Spaces:
Runtime error
Runtime error
Upload 7 files
Browse files- 1026.pt +3 -0
- Dockerfile +24 -0
- app.py +941 -0
- main.png +0 -0
- output_vectors.json +0 -0
- requirements.txt +72 -0
- sums_data.json +0 -0
1026.pt
ADDED
|
@@ -0,0 +1,3 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
version https://git-lfs.github.com/spec/v1
|
| 2 |
+
oid sha256:87af30931732d6ac63bd65230b33f22ca157a3dd97e72c361b55be8a3a2dfade
|
| 3 |
+
size 22568035
|
Dockerfile
ADDED
|
@@ -0,0 +1,24 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# Use the official Python 3.10.9 image
|
| 2 |
+
FROM python:3.10.9
|
| 3 |
+
|
| 4 |
+
# Copy the current directory contents into the container at .
|
| 5 |
+
COPY . .
|
| 6 |
+
# Install dependencies for OpenCV and other requirements
|
| 7 |
+
RUN apt-get update && apt-get install -y libgl1 libglib2.0-0 curl
|
| 8 |
+
# Set the working directory to /
|
| 9 |
+
WORKDIR /
|
| 10 |
+
# Create a user to avoid permission issues
|
| 11 |
+
RUN useradd -m appuser
|
| 12 |
+
USER appuser
|
| 13 |
+
|
| 14 |
+
# Set the working directory to /home/appuser
|
| 15 |
+
WORKDIR /home/appuser
|
| 16 |
+
|
| 17 |
+
# Add /home/appuser/.local/bin to PATH
|
| 18 |
+
ENV PATH="/home/appuser/.local/bin:${PATH}"
|
| 19 |
+
|
| 20 |
+
# Install requirements.txt
|
| 21 |
+
RUN pip install --no-cache-dir --upgrade -r /requirements.txt
|
| 22 |
+
|
| 23 |
+
# Start the FastAPI app on port 7860, the default port expected by Spaces
|
| 24 |
+
CMD ["uvicorn", "app:app", "--host", "0.0.0.0", "--port", "7860"]
|
app.py
ADDED
|
@@ -0,0 +1,941 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
# -*- coding: utf-8 -*-
|
| 2 |
+
|
| 3 |
+
# Commented out IPython magic to ensure Python compatibility.
|
| 4 |
+
|
| 5 |
+
|
| 6 |
+
|
| 7 |
+
|
| 8 |
+
import os
|
| 9 |
+
import supervision as sv
|
| 10 |
+
from PIL import Image, ImageFilter
|
| 11 |
+
import numpy as np
|
| 12 |
+
import cv2
|
| 13 |
+
import pycocotools.mask as mask_util
|
| 14 |
+
|
| 15 |
+
from fastapi import FastAPI, File, UploadFile, Form
|
| 16 |
+
from fastapi.middleware.cors import CORSMiddleware
|
| 17 |
+
from fastapi.responses import FileResponse, HTMLResponse
|
| 18 |
+
import shutil
|
| 19 |
+
import json
|
| 20 |
+
from pathlib import Path
|
| 21 |
+
import nest_asyncio
|
| 22 |
+
import uvicorn
|
| 23 |
+
from pyngrok import ngrok
|
| 24 |
+
from diffusers import StableDiffusionInpaintPipeline
|
| 25 |
+
import torch
|
| 26 |
+
from simple_lama_inpainting import SimpleLama
|
| 27 |
+
from sklearn.cluster import (
|
| 28 |
+
KMeans, AgglomerativeClustering, DBSCAN, MiniBatchKMeans, Birch,
|
| 29 |
+
SpectralClustering, MeanShift, OPTICS
|
| 30 |
+
)
|
| 31 |
+
from sklearn.decomposition import PCA
|
| 32 |
+
from sklearn.metrics import silhouette_score
|
| 33 |
+
from sklearn.neighbors import KNeighborsClassifier
|
| 34 |
+
from torchvision import transforms
|
| 35 |
+
import threading
|
| 36 |
+
import concurrent.futures
|
| 37 |
+
from typing import Tuple
|
| 38 |
+
from types import SimpleNamespace
|
| 39 |
+
import subprocess
|
| 40 |
+
import uuid
|
| 41 |
+
from datetime import datetime
|
| 42 |
+
from ultralytics import YOLO
|
| 43 |
+
import math
|
| 44 |
+
import numpy as np
|
| 45 |
+
import matplotlib.pyplot as plt
|
| 46 |
+
|
| 47 |
+
#この下のコードは特定の領域をマスクしないタイプのコード
|
| 48 |
+
import uuid
|
| 49 |
+
from datetime import datetime
|
| 50 |
+
|
| 51 |
+
|
| 52 |
+
|
| 53 |
+
import cv2
|
| 54 |
+
import numpy as np
|
| 55 |
+
from datetime import datetime
|
| 56 |
+
from ultralytics import YOLO
|
| 57 |
+
from PIL import Image
|
| 58 |
+
app = FastAPI()
|
| 59 |
+
# CORSミドルウェアの追加
|
| 60 |
+
app.add_middleware(
|
| 61 |
+
CORSMiddleware,
|
| 62 |
+
allow_origins=["*"], # ここを適切なオリジンに設定することもできます
|
| 63 |
+
allow_credentials=True,
|
| 64 |
+
allow_methods=["*"],
|
| 65 |
+
allow_headers=["*"],
|
| 66 |
+
)
|
| 67 |
+
|
| 68 |
+
|
| 69 |
+
HOME = "./"
|
| 70 |
+
|
| 71 |
+
dangerarray=[10,30,90,50,80,20,40,70,100,60]#ここに各クラスターの危険度を設定しておく
|
| 72 |
+
#ここで認識する精度を上げたり下げたりできる
|
| 73 |
+
|
| 74 |
+
thresholds = {
|
| 75 |
+
'text': 0.1,
|
| 76 |
+
'name tag': 0.1,
|
| 77 |
+
'license plate': 0.3,
|
| 78 |
+
'Mail': 0.3,
|
| 79 |
+
'Documents': 0.3,
|
| 80 |
+
'QR codes': 0.4,
|
| 81 |
+
'barcodes': 0.4,
|
| 82 |
+
'map': 0.5,
|
| 83 |
+
'digital screens': 0.6,
|
| 84 |
+
'information board': 0.5,
|
| 85 |
+
'signboard': 0.3,
|
| 86 |
+
'poster': 0.8,
|
| 87 |
+
'sign': 0.3,
