Refactor: predict, train 리팩토링

ai/app/api/yolo/detection.py

@@ -1,17 +1,16 @@
 import json
 
-from fastapi import APIRouter, HTTPException, Response
+from fastapi import APIRouter, HTTPException
 from schemas.predict_request import PredictRequest
 from schemas.train_request import TrainRequest
 from schemas.predict_response import PredictResponse, LabelData
+from schemas.train_report_data import ReportData
 from services.load_model import load_detection_model
 from services.create_model import save_model
 from utils.dataset_utils import split_data
-from utils.file_utils import get_dataset_root_path, process_directories, process_image_and_label, join_path, get_model_path
+from utils.file_utils import get_dataset_root_path, process_directories, process_image_and_label, join_path
-from utils.websocket_utils import WebSocketClient, WebSocketConnectionException
 from utils.slackMessage import send_slack_message
 import asyncio
-import time
 
 
 router = APIRouter()
@@ -21,32 +20,20 @@ async def detection_predict(request: PredictRequest):
 
     send_slack_message(f"predict 요청{request}", status="success")
 
-    # Spring 서버의 WebSocket URL
-    # TODO: 배포 시 변경
-    # spring_server_ws_url = f"ws://localhost:8080/ws"
-    
-    # WebSocketClient 인스턴스 생성
-    # ws_client = WebSocketClient(spring_server_ws_url)
-
     # 모델 로드
-    model = load_model(request)
+    model = get_model(request)
     
     # 모델 레이블 카테고리 연결
     classes = list(request.label_map) if request.label_map else None
 
-    # 결과를 저장할 리스트
+    # 이미지 데이터 정리
-    response = []
+    url_list = list(map(lambda x:x.image_url, request.image_list))
 
-    # 웹소켓 연결
-    # await connect_to_websocket(ws_client)
 
     # 추론
     try:
-        for idx, image in enumerate(request.image_list):
+        results = run_predictions(model, url_list, request, classes)
-            result = run_predictions(model, image, request, classes)
+        response = [process_prediction_result(result, image, request.label_map) for result, image in zip(results,request.image_list)]
-            response_item = process_prediction_result(result, request, image)
-            response.append(response_item)
-
         return response
 
     except Exception as e:
@@ -54,33 +41,18 @@ async def detection_predict(request: PredictRequest):
         send_slack_message(f"프로젝트 ID: {request.project_id} - 실패! 에러: {str(e)}",status="error")
         raise HTTPException(status_code=500, detail="Prediction process failed")
 
-    # finally:
-    #     send_slack_message("종료")
-        # if ws_client.is_connected():
-        #     await ws_client.close()
-
 # 모델 로드
-def load_model(request: PredictRequest):
+def get_model(request: PredictRequest):
     try:
-        model_path = request.m_key and get_model_path(request.project_id, request.m_key)
+        return load_detection_model(request.project_id, request.m_key)
-        return load_detection_model(model_path=model_path)
     except Exception as e:
         raise HTTPException(status_code=500, detail="load model exception: " + str(e))
 
-# 웹소켓 연결
-async def connect_to_websocket(ws_client):
-    try:
-        await ws_client.connect()
-        if not ws_client.is_connected():
-            raise WebSocketConnectionException("웹 소켓 연결 실패")
-    except Exception as e:
-        raise HTTPException(status_code=500, detail="websocket connect failed: " + str(e))
-
 # 추론 실행 함수
 def run_predictions(model, image, request, classes):
     try:
         predict_results = model.predict(
-            source=image.image_url,
+        source=image,
         iou=request.iou_threshold,
         conf=request.conf_threshold,
         classes=classes
@@ -89,8 +61,9 @@ def run_predictions(model, image, request, classes):
     except Exception as e:
         raise HTTPException(status_code=500, detail="model predict exception: " + str(e))
     
+
 # 추론 결과 처리 함수
-def process_prediction_result(result, request, image):
+def process_prediction_result(result, image, label_map):
     label_data = LabelData(
         version="0.0.0",
         task_type="det",
@@ -102,7 +75,7 @@ def process_prediction_result(result, request, image):
                     [summary['box']['x1'], summary['box']['y1']],
                     [summary['box']['x2'], summary['box']['y2']]
                 ],
-                "group_id": request.label_map[summary['class']] if request.label_map else summary['class'],
+                "group_id": label_map[summary['class']] if label_map else summary['class'],
                 "shape_type": "rectangle",
                 "flags": {}
             }
@@ -119,24 +92,18 @@ def process_prediction_result(result, request, image):
         data=json.dumps(label_data.dict())
     )
 
