Download app/main.py from CJR61/papi_cc: direct link, hf CLI and curl.
- Browser
- Download file 5.98 kB
-
https://huggingface.co/spaces/CJR61/papi_cc/resolve/main/app/main.py
- Command line
-
hf download hf://spaces/CJR61/papi_cc/app/main.py
-
curl -L -o main.py https://huggingface.co/spaces/CJR61/papi_cc/resolve/main/app/main.py
5.98 kB
| # 20251015 update for open data classification | |
| from fastapi import FastAPI, UploadFile, File | |
| from app.model import load_model, predict_image | |
| from app.utils import save_uploaded_file, append_to_csv | |
| from app.log import logger, configure_logger | |
| from app.dashboard.router import router as dashboard_router | |
| from app.auth import check_predict_key | |
| from fastapi import Depends | |
| import os | |
| from app.utils import preprocess_image, is_valid_image | |
| from contextlib import asynccontextmanager | |
| import numpy as np | |
| SIM_THRES = 0.35 # Similarity threshold (lowered from 0.55; cluster_centers.npy covers broader distribution) | |
| async def lifespan(app: FastAPI): | |
| # Set model loading path | |
| current_directory = os.path.dirname(os.path.abspath(__file__)) | |
| parent_folder = os.path.dirname(current_directory) | |
| resource_dir = os.path.join(parent_folder, "resource") | |
| app.state.database_dir = os.path.join(parent_folder, "database") | |
| app.state.uploads_dir = os.path.join(parent_folder, "uploads") | |
| app.state.logs_dir = os.path.join(parent_folder, "logs") | |
| configure_logger(app.state.logs_dir) | |
| # MODEL_PATH = os.path.join(parent_folder, "resource", "model_2c_v1.onnx") | |
| # 改:使用 emb 版 ONNX,才能同時拿到 embedding + prob | |
| MODEL_PATH = os.path.join(resource_dir, "model_b0_balanced_v2_emb.onnx") | |
| REF_EMB_PATH = os.path.join(resource_dir, "avg12_embedding.npy") | |
| # Load model | |
| logger.info("Starting application... Loading model.") | |
| model = load_model(MODEL_PATH) | |
| app.state.model = model # Store the model in `app.state` for later access | |
| logger.info("Model loaded successfully!") | |
| # 優先載入 cluster_centers.npy(k-means 多中心點) | |
| # fallback: avg12_embedding.npy(舊版單中心點) | |
| cluster_path = os.path.join(resource_dir, "cluster_centers.npy") | |
| ref_emb = np.load(cluster_path if os.path.exists(cluster_path) else REF_EMB_PATH).astype(np.float32) | |
| # 舊版 avg12 shape=(1,1536) → squeeze 成 1-D;cluster_centers shape=(k,1536) 保持 2-D | |
| if ref_emb.ndim == 2 and ref_emb.shape[0] == 1: | |
| ref_emb = ref_emb.squeeze(0) | |
| mode = "cluster_centers" if (ref_emb.ndim == 2) else "avg_single" | |
| logger.info(f"Reference embedding loaded: {mode}, shape={ref_emb.shape}") | |
| app.state.ref_emb = ref_emb | |
| app.state.sim_thres = SIM_THRES | |
| yield # Enter running state, FastAPI will start accepting requests at this point | |
| # Release resources | |
| logger.info("Shutting down application... Cleaning up resources.") | |
| del app.state.model | |
| logger.info("Model resources cleaned up.") | |
| # Initialize app and bind lifespan | |
| app = FastAPI(lifespan=lifespan) | |
| app.include_router(dashboard_router) | |
| async def read_root(): | |
| return {"message": "Connection successful!"} | |
| # Inference API | |
| async def predict(file: UploadFile = File(...)): | |
| # Save uploaded image and generate ID | |
| try: | |
| saved_path, image_id = save_uploaded_file(app.state.uploads_dir, file) | |
| except ValueError as e: | |
| return {"error": str(e)} | |
| logger.info(f"Image saved: {saved_path}, ID: {image_id}") | |
| # Check if the image is valid | |
| if not is_valid_image(saved_path): | |
| logger.error(f"Invalid image file - ID: {image_id}, Path: {saved_path}") | |
| os.remove(saved_path) # Delete invalid file | |
| return {"error": "Invalid image file, please upload a valid image format"} | |
| # Preprocess image | |
| try: | |
| preprocessed_image = preprocess_image(saved_path) | |
| except Exception as e: | |
| logger.error(f"Image preprocessing failed - ID: {image_id}, Error: {str(e)}") | |
| os.remove(saved_path) | |
| return {"error": f"Image preprocessing failed: {str(e)}"} | |
| # Inference | |
| try: | |
| model = app.state.model | |
| ref_emb = app.state.ref_emb | |
| thres = app.state.sim_thres | |
| # 新版 predict_image:回傳 (is_in_criteria: bool, prob: float, sim: float) | |
| is_in_criteria, probability, sim = predict_image(model, preprocessed_image, ref_emb, thres=thres) | |
| # 先把 positive 類別的原始機率四捨五入(保留原本行為) | |
| probability = round(float(probability), 2) | |
| # 所屬類別機率(bacteria prob 直接用;virus prob = 1 - bacteria prob) | |
| class_prob = probability if probability > 0.5 else round(1 - probability, 2) | |
| # 高信心 bypass:class_prob >= HIGH_CONF 且 sim >= MIN_SIM 時直接分類 | |
| # 解決非典型拍攝角度(如臟器黑底標本)被 sim gate 誤擋的問題 | |
| # MIN_SIM 防止完全無關圖片通過 bypass(B0 模型對非豬圖片也極端自信) | |
| HIGH_CONF = 0.85 | |
| MIN_SIM_BYPASS = 0.24 | |
| if class_prob >= HIGH_CONF and sim >= MIN_SIM_BYPASS: | |
| is_in_criteria = True # bypass sim gate | |
| if not is_in_criteria: | |
| prediction = "None" | |
| else: | |
| if probability > 0.5: | |
| prediction = "bacteria" | |
| else: | |
| prediction = "virus" | |
| probability = round(1 - probability, 2) | |
| logger.info( | |
| f"Inference result - ID: {image_id}, Class: {prediction}, " | |
| f"Probability: {probability:.2f}, ClassProb: {class_prob:.2f}, Sim: {sim:.3f}" | |
| ) | |
| except Exception as e: | |
| logger.error(f"Model inference failed - ID: {image_id}, Error: {str(e)}") | |
| return {"error": f"Model inference failed: {str(e)}"} | |
| # Save result to CSV | |
| try: | |
| csv_path = os.path.join(app.state.database_dir, "inference_results.csv") | |
| append_to_csv(csv_path, image_id, prediction, probability, sim) | |
| except Exception as e: | |
| logger.error(f"Failed to save result to CSV: {str(e)}") | |
| return {"error": f"Failed to save result to CSV: {str(e)}"} | |
| # Return inference result | |
| return {"id": image_id, "class": prediction, "probability": probability} | |