|
| 88 |
+
'logo': 0.3,
|
| 89 |
+
'card': 0.4,
|
| 90 |
+
'window': 0.2,
|
| 91 |
+
'mirror': 0.2,
|
| 92 |
+
'Famous landmark': 0.7,
|
| 93 |
+
'cardboard': 0.6,
|
| 94 |
+
'manhole': 0.6,
|
| 95 |
+
'utility pole': 0.7
|
| 96 |
+
}
|
| 97 |
+
|
| 98 |
+
'''
|
| 99 |
+
|
| 100 |
+
'''
|
| 101 |
+
|
| 102 |
+
# Define paths
|
| 103 |
+
|
| 104 |
+
CONFIG_PATH = os.path.join(HOME, "GroundingDINO/groundingdino/config/GroundingDINO_SwinT_OGC.py")
|
| 105 |
+
WEIGHTS_NAME = "groundingdino_swint_ogc.pth"
|
| 106 |
+
WEIGHTS_PATH = os.path.join(HOME, "weights", WEIGHTS_NAME)
|
| 107 |
+
from PIL import Image
|
| 108 |
+
|
| 109 |
+
def is_bright(pixel):
|
| 110 |
+
# ピクセルの輝度を計算して明るさを判定する
|
| 111 |
+
r, g, b = pixel
|
| 112 |
+
brightness = (0.299 * r + 0.587 * g + 0.114 * b) # 輝度の計算
|
| 113 |
+
return brightness > 127 # 閾値を127に設定
|
| 114 |
+
|
| 115 |
+
def analyze_mask_brightness(original_image_path, mask_image_path):
|
| 116 |
+
# 画像を開く
|
| 117 |
+
original_img = Image.open(original_image_path).convert('RGB')
|
| 118 |
+
mask_img = Image.open(mask_image_path).convert('L') # グレースケールに変換
|
| 119 |
+
|
| 120 |
+
width, height = original_img.size
|
| 121 |
+
|
| 122 |
+
if mask_img.size != (width, height):
|
| 123 |
+
print("エラー: マスク画像と元画像のサイズが一致していません。")
|
| 124 |
+
return
|
| 125 |
+
|
| 126 |
+
# 明るいピクセルと暗いピクセルのカウント
|
| 127 |
+
bright_count = 0
|
| 128 |
+
dark_count = 0
|
| 129 |
+
|
| 130 |
+
for y in range(height):
|
| 131 |
+
for x in range(width):
|
| 132 |
+
mask_value = mask_img.getpixel((x, y))
|
| 133 |
+
if mask_value > 127: # マスクが白(対象領域)ならば
|
| 134 |
+
pixel = original_img.getpixel((x, y))
|
| 135 |
+
if is_bright(pixel):
|
| 136 |
+
bright_count += 1
|
| 137 |
+
else:
|
| 138 |
+
dark_count += 1
|
| 139 |
+
|
| 140 |
+
# 明るさの結果を判定
|
| 141 |
+
brightness_result = 1 if bright_count > dark_count else 2
|
| 142 |
+
|
| 143 |
+
return brightness_result
|
| 144 |
+
|
| 145 |
+
def classify_mask_size(mask_image_path, small_threshold, medium_threshold, large_threshold):
|
| 146 |
+
# マスク画像を開く
|
| 147 |
+
mask_img = Image.open(mask_image_path).convert('L') # グレースケールに変換
|
| 148 |
+
|
| 149 |
+
width, height = mask_img.size
|
| 150 |
+
total_pixels = width * height
|
| 151 |
+
white_pixel_count = 0
|
| 152 |
+
|
| 153 |
+
# マスク画像の白いピクセルをカウント
|
| 154 |
+
for y in range(height):
|
| 155 |
+
for x in range(width):
|
| 156 |
+
mask_value = mask_img.getpixel((x, y))
|
| 157 |
+
if mask_value > 127: # 白いピクセルと判断
|
| 158 |
+
white_pixel_count += 1
|
| 159 |
+
|
| 160 |
+
# 白いピクセルの割合を計算
|
| 161 |
+
mask_area_ratio = (white_pixel_count / total_pixels) * 100
|
| 162 |
+
|
| 163 |
+
# マスクサイズを分類
|
| 164 |
+
if mask_area_ratio <= small_threshold:
|
| 165 |
+
size_category = 1 # すごく小さい
|
| 166 |
+
elif mask_area_ratio <= medium_threshold:
|
| 167 |
+
size_category = 2 # 小さい
|
| 168 |
+
elif mask_area_ratio <= large_threshold:
|
| 169 |
+
size_category = 3 # 大きい
|
| 170 |
+
else:
|
| 171 |
+
size_category = 4 # すごく大きい
|
| 172 |
+
|
| 173 |
+
return size_category
|
| 174 |
+
|
| 175 |
+
def analyze_mask_combined(original_image_path, mask_image_path, small_threshold, medium_threshold, large_threshold):
|
| 176 |
+
# マスクの大きさを判定
|
| 177 |
+
size_category = classify_mask_size(mask_image_path, small_threshold, medium_threshold, large_threshold)
|
| 178 |
+
|
| 179 |
+
# マスク部分の明るさを判定
|
| 180 |
+
brightness_result = analyze_mask_brightness(original_image_path, mask_image_path)
|
| 181 |
+
|
| 182 |
+
# 結果を出力
|
| 183 |
+
size_text = {1: "すごく小さい", 2: "小さい", 3: "大きい", 4: "すごく大きい"}
|
| 184 |
+
print(f"マスクの大きさ: {size_text[size_category]} ({size_category})")
|
| 185 |
+
print(f"マスクの明るさ: {brightness_result}")
|
| 186 |
+
result={
|
| 187 |
+
'size':size_category,
|
| 188 |
+
'brightness':brightness_result
|
| 189 |
+
}
|
| 190 |
+
return result
|
| 191 |
+
|
| 192 |
+
|
| 193 |
+
|
| 194 |
+
#この下で消去対象を決定
|
| 195 |
+
def decide_to_object(risk_level):
|
| 196 |
+
'''
|
| 197 |
+
tex = [
|
| 198 |
+
'text','Name tag', 'License plate', 'Mail', 'Documents', 'QR codes',
|
| 199 |
+
'barcodes', 'Map', 'Digital screens', 'information board',
|
| 200 |
+
'signboard', 'poster', 'sign', 'utility pole'
|
| 201 |
+
|
| 202 |
+
]
|
| 203 |
+
'''
|
| 204 |
+
tex = [
|
| 205 |
+
'text', 'License plate', 'Digital screens',
|
| 206 |
+
'signboard', 'poster', 'sign', 'logo', 'card', 'window', 'mirror',
|
| 207 |
+
'Famous landmark', 'cardboard', 'manhole', 'utility pole'
|
| 208 |
+
|
| 209 |
+