+
+
 @router.post("/train")
 async def detection_train(request: TrainRequest):
-    # Spring 서버의 WebSocket URL
-    # TODO: 배포시에 변경
-    spring_server_ws_url = f"ws://localhost:8080/ws"
 
-    # WebSocketClient 인스턴스 생성
+    send_slack_message(f"train 요청{request}", status="success")
-    ws_client = WebSocketClient(spring_server_ws_url)
 
     # 데이터셋 루트 경로 얻기
     dataset_root_path = get_dataset_root_path(request.project_id)
 
     # 모델 로드
-    try:
+    model = get_model(request)
-        model_path = request.m_key and get_model_path(request.project_id, request.m_key)
-        model = load_detection_model(model_path=model_path)
-    except Exception as e:
-        raise HTTPException(status_code=500, detail="load model exception: " + str(e))
 
     # 학습할 모델 카테고리 정리 카테고리가 추가되는 경우에 추가할 수 있게
     names = model.names
@@ -145,41 +112,19 @@ async def detection_train(request: TrainRequest):
     process_directories(dataset_root_path, names)
 
     # 레이블 맵
-    inverted_label_map = None
+    inverted_label_map = {value: key for key, value in request.label_map.items()} if request.label_map else None
-    if request.label_map:
-        inverted_label_map =  {value: key for key, value in request.label_map.items()}
 
     # 학습 데이터 분류
     train_data, val_data = split_data(request.data, request.ratio)
 
     try:
-        await ws_client.connect()
-        if not ws_client.is_connected():
-            raise WebSocketConnectionException()
-
         # 학습 데이터 처리
-        total_data = len(train_data)
+        for data in train_data:
-        for idx, data in enumerate(train_data):
+            process_image_and_label(data, dataset_root_path, "train", inverted_label_map)
-            # TODO: 비동기면 await 연결
-            # process_image_and_label(data, dataset_root_path, "train")
-            
-            # 진행률 계산
-            progress = (idx + 1) / total_data * 100
-            
-            await ws_client.send_message("/app/ai/train/progress", f"학습 데이터 처리 중 {request.project_id}: {progress:.2f}% 완료")
 
         # 검증 데이터 처리
-        total_val_data = len(val_data)
+        for data in val_data:
-        for idx, data in enumerate(val_data):
+            process_image_and_label(data, dataset_root_path, "val", inverted_label_map)
-            # TODO: 비동기면 await 연결
-            # process_image_and_label(data, dataset_root_path, "val")
-
-            # 진행률 계산
-            progress = (idx + 1) / total_val_data * 100
-            # 웹소켓으로 메시지 전송 (필요할 경우 추가)
-            await ws_client.send_message("/app/ai/val/progress", f"검증 데이터 처리 중 {request.project_id}: {progress:.2f}% 완료")
-
-        from ultralytics.models.yolo.detect import DetectionTrainer
 
         def send_data(trainer):
             # 첫번째 epoch는 스킵
@@ -188,52 +133,23 @@ async def detection_train(request: TrainRequest):
 
             ## 남은 시간 계산(초)
             left_epochs = trainer.epochs-trainer.epoch
-            left_sec = left_epochs*trainer.epoch_time
+            left_seconds = left_epochs*trainer.epoch_time
             ## 로스 box_loss, cls_loss, dfl_loss
             loss = trainer.label_loss_items(loss_items=trainer.loss_items)
-            data = {
+            data = ReportData(
-                "epoch": trainer.epoch,             # 현재 에포크
+                epoch= trainer.epoch,             # 현재 에포크
-                "total_epochs": trainer.epochs,     # 전체 에포크
+                total_epochs= trainer.epochs,     # 전체 에포크
-                "box_loss": loss["box_loss"],       # box loss
+                box_loss= loss["train/box_loss"], # box loss
-                "cls_loss": loss["cls_loss"],       # cls loss
+                cls_loss= loss["train/cls_loss"], # cls loss
-                "dfl_loss": loss["dfl_loss"],       # dfl loss
+                dfl_loss= loss["train/dfl_loss"], # dfl loss
-                "fitness": trainer.fitness,         # 적합도
+                fitness= trainer.fitness,         # 적합도
-                "epoch_time": trainer.epoch_time,   # 지난 에포크 걸린 시간 (에포크 시작 기준으로 결정)
+                epoch_time= trainer.epoch_time,   # 지난 에포크 걸린 시간 (에포크 시작 기준으로 결정)
-                "left_second": left_sec             # 남은 시간(초)
+                left_seconds= left_seconds        # 남은 시간(초)
-            }
+            )
             # 데이터 전송
-            ws_client.send_message() 
 
         model.add_callback("on_train_epoch_start", send_data)
 
