ID（raw_id）")
|
||||
settings_override = Column(JSON, nullable=True, comment="任务级算子参数覆盖")
|
||||
inputs = Column(String(64), nullable=True, comment="输入模态")
|
||||
outputs = Column(String(64), nullable=True, comment="输出模态")
|
||||
created_at = Column(
|
||||
TIMESTAMP,
|
||||
server_default=func.current_timestamp(),
|
||||
nullable=False,
|
||||
comment="创建时间",
|
||||
)
|
||||
updated_at = Column(
|
||||
TIMESTAMP,
|
||||
server_default=func.current_timestamp(),
|
||||
onupdate=func.current_timestamp(),
|
||||
nullable=False,
|
||||
comment="更新时间",
|
||||
)
|
||||
|
||||
__table_args__ = (
|
||||
UniqueConstraint("task_id", "op_index", name="uk_task_op_index"),
|
||||
Index("idx_task_id", "task_id"),
|
||||
Index("idx_operator_id", "operator_id"),
|
||||
)
|
||||
def is_deleted(self) -> bool:
|
||||
"""检查是否已被软删除"""
|
||||
return self.deleted_at is not None
|
||||
|
||||
|
||||
class AnnotationTaskOperatorInstance(Base):
|
||||
"""自动标注任务内算子实例模型，对应表 t_dm_annotation_task_operator_instance"""
|
||||
|
||||
__tablename__ = "t_dm_annotation_task_operator_instance"
|
||||
|
||||
id = Column(BigInteger, primary_key=True, autoincrement=True, comment="自增主键")
|
||||
task_id = Column(String(36), nullable=False, comment="自动标注任务ID")
|
||||
op_index = Column(Integer, nullable=False, comment="算子顺序（从1开始）")
|
||||
operator_id = Column(String(64), nullable=False, comment="算子ID（raw_id）")
|
||||
settings_override = Column(JSON, nullable=True, comment="任务级算子参数覆盖")
|
||||
inputs = Column(String(64), nullable=True, comment="输入模态")
|
||||
outputs = Column(String(64), nullable=True, comment="输出模态")
|
||||
created_at = Column(
|
||||
TIMESTAMP,
|
||||
server_default=func.current_timestamp(),
|
||||
nullable=False,
|
||||
comment="创建时间",
|
||||
)
|
||||
updated_at = Column(
|
||||
TIMESTAMP,
|
||||
server_default=func.current_timestamp(),
|
||||
onupdate=func.current_timestamp(),
|
||||
nullable=False,
|
||||
comment="更新时间",
|
||||
)
|
||||
|
||||
__table_args__ = (
|
||||
UniqueConstraint("task_id", "op_index", name="uk_task_op_index"),
|
||||
Index("idx_task_id", "task_id"),
|
||||
Index("idx_operator_id", "operator_id"),
|
||||
)
|
||||
|
||||
Reference in New Issue
Block a user