]
|
| 210 |
+
|
| 211 |
+
|
| 212 |
+
#この配列の要素の順番を変えると消える順番が変わる。
|
| 213 |
+
risk_level = int(risk_level / 20)*(len(tex)/10)#個数決定(1/2)
|
| 214 |
+
return tex[:int(risk_level)+1]
|
| 215 |
+
|
| 216 |
+
def create_mask(image, x1, y1, x2, y2):
|
| 217 |
+
# Create a black image with the same size as the input image
|
| 218 |
+
mask = np.zeros((image.shape[0], image.shape[1]), dtype=np.uint8)
|
| 219 |
+
|
| 220 |
+
# Draw a white rectangle on the mask where the object is located
|
| 221 |
+
cv2.rectangle(mask, (int(x1), int(y1)), (int(x2), int(y2)), 255, -1)
|
| 222 |
+
|
| 223 |
+
return mask
|
| 224 |
+
|
| 225 |
+
|
| 226 |
+
def special_process_image_yolo(risk_level, image_path, point1, point2, thresholds=None):
|
| 227 |
+
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
|
| 228 |
+
print(device)
|
| 229 |
+
# YOLOv8モデルをロードし、GPUに移動
|
| 230 |
+
model = YOLO('./1026.pt') # モデルのパスを指定
|
| 231 |
+
model.to(device) # モデルをGPUに移動
|
| 232 |
+
|
| 233 |
+
|
| 234 |
+
# タイムスタンプを作成
|
| 235 |
+
timestamp = datetime.now().strftime("%Y%m%d%H%M%S")
|
| 236 |
+
|
| 237 |
+
# リスクレベルに基づいた減衰率の計算
|
| 238 |
+
def logistic_decay(risk_level, k=0.1, r0=50):
|
| 239 |
+
return 1 / (1 + np.exp(-k * (risk_level - r0)))
|
| 240 |
+
|
| 241 |
+
decay_factor = logistic_decay(risk_level)
|
| 242 |
+
adjusted_thresholds = {key: max(value - decay_factor + 0.8, 0.01) / 2 for key, value in thresholds.items()}
|
| 243 |
+
|
| 244 |
+
|
| 245 |
+
|
| 246 |
+
# 画像の読み込みとRGB変換
|
| 247 |
+
image = cv2.imread(image_path)
|
| 248 |
+
image_rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
|
| 249 |
+
image_np = np.array(image_rgb, dtype=np.uint8)
|
| 250 |
+
|
| 251 |
+
# 推論実行
|
| 252 |
+
results = model(image_rgb)
|
| 253 |
+
|
| 254 |
+
# 初期化したマスク画像
|
| 255 |
+
mask = np.zeros((image_np.shape[0], image_np.shape[1]), dtype=np.uint8)
|
| 256 |
+
|
| 257 |
+
# 各検出結果に基づきマスク作成
|
| 258 |
+
for box in results[0].boxes:
|
| 259 |
+
x1, y1, x2, y2 = map(int, box.xyxy[0]) # ボックスの座標
|
| 260 |
+
confidence = box.conf[0]
|
| 261 |
+
class_id = box.cls[0]
|
| 262 |
+
object_type = model.names[int(class_id)]
|
| 263 |
+
|
| 264 |
+
# クラス名に基づいたしきい値
|
| 265 |
+
threshold = adjusted_thresholds.get(object_type, 0.5)
|
| 266 |
+
|
| 267 |
+
if confidence >= threshold:
|
| 268 |
+
mask[y1:y2, x1:x2] = 255 # ボックス領域を白に設定
|
| 269 |
+
|
| 270 |
+
# 絶対座標に変換した点の範囲を黒に設定
|
| 271 |
+
p1_x, p1_y = int(point1[0] * image_np.shape[1]), int(point1[1] * image_np.shape[0])
|
| 272 |
+
p2_x, p2_y = int(point2[0] * image_np.shape[1]), int(point2[1] * image_np.shape[0])
|
| 273 |
+
x_min, y_min = max(0, min(p1_x, p2_x)), max(0, min(p1_y, p2_y))
|
| 274 |
+
x_max, y_max = min(image_np.shape[1], max(p1_x, p2_x)), min(image_np.shape[0], max(p1_y, p2_y))
|
| 275 |
+
mask[y_min:y_max, x_min:x_max] = 0 # 範囲を黒に設定
|
| 276 |
+
|
| 277 |
+
# デバッグ用に白い長方形を描画
|
| 278 |
+
debug_image = image_np.copy()
|
| 279 |
+
cv2.rectangle(debug_image, (x_min, y_min), (x_max, y_max), (255, 255, 255), 2)
|
| 280 |
+
|
| 281 |
+
# デバッグ画像とマスク画像を保存
|
| 282 |
+
debug_image_pil = Image.fromarray(debug_image)
|
| 283 |
+
debug_image_pil.save(f"./debug_image_with_rectangle_{timestamp}.jpg")
|
| 284 |
+
|
| 285 |
+
mask_image_pil = Image.fromarray(mask)
|
| 286 |
+
mask_image_pil.save(f"./final_mask_{timestamp}.jpg")
|
| 287 |
+
|
| 288 |
+
return f"./final_mask_{timestamp}.jpg"
|
| 289 |
+
|
| 290 |
+
|
| 291 |
+
|
| 292 |
+
|
| 293 |
+
|
| 294 |
+
def convert_image_format(input_path, output_format="png"):
|
| 295 |
+
"""
|
| 296 |
+
画像をJPGからPNGまたはPNGからJPGに変換する関数。
|
| 297 |
+
|
| 298 |
+
Parameters:
|
| 299 |
+
- input_path: 変換したい元画像のパス
|
| 300 |
+
- output_format: 出力形式 ("png" または "jpg" を指定、デフォルトは "png")
|
| 301 |
+
|
| 302 |
+
Returns:
|
| 303 |
+
- output_path: 変換された画像の出力パス
|
| 304 |
+
"""
|
| 305 |
+
# サポートされているフォーマットかを確認
|
| 306 |
+
if output_format not in ["png", "jpg", "jpeg"]:
|
| 307 |
+
raise ValueError("サポートされている出力形式は 'png' または 'jpg' です��")
|
| 308 |
+
|
| 309 |
+
# 画像の読み込み
|
| 310 |
+
image = cv2.imread(input_path)
|
| 311 |
+
if image is None:
|
| 312 |
+
raise ValueError(f"画像が見つかりません: {input_path}")
|
| 313 |
+
|
| 314 |
+
# 出力パスの生成
|
| 315 |
+
base_name = os.path.splitext(os.path.basename(input_path))[0]
|
| 316 |
+
output_path = f"{base_name}.{output_format}"
|
| 317 |
+
|
| 318 |
+
# 画像の保存
|
| 319 |
+
if output_format == "png":
|
| 320 |
+
cv2.imwrite(output_path, image, [cv2.IMWRITE_PNG_COMPRESSION, 9]) # PNG形式で最高圧縮率
|
| 321 |