-        model.train(
-            data=join_path(dataset_root_path, "dataset.yaml"),
-            name=join_path(dataset_root_path, "result"),
-            epochs=request.epochs,
-            batch=request.batch,
-            lr0=request.lr0,
-            lrf=request.lrf,
-            optimizer=request.optimizer
-        )
-
-        model_key = save_model(project_id=request.project_id, path=join_path(dataset_root_path, "result", "weights", "best.pt"))
-
-        return {"model_key": model_key, "results": results.results_dict}
-    
-    except WebSocketConnectionException as e:
-
-         # 학습 데이터 처리
-        total_data = len(train_data)
-        for idx, data in enumerate(train_data):
-            # TODO: 비동기면 await 연결
-            process_image_and_label(data, dataset_root_path, "train", inverted_label_map)
-
-        # 검증 데이터 처리
-        total_val_data = len(val_data)
-        for idx, data in enumerate(val_data):
-            # TODO: 비동기면 await 연결
-            process_image_and_label(data, dataset_root_path, "val", inverted_label_map)
-
         results = model.train(
             data=join_path(dataset_root_path, "dataset.yaml"),
             name=join_path(dataset_root_path, "result"),
@@ -247,14 +163,8 @@ async def detection_train(request: TrainRequest):
         model_key = save_model(project_id=request.project_id, path=join_path(dataset_root_path, "result", "weights", "best.pt"))
 
         return {"model_key": model_key, "results": results.results_dict}
-
-
     except Exception as e:
-        print(f"Training process failed: {str(e)}")
-        raise HTTPException(status_code=500, detail="Training process failed")
 
-    finally:
+        raise HTTPException(status_code=500, detail="model train exception: " + str(e))
-        if ws_client.is_connected():
-            await ws_client.close()
 
 

ai/app/api/yolo/segmentation.py

@@ -2,7 +2,6 @@ from fastapi import APIRouter, HTTPException
 from schemas.predict_request import PredictRequest
 from schemas.predict_response import PredictResponse, LabelData
 from services.load_model import load_segmentation_model
-from utils.file_utils import get_model_path
 from typing import List
 
 router = APIRouter()
@@ -12,8 +11,7 @@ def predict(request: PredictRequest):
     
     # 모델 로드
     try:
-        model_path = request.m_key and get_model_path(request.project_id, request.m_key)
+        model = load_segmentation_model()
-        model = load_segmentation_model(model_path)
     except Exception as e:
         raise HTTPException(status_code=500, detail="load model exception: "+str(e))
     

ai/app/schemas/train_report_data.py

@@ -0,0 +1,12 @@
+from pydantic import BaseModel
+
+class ReportData(BaseModel):
+    
+    epoch: int          # 현재 에포크
+    total_epochs: int   # 전체 에포크
+    box_loss: float     # box loss
+    cls_loss: float     # cls loss
+    dfl_loss: float     # dfl loss
+    fitness: float      # 적합도
+    epoch_time: float   # 지난 에포크 걸린 시간 (에포크 시작 기준으로 결정)
+    left_seconds: float # 남은 시간(초)

ai/app/schemas/train_request.py

@@ -4,11 +4,12 @@ from schemas.predict_response import LabelData
 
 class TrainDataInfo(BaseModel):
     image_url: str
-    label: LabelData
+    label: str
 
 class TrainRequest(BaseModel):
     project_id: int
     m_key: Optional[str] = Field(None, alias="model_key")
+    m_id: Optional[str] = Field(None, alias="model_id") # 학습 중 에포크 결과를 보낼때 model_id를 보냄
     label_map: dict[int, int] = Field(None, description="모델 레이블 카테고리 idx: 프로젝트 레이블 카테고리 idx , None 일경우 레이블 데이터(프로젝트 레이블)의 idx로 학습")
     data: List[TrainDataInfo]
     ratio: float = 0.8 # 훈련/검증 분할 비율

ai/app/services/load_model.py

@@ -5,35 +5,27 @@ from ultralytics.models.yolo.model import YOLO as YOLO_Model
 from ultralytics.nn.tasks import DetectionModel, SegmentationModel
 import os
 import torch
-import re
 