+
else:
|
| 322 |
+
cv2.imwrite(output_path, image, [cv2.IMWRITE_JPEG_QUALITY, 90]) # JPG形式で高画質
|
| 323 |
+
|
| 324 |
+
return output_path
|
| 325 |
+
|
| 326 |
+
|
| 327 |
+
|
| 328 |
+
|
| 329 |
+
|
| 330 |
+
#この下は、openCV
|
| 331 |
+
def inpaint_image_with_mask(image_path, mask_path, output_path, inpaint_radius=5, inpaint_method=cv2.INPAINT_TELEA):
|
| 332 |
+
"""
|
| 333 |
+
マスク画像を使用して元画像のインペイントを行う関数。
|
| 334 |
+
|
| 335 |
+
Parameters:
|
| 336 |
+
- image_path: 元画像のパス
|
| 337 |
+
- mask_path: マスク画像のパス(修復したい領域が白、その他が黒)
|
| 338 |
+
- output_path: インペイント結果の出力パス
|
| 339 |
+
- inpaint_radius: インペイントの半径(デフォルトは5)
|
| 340 |
+
- inpaint_method: インペイントのアルゴリズム(デフォルトはcv2.INPAINT_TELEA)
|
| 341 |
+
|
| 342 |
+
Returns:
|
| 343 |
+
- inpainted_image: インペイントされた画像
|
| 344 |
+
"""
|
| 345 |
+
# 画像とマスクを読み込み
|
| 346 |
+
image = cv2.imread(image_path)
|
| 347 |
+
mask = cv2.imread(mask_path, cv2.IMREAD_GRAYSCALE) # マスクはグレースケールで読み込み
|
| 348 |
+
|
| 349 |
+
# マスク画像が正常に読み込めたかチェック
|
| 350 |
+
if image is None:
|
| 351 |
+
raise ValueError(f"元画像が見つかりません: {image_path}")
|
| 352 |
+
if mask is None:
|
| 353 |
+
raise ValueError(f"マスク画像が見つかりません: {mask_path}")
|
| 354 |
+
|
| 355 |
+
# マスク画像が元画像と同じサイズでない場合、リサイズ
|
| 356 |
+
if image.shape[:2] != mask.shape[:2]:
|
| 357 |
+
print(f"マスク画像のサイズを元画像に合わせてリサイズします: {mask.shape} -> {image.shape[:2]}")
|
| 358 |
+
mask = cv2.resize(mask, (image.shape[1], image.shape[0]))
|
| 359 |
+
|
| 360 |
+
# インペイント処理
|
| 361 |
+
inpainted_image = cv2.inpaint(image, mask, inpaint_radius, inpaint_method)
|
| 362 |
+
|
| 363 |
+
# インペイント結果を保存
|
| 364 |
+
cv2.imwrite(output_path, inpainted_image)
|
| 365 |
+
|
| 366 |
+
return output_path
|
| 367 |
+
|
| 368 |
+
|
| 369 |
+
def stamp_image_with_mask(base_image_path, mask_path,output_path,stamp_image_path='./main.png'):
|
| 370 |
+
"""
|
| 371 |
+
マスク画像を使用して元画像に別の画像を埋め込む関数。
|
| 372 |
+
|
| 373 |
+
Parameters:
|
| 374 |
+
- base_image_path: 元画像のパス
|
| 375 |
+
- mask_path: マスク画像のパス(埋め込みたい領域が白、その他が黒)
|
| 376 |
+
- embed_image_path: 埋め込み用画像のパス
|
| 377 |
+
- output_path: 結果の出力パス
|
| 378 |
+
|
| 379 |
+
Returns:
|
| 380 |
+
- output_path: 埋め込み処理された画像の出力パス
|
| 381 |
+
"""
|
| 382 |
+
# 画像とマスクを読み込み
|
| 383 |
+
base_image = cv2.imread(base_image_path)
|
| 384 |
+
mask = cv2.imread(mask_path, cv2.IMREAD_GRAYSCALE)
|
| 385 |
+
embed_image = cv2.imread(stamp_image_path)
|
| 386 |
+
|
| 387 |
+
# 画像が正常に読み込めたかチェック
|
| 388 |
+
if base_image is None:
|
| 389 |
+
raise ValueError(f"元画像が見つかりません: {base_image_path}")
|
| 390 |
+
if mask is None:
|
| 391 |
+
raise ValueError(f"マスク画像が見つかりません: {mask_path}")
|
| 392 |
+
if embed_image is None:
|
| 393 |
+
raise ValueError(f"埋め込み用画像が見つかりません: {stamp_image_path}")
|
| 394 |
+
|
| 395 |
+
# マスク画像と埋め込み画像を元画像と同じサイズにリサイズ
|
| 396 |
+
if base_image.shape[:2] != mask.shape[:2]:
|
| 397 |
+
print(f"マスク画像のサイズを元画像に合わせてリサイズします: {mask.shape} -> {base_image.shape[:2]}")
|
| 398 |
+
mask = cv2.resize(mask, (base_image.shape[1], base_image.shape[0]))
|
| 399 |
+
if base_image.shape[:2] != embed_image.shape[:2]:
|
| 400 |
+
print(f"埋め込み画像のサイズを元画像に合わせてリサイズします: {embed_image.shape[:2]} -> {base_image.shape[:2]}")
|
| 401 |
+
embed_image = cv2.resize(embed_image, (base_image.shape[1], base_image.shape[0]))
|
| 402 |
+
|
| 403 |
+
# マスク領域に埋め込み画像を配置
|
| 404 |
+
embedded_image = base_image.copy()
|
| 405 |
+
embedded_image[mask == 255] = embed_image[mask == 255]
|
| 406 |
+
|
| 407 |
+
# 結果を保存
|
| 408 |
+
cv2.imwrite(output_path, embedded_image)
|
| 409 |
+
|
| 410 |
+
return output_path
|
| 411 |
+
import torch
|
| 412 |
+
from PIL import Image, ImageFilter
|
| 413 |
+
import numpy as np
|
| 414 |
+
from simple_lama_inpainting import SimpleLama
|
| 415 |
+
|
| 416 |
+
def inpaint_image_with_mask1(img_path, mask_path, output_path, resize_factor=0.5):
|
| 417 |
+
print('lama')
|
| 418 |
+
|
| 419 |
+
# GPUが利用可能か確認
|
| 420 |
+
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
|
| 421 |
+
|
| 422 |
+
# 画像とマスクを読み込み
|
| 423 |
+
image = Image.open(img_path).convert("RGB") # 画像をRGBに変換
|
| 424 |
+
mask = Image.open(mask_path).convert('L') # マスクをグレースケールに変換
|
| 425 |
+
|
| 426 |
+
# 画像とマスクのサイズを合わせる
|
| 427 |
+
mask = mask.resize(image.size, Image.NEAREST)
|
| 428 |
+
|
| 429 |
+
# マスクのエッジをぼかす (Gaussian Blur)
|
| 430 |
+
blurred_mask = mask.filter(ImageFilter.GaussianBlur(radius=3)) # 半径3ピクセルでぼかし
|
| 431 |
+
|
| 432 |
+
# SimpleLama インスタンスを作成
|
| 433 |
+
simple_lama = SimpleLama()
|
| 434 |
+
|
| 435 |
+
# 画像とマスクをNumPy配列に変換
|
| 436 |
+
image_np = np.array(image)
|
| 437 |
+
mask_np = np.array(blurred_mask) / 255.0 # マスクを0-1範囲にスケーリング
|
| 438 |
+
|
| 439 |
+
# 入力画像とマスクをSimpleLamaに渡してインペイント
|
| 440 |
+
inpainted_np = simple_lama(image_np, mask_np) # NumPy配列を渡す
|
| 441 |
+
|
| 442 |
+
# 結果を画像として保存
|
| 443 |
+
result_image = Image.fromarray(np.uint8(inpainted_np)) # NumPy array -> PIL Image
|
| 444 |
+
|
| 445 |
+
# 出力画像をリサイズ
|
| 446 |
+
new_size = (int(result_image.width * resize_factor), int(result_image.height * resize_factor))
|
| 447 |
+
result_image = result_image.resize(new_size, Image.ANTIALIAS)
|
| 448 |
+
|
| 449 |
+
# 結果を保存
|
| 450 |
+
result_image.save(output_path)
|
| 451 |
+
print(f"Inpainted image saved at {output_path}")
|
| 452 |
+
return output_path
|
| 453 |
+
|
| 454 |
+
|
| 455 |
+
|
| 456 |
+
|
| 457 |
+
|
| 458 |
+
|
| 459 |
+
|
| 460 |
+
|
| 461 |
+
|
| 462 |
+
|
| 463 |
+
|
| 464 |
+
|
| 465 |
+
|
| 466 |
+
|
| 467 |
+
|
| 468 |
+
|
| 469 |
+
|
| 470 |
+
|
| 471 |
+
# 保存先のディレクトリを指定
|
| 472 |
+
SAVE_DIR = Path("./saved_images")
|
| 473 |
+
SAVE_DIR.mkdir(parents=True, exist_ok=True)
|
| 474 |
+
|
| 475 |
+
def save_image(file, filename):
|
| 476 |
+
"""画像ファイルを指定ディレクトリに保存"""
|
| 477 |
+
filepath = SAVE_DIR / filename
|
| 478 |
+
with open(filepath, "wb") as buffer:
|
| 479 |
+
shutil.copyfileobj(file, buffer)
|
| 480 |
+
return filepath
|
| 481 |
+
|
| 482 |
+
@app.post("/create-mask-and-inpaint-opencv")
|
| 483 |
+
async def create_mask_and_inpaint_opencv(image: UploadFile = File(...), risk_level: int = Form(...)):
|
| 484 |
+
point1 = (0.00000000000002, 0.00000000000002)
|
| 485 |
+
point2 = (0.00000000000001, 0.00000000000001)
|
| 486 |
+
input_path = save_image(image.file, "input.jpg")
|
| 487 |
+
mask_path = special_process_image_yolo(risk_level, input_path, point1, point2, thresholds)
|
| 488 |
+
|
| 489 |
+
output_path = SAVE_DIR / "output_opencv.jpg"
|
| 490 |
+
# OpenCVでインペイント
|
| 491 |
+
inpaint_image_with_mask(input_path, mask_path, output_path)
|
| 492 |
+
|
| 493 |
+
return FileResponse(output_path)
|
| 494 |
+
@app.post("/create-mask-and-inpaint-stamp")
|
| 495 |
+
async def create_mask_and_inpaint_opencv(image: UploadFile = File(...), risk_level: int = Form(...)):
|
| 496 |
+
point1 = (0.00000000000002, 0.00000000000002)
|
| 497 |
+
point2 = (0.00000000000001, 0.00000000000001)
|
| 498 |
+
input_path = save_image(image.file, "input.jpg")
|
| 499 |
+
mask_path = special_process_image_yolo(risk_level, input_path, point1, point2, thresholds)
|
| 500 |
+
|
| 501 |
+
output_path = SAVE_DIR / "output_opencv.jpg"
|
| 502 |
+
# OpenCVでインペイント
|
| 503 |
+
stamp_image_with_mask(input_path, mask_path, output_path)
|
| 504 |
+
|
| 505 |
+
return FileResponse(output_path)
|
| 506 |
+
|
| 507 |
+
|
| 508 |
+
|
| 509 |
+
|
| 510 |
+
|
| 511 |
+
|
| 512 |
+
@app.post("/create-mask-and-inpaint-simple-lama")
|
| 513 |
+
async def create_mask_and_inpaint_simple_lama(image: UploadFile = File(...), risk_level: int = Form(...)):
|
| 514 |
+
input_path = save_image(image.file, "input.jpg")
|
| 515 |
+
point1 = (0.00000000000002, 0.00000000000002)
|
| 516 |
+
point2 = (0.00000000000001, 0.00000000000001)
|
| 517 |
+
mask_path = special_process_image_yolo(risk_level, input_path, point1, point2, thresholds)
|
| 518 |
+
output_path = SAVE_DIR / "output_simple_lama.jpg"
|
| 519 |
+
# SimpleLamaでインペイント
|
| 520 |
+
inpaint_image_with_mask1(input_path, mask_path, output_path, resize_factor=1)
|
| 521 |
+
|
| 522 |
+
return FileResponse(output_path)
|
| 523 |
+
|
| 524 |
+
|
| 525 |
+
#下のendpointは特定領域をマスクしないタイプのもの
|
| 526 |
+
|
| 527 |
+
|
| 528 |
+
#下記はDeepFillv2
|
| 529 |
+
|
| 530 |
+
|
| 531 |
+
|
| 532 |
+
|
| 533 |
+
|
| 534 |
+
|
| 535 |
+
|
| 536 |
+
|
| 537 |
+
|
| 538 |
+
|
| 539 |
+
|
| 540 |
+
|
| 541 |
+
|
| 542 |
+
|
| 543 |
+
|
| 544 |
+
|
| 545 |
+
|
| 546 |
+
|
| 547 |
+
|
| 548 |
+
|
| 549 |
+
|
| 550 |
+
|
| 551 |
+
|
| 552 |
+
|
| 553 |
+
# ベクトル化対象のオブジェクトリスト
|
| 554 |
+
TEXT_PROMPTS = [
|
| 555 |
+
'text','Name tag', 'License plate', 'Mail', 'Documents', 'QR codes',
|
| 556 |
+
'barcodes', 'Map', 'Digital screens', 'information board',
|
| 557 |
+
'signboard', 'poster', 'sign', 'logo', 'card', 'window', 'mirror',
|
| 558 |
+
'Famous landmark', 'cardboard', 'manhole', 'utility pole'
|
| 559 |
+
]
|
| 560 |
+
BOX_THRESHOLD = 0.3
|
| 561 |
+
TEXT_THRESHOLD = 0.3
|
| 562 |
+
|
| 563 |
+
# クラスタリング結果をJSONファイルから読み込む関数
|
| 564 |