-def load_detection_model(model_path:str|None):
+def load_detection_model(project_id:int, model_key:str):
-    """
+    default_model_map = {"yolo8": os.path.join("resources","models","yolov8n.pt")}
-    지정된 경로에서 YOLO 모델을 로드합니다.
+    # 디폴트 모델 확인
-
+    if model_key in default_model_map:
-    Args:
+        model = YOLO(default_model_map[model_key])
-        model_path (str): 모델 파일 경로.
-        device (str): 모델을 로드할 장치. 기본값은 'cpu'.
-                      'cpu' 또는 'cuda'와 같은 장치를 지정할 수 있습니다.
-
-    Returns:
-        YOLO: 로드된 YOLO 모델 인스턴스
-    """
-
-    if model_path:
-        model = load_model(model_path)
     else:
-        model = YOLO(os.path.join("resources","models","yolov8n.pt"))
+        model = load_model(model_path=os.path.join("projects",str(project_id),"models",model_key))
+
     # Detection 모델인지 검증
     if model.task != "detect":
         raise TypeError(f"Invalid model type: {model.task}. Expected a DetectionModel.")
     return model
     
-def load_segmentation_model(model_path: str|None): 
+def load_segmentation_model(project_id:int, model_key:str): 
-    if model_path:
+    default_model_map = {"yolo8": os.path.join("resources","models","yolov8n-seg.pt")}
-        model = YOLO(model_path)
+    # 디폴트 모델 확인
+    if model_key in default_model_map:
+        model = YOLO(default_model_map[model_key])
     else:
-        model = YOLO(os.path.join("resources","models","yolov8n-seg.pt"))
+        model = load_model(model_path=os.path.join("projects",str(project_id),"models",model_key))
         
     # Segmentation 모델인지 검증
     if model.task != "segment":

ai/app/utils/file_utils.py

@@ -3,6 +3,9 @@ import shutil
 import yaml
 from PIL import Image
 from schemas.train_request import TrainDataInfo
+from schemas.predict_response import LabelData
+import urllib
+import json
 
 def get_dataset_root_path(project_id):
     """데이터셋 루트 절대 경로 반환"""
@@ -39,18 +42,28 @@ def process_directories(dataset_root_path:str, names:list[str]):
 def process_image_and_label(data:TrainDataInfo, dataset_root_path:str, child_path:str, label_map:dict[int, int]|None):
     
     """이미지 저장 및 레이블 파일 생성"""
-    # 이미지 저장
+    # 이미지 url로부터 파일명 분리
-    img = Image.open(data.image_url)
+    img_name = data.image_url.split('/')[-1]
 
-    # 파일명에서 확장자를 제거하여 img_title과 img_ext 생성
+    img_path = os.path.join(dataset_root_path,child_path,img_name)
-    img_title, img_ext = os.path.splitext(os.path.basename(data.image_url))
 
-    # 이미지 파일 저장 (확장자를 그대로 사용)
+    # url로부터 이미지 다운로드
-    img.save(os.path.join(dataset_root_path, child_path, img_title + img_ext))
+    urllib.request.urlretrieve(data.image_url, img_path)
 
-    # 레이블 -> 학습용 레이블 데이터 파싱(detection)
+    # 파일명에서 확장자를 제거하여 img_title을 얻는다
-    label = data.label
+    img_title = os.path.splitext(os.path.basename(img_path))[0]
-    with open(os.path.join(dataset_root_path, child_path, f"{img_title}.txt"), "w") as train_label_txt:
+
+    # 레이블 파일 경로
+    label_path = os.path.join(dataset_root_path, child_path, f"{img_title}.txt")
+
+    # 레이블 역직렬화
+    label = json_to_object(data.label)
+
+    # 레이블 -> 학습용 레이블 데이터 파싱 후 생성
+    create_detection_train_label(label, label_path, label_map)
+
+def create_detection_train_label(label:LabelData, label_path:str, label_map:dict[int, int]|None):
+    with open(label_path, "w") as train_label_txt:
         for shape in label.shapes:
             train_label = []
             x1 = shape.points[0][0]
@@ -93,5 +106,12 @@ def get_file_name(path):
         raise FileNotFoundError()
     return os.path.basename(path)
 
-def get_model_path(project_id:int, model_key:str):
+def json_to_object(json_string):
-    return os.path.join("resources", "projects", str(project_id), "models", model_key)
+    try:
+        # JSON 문자열을 Python 객체로 변환
+        python_object = json.loads(json_string)
+        return python_object
+    except json.JSONDecodeError as e:
+        raise json.JSONDecodeError("json_decode_error:"+str(e))
+    except Exception as e:
+        raise Exception("exception at json_to_object:"+str(e))