+
def load_sums_from_json(filepath):
|
| 565 |
+
with open(filepath, 'r') as json_file:
|
| 566 |
+
sums = json.load(json_file)
|
| 567 |
+
return sums
|
| 568 |
+
|
| 569 |
+
# ベクトルデータをJSONファイルから読み込む関数
|
| 570 |
+
def load_vectors_from_json(filepath):
|
| 571 |
+
with open(filepath, 'r') as json_file:
|
| 572 |
+
data = json.load(json_file)
|
| 573 |
+
return data
|
| 574 |
+
|
| 575 |
+
# 新しい画像を分類する関数
|
| 576 |
+
def classify_new_image(new_image_vector, sums_data, loaded_vectors, loaded_object_names, k=1):
|
| 577 |
+
cluster_centers = []
|
| 578 |
+
for cluster in sums_data:
|
| 579 |
+
indices = [loaded_object_names.index(obj_name) for obj_name in cluster]
|
| 580 |
+
cluster_vectors = np.array([loaded_vectors[obj_name] for obj_name in cluster])
|
| 581 |
+
cluster_center = np.mean(cluster_vectors, axis=0)
|
| 582 |
+
cluster_centers.append(cluster_center)
|
| 583 |
+
|
| 584 |
+
knn = KNeighborsClassifier(n_neighbors=k)
|
| 585 |
+
knn.fit(cluster_centers, range(len(cluster_centers)))
|
| 586 |
+
|
| 587 |
+
new_image_label = knn.predict([new_image_vector])
|
| 588 |
+
return new_image_label[0]
|
| 589 |
+
|
| 590 |
+
import torch
|
| 591 |
+
import cv2
|
| 592 |
+
import numpy as np
|
| 593 |
+
from ultralytics import YOLO # YOLOv8ライブラリ
|
| 594 |
+
|
| 595 |
+
def process_image_vec(image_path):
|
| 596 |
+
# GPUを使用できるか確認
|
| 597 |
+
device = torch.device('cuda' if torch.cuda.is_available() else 'cpu')
|
| 598 |
+
print(device)
|
| 599 |
+
# YOLOv8モデルをロードし、GPUに移動
|
| 600 |
+
model = YOLO('./1026.pt') # モデルのパスを指定
|
| 601 |
+
model.to(device) # モデルをGPUに移動
|
| 602 |
+
|
| 603 |
+
# 初期化
|
| 604 |
+
object_vector = np.zeros(len(TEXT_PROMPTS))
|
| 605 |
+
|
| 606 |
+
# 画像の読み込み
|
| 607 |
+
image = cv2.imread(image_path)
|
| 608 |
+
image_rgb = cv2.cvtColor(image, cv2.COLOR_BGR2RGB)
|
| 609 |
+
|
| 610 |
+
# YOLOで推論を実行
|
| 611 |
+
results = model(image_rgb) # 推論を実行
|
| 612 |
+
|
| 613 |
+
# 各プロンプトごとに確認
|
| 614 |
+
for i, text_prompt in enumerate(TEXT_PROMPTS):
|
| 615 |
+
prompt_sum = 0 # 各プロンプトに対応するスコアの合計
|
| 616 |
+
|
| 617 |
+
for box in results[0].boxes:
|
| 618 |
+
class_id = int(box.cls[0])
|
| 619 |
+
confidence = box.conf[0]
|
| 620 |
+
detected_class = model.names[class_id]
|
| 621 |
+
|
| 622 |
+
# 検出クラス名とテキストプロンプトの一致を確認
|
| 623 |
+
if text_prompt.lower() == detected_class.lower():
|
| 624 |
+
prompt_sum += confidence # クラスが一致した場合、信頼度を加算
|
| 625 |
+
|
| 626 |
+
# object_vectorにスコアを格納
|
| 627 |
+
object_vector[i] = prompt_sum
|
| 628 |
+
|
| 629 |
+
print(object_vector)
|
| 630 |
+
return object_vector.tolist()
|
| 631 |
+
|
| 632 |
+
|
| 633 |
+
|
| 634 |
+
|
| 635 |
+
|
| 636 |
+
# APIのエンドポイント
|
| 637 |
+
@app.post("/classify-image/")
|
| 638 |
+
async def classify_image(file: UploadFile = File(...)):
|
| 639 |
+
image_path = "./temp_image.jpg"
|
| 640 |
+
|
| 641 |
+
# アップロードされた画像を保存
|
| 642 |
+
with open(image_path, "wb") as buffer:
|
| 643 |
+
buffer.write(await file.read())
|
| 644 |
+
|
| 645 |
+
# 画像をベクトル化
|
| 646 |
+
new_image_vector = process_image_vec(image_path)
|
| 647 |
+
|
| 648 |
+
# JSONファイルからデータを読み込む
|
| 649 |
+
json_filepath = "./output_vectors.json"
|
| 650 |
+
loaded_data = load_vectors_from_json(json_filepath)
|
| 651 |
+
loaded_vectors = {obj_name: np.array(vector) for obj_name, vector in loaded_data.items()}
|
| 652 |
+
loaded_object_names = list(loaded_vectors.keys())
|
| 653 |
+
|
| 654 |
+
# 既存のクラスタリング結果を読み込む
|
| 655 |
+
sums_data = load_sums_from_json("./sums_data.json")
|
| 656 |
+
|
| 657 |
+
# 新しい画像がどのクラスタに分類されるかを判定
|
| 658 |
+
new_image_cluster = classify_new_image(new_image_vector, sums_data, loaded_vectors, loaded_object_names)
|
| 659 |
+
|
| 660 |
+
return {"danger":dangerarray[int(new_image_cluster + 1)]}#バグったらここを+にして
|
| 661 |
+
|
| 662 |
+
|
| 663 |
+
@app.post("/create-mask-and-inpaint-simple-lama-special")
|
| 664 |
+
async def create_mask_and_inpaint_simple_lama(
|
| 665 |
+
image: UploadFile = File(...),
|
| 666 |
+
risk_level: int = Form(...),
|
| 667 |
+
x1: float = Form(...),
|
| 668 |
+
y1: float = Form(...),
|
| 669 |
+
x2: float = Form(...),
|
| 670 |
+
y2: float = Form(...),
|
| 671 |
+
):
|
| 672 |
+
# Extract points from the form data
|
| 673 |
+
point1 = [x1, y1]
|
| 674 |
+
point2 = [x2, y2]
|
| 675 |
+
|
| 676 |
+
# Save the input image
|
| 677 |
+
input_path = save_image(image.file, "input.jpg")
|
| 678 |
+
print('1111',point1,point2)
|
| 679 |
+
# Create a mask image (using the new process_image function)
|
| 680 |
+
mask_path = special_process_image_yolo(risk_level, input_path, point1, point2,thresholds=thresholds)
|
| 681 |
+
|
| 682 |
+
# Define the output path for the inpainted image
|
| 683 |
+
output_path = "./output_simple_lama.jpg"
|
| 684 |
+
|
| 685 |
+
# Perform inpainting with SimpleLama
|
| 686 |
+
inpaint_image_with_mask1(input_path, mask_path, output_path, resize_factor=1)
|
| 687 |
+
|
| 688 |
+
# Return the resulting image as a response
|
| 689 |
+
return FileResponse(output_path, media_type="image/jpeg", filename="output_simple_lama.jpg")
|
| 690 |
+
|
| 691 |
+
|
| 692 |
+
|
| 693 |
+
|
| 694 |
+
from PIL import Image
|
| 695 |
+
|
| 696 |
+
def resize_mask_to_match(image_path, mask_path):
|
| 697 |
+
# オリジナル画像とマスク画像を読み込む
|
| 698 |
+
original_image = Image.open(image_path)
|
| 699 |
+
mask_image = Image.open(mask_path)
|
| 700 |
+
|
| 701 |
+
# マスク画像をオリジナル画像のサイズにリサイズ
|
| 702 |
+
resized_mask = mask_image.resize(original_image.size)
|
| 703 |
+
|
| 704 |
+
# マスク画像を上書き保存
|
| 705 |
+
resized_mask.save(mask_path)
|
| 706 |
+
|
| 707 |
+
@app.post("/create-mask-and-inpaint-sum")
|
| 708 |
+
async def create_mask_sum(image: UploadFile = File(...), risk_level: int = Form(...),
|
| 709 |
+
x1: float = Form(...),
|
| 710 |
+
y1: float = Form(...),
|
| 711 |
+
x2: float = Form(...),
|
| 712 |
+
y2: float = Form(...),):
|
| 713 |
+
default_x = 0.001
|
| 714 |
+
default_y = 0.001
|
| 715 |
+
|
| 716 |
+
|
| 717 |
+
point1 = [default_x if math.isnan(x1) else x1, default_y if math.isnan(y1) else y1]
|
| 718 |
+
|
| 719 |
+
point2 = [default_x if math.isnan(x2) else x2, default_y if math.isnan(y2) else y2]
|
| 720 |
+
|
| 721 |
+
|
| 722 |
+
input_path = save_image(image.file, "input.jpg")
|
| 723 |
+
mask_path = special_process_image_yolo(risk_level, input_path, point1, point2,thresholds=thresholds)
|
| 724 |
+
# 現在のタイムスタンプを生成
|
| 725 |
+
timestamp = datetime.now().strftime("%Y%m%d_%H%M%S")
|
| 726 |
+
# 一意な識別子を生成
|
| 727 |
+
unique_id = uuid.uuid4().hex
|
| 728 |
+
output_path = f"./output_simple_lama_{timestamp}_{unique_id}.jpg"
|
| 729 |
+
|
| 730 |
+
# OpenCVでインペイント
|
| 731 |
+
inpaint_image_with_mask1(input_path, mask_path, output_path)
|
| 732 |
+
|
| 733 |
+
return FileResponse(output_path)
|
| 734 |
+
|
| 735 |
+
|
| 736 |
+
|
| 737 |
+
@app.get("/", response_class=HTMLResponse)
|
| 738 |
+
async def read_root():
|
| 739 |
+
html_content = """
|
| 740 |
+
<!DOCTYPE html>
|
| 741 |
+
<html lang="ja">
|
| 742 |
+
<head>
|
| 743 |
+
<meta charset="UTF-8">
|
| 744 |
+
<meta name="viewport" content="width=device-width, initial-scale=1.0">
|
| 745 |
+
<title>画像処理アプリ</title>
|
| 746 |
+
<!-- Bootstrap CSS -->
|
| 747 |
+
<link href="https://stackpath.bootstrapcdn.com/bootstrap/4.5.2/css/bootstrap.min.css" rel="stylesheet">
|
| 748 |
+
<!-- jQuery UI CSS -->
|
| 749 |
+
<link rel="stylesheet" href="https://code.jquery.com/ui/1.12.1/themes/base/jquery-ui.css">
|
| 750 |
+
<link href="https://cdnjs.cloudflare.com/ajax/libs/font-awesome/5.15.4/css/all.min.css" rel="stylesheet">
|
| 751 |
+
<style>
|
| 752 |
+
body {
|
| 753 |
+
background-color: #f0f0f5;
|
| 754 |
+
color: #333;
|
| 755 |
+
text-align: center;
|
| 756 |
+
padding: 40px 20px;
|
| 757 |
+
}
|
| 758 |
+
h1 {
|
| 759 |
+
color: #555;
|
| 760 |
+
margin-bottom: 30px;
|
| 761 |
+
font-weight: bold;
|
| 762 |
+
}
|
| 763 |
+
.image-preview, .processed-preview {
|
| 764 |
+
max-width: 100%;
|
| 765 |
+
height: auto;
|
| 766 |
+
border-radius: 10px;
|
| 767 |
+
box-shadow: 0 4px 15px rgba(0, 0, 0, 0.2);
|
| 768 |
+
margin-top: 20px;
|
| 769 |
+
}
|
| 770 |
+
#result {
|
| 771 |
+
margin-top: 40px;
|
| 772 |
+
display: none;
|
| 773 |
+
}
|
| 774 |
+
.slider-container {
|
| 775 |
+
text-align: left;
|
| 776 |
+
margin-top: 20px;
|
| 777 |
+
}
|
| 778 |
+
.slider-label {
|
| 779 |
+
font-size: 1.2rem;
|
| 780 |
+
color: #333;
|
| 781 |
+
}
|
| 782 |
+
#slider {
|
| 783 |
+
margin-top: 10px;
|
| 784 |
+
}
|
| 785 |
+
.btn-primary {
|
| 786 |
+
background-color: #007bff;
|
| 787 |
+
border-color: #007bff;
|
| 788 |
+
font-size: 1.2rem;
|
| 789 |
+
padding: 10px 20px;
|
| 790 |
+
border-radius: 50px;
|
| 791 |
+
}
|
| 792 |
+
.btn-primary:hover {
|
| 793 |
+
background-color: #0056b3;
|
| 794 |
+
border-color: #004085;
|
| 795 |
+
}
|
| 796 |
+
.form-control, .custom-select {
|
| 797 |
+
border-radius: 20px;
|
| 798 |
+
box-shadow: 0 2px 5px rgba(0, 0, 0, 0.1);
|
| 799 |
+
}
|
| 800 |
+
.form-control-file {
|
| 801 |
+
font-size: 1rem;
|
| 802 |
+
}
|
| 803 |
+
.form-group {
|
| 804 |
+
margin-bottom: 25px;
|
| 805 |
+
}
|
| 806 |
+
.btn-success {
|
| 807 |
+
padding: 10px 20px;
|
| 808 |
+
border-radius: 50px;
|
| 809 |
+
}
|
| 810 |
+
</style>
|
| 811 |
+
</head>
|
| 812 |
+
<body>
|
| 813 |
+
<div class="container">
|
| 814 |
+
<h1><i class="fas fa-image"></i> 画像処理アプリ - モザイクとインペイント</h1>
|
| 815 |
+
|
| 816 |
+
<div class="form-group">
|
| 817 |
+
<input type="file" id="uploadImage" class="form-control-file" accept="image/*" onchange="previewImage()">
|
| 818 |
+
</div>
|
| 819 |
+
<img id="uploadedImage" class="image-preview" src="#" alt="アップロードされた画像" style="display: none;">
|
| 820 |
+
|
| 821 |
+
<div class="form-group mt-4">
|
| 822 |
+
<label for="processingType">処理方法を選択:</label>
|
| 823 |
+
<select id="processingType" class="custom-select">
|
| 824 |
+
<option value="opencv">OpenCVインペイント</option>
|
| 825 |
+
<option value="simple_lama">Simple Lamaインペイント</option>
|
| 826 |
+
<option value="stable_diffusion">Stable Diffusionインペイント</option>
|
| 827 |
+
<option value="deep_fill_v2">DeepFillv2インペイント</option>
|
| 828 |
+
</select>
|
| 829 |
+
</div>
|
| 830 |
+
|
| 831 |
+
<div class="slider-container">
|
| 832 |
+
<label for="riskLevel" class="slider-label">リスクレベル (0-100): <span id="riskLevelLabel">50</span></label>
|
| 833 |
+
<div id="slider"></div>
|
| 834 |
+
</div>
|
| 835 |
+
|
| 836 |
+
<button class="btn btn-primary mt-4" onclick="processImage()">処理開始</button>
|
| 837 |
+
|
| 838 |
+
<div id="result" class="mt-5">
|
| 839 |
+
<h2>処理結果:</h2>
|
| 840 |
+
<img id="processedImage" class="processed-preview" src="" alt="">
|
| 841 |
+
<a id="downloadLink" class="btn btn-success mt-3" href="#" download="processed_image.jpg">処理された画像をダウンロード</a>
|
| 842 |
+
</div>
|
| 843 |
+
</div>
|
| 844 |
+
|
| 845 |
+
<!-- jQuery and Bootstrap JS -->
|
| 846 |
+
<script src="https://code.jquery.com/jquery-3.5.1.min.js"></script>
|
| 847 |
+
<script src="https://stackpath.bootstrapcdn.com/bootstrap/4.5.2/js/bootstrap.min.js"></script>
|
| 848 |
+
<!-- jQuery UI -->
|
| 849 |
+
<script src="https://code.jquery.com/ui/1.12.1/jquery-ui.js"></script>
|
| 850 |
+
|
| 851 |
+
<script>
|
| 852 |
+
$(function() {
|
| 853 |
+
// スライダーの設定
|
| 854 |
+
$("#slider").slider({
|
| 855 |
+
range: "min",
|
| 856 |
+
value: 50, // 初期値
|
| 857 |
+
min: 0,
|
| 858 |
+
max: 100,
|
| 859 |
+
slide: function(event, ui) {
|
| 860 |
+
$("#riskLevelLabel").text(ui.value);
|
| 861 |
+
}
|
| 862 |
+
});
|
| 863 |
+
});
|
| 864 |
+
|
| 865 |
+
function previewImage() {
|
| 866 |
+
const fileInput = document.getElementById('uploadImage');
|
| 867 |
+
const uploadedImage = document.getElementById('uploadedImage');
|
| 868 |
+
|
| 869 |
+
if (fileInput.files && fileInput.files[0]) {
|
| 870 |
+
const reader = new FileReader();
|
| 871 |
+
reader.onload = function (e) {
|
| 872 |
+
uploadedImage.src = e.target.result;
|
| 873 |
+
uploadedImage.style.display = 'block';
|
| 874 |
+
};
|
| 875 |
+
reader.readAsDataURL(fileInput.files[0]);
|
| 876 |
+
}
|
| 877 |
+
}
|
| 878 |
+
|
| 879 |
+
function processImage() {
|
| 880 |
+
const fileInput = document.getElementById('uploadImage');
|
| 881 |
+
const processingType = document.getElementById('processingType').value;
|
| 882 |
+
const riskLevel = $("#slider").slider("value"); // スライ���ーから値を取得
|
| 883 |
+
const resultDiv = document.getElementById('result');
|
| 884 |
+
const processedImage = document.getElementById('processedImage');
|
| 885 |
+
const downloadLink = document.getElementById('downloadLink');
|
| 886 |
+
|
| 887 |
+
if (fileInput.files.length === 0) {
|
| 888 |
+
alert("画像を選択してください。");
|
| 889 |
+
return;
|
| 890 |
+
}
|
| 891 |
+
|
| 892 |
+
const file = fileInput.files[0];
|
| 893 |
+
const formData = new FormData();
|
| 894 |
+
formData.append('image', file);
|
| 895 |
+
formData.append('risk_level', riskLevel); // リスクレベルを追加
|
| 896 |
+
|
| 897 |
+
let apiEndpoint;
|
| 898 |
+
if (processingType === "opencv") {
|
| 899 |
+
apiEndpoint = "/create-mask-and-inpaint-opencv";
|
| 900 |
+
} else if (processingType === "simple_lama") {
|
| 901 |
+
apiEndpoint = "/create-mask-and-inpaint-simple-lama";
|
| 902 |
+
} else if (processingType === "stable_diffusion") {
|
| 903 |
+
apiEndpoint = "/create-mask-and-inpaint-stable-diffusion";
|
| 904 |
+
} else if (processingType=="deep_fill_v2"){
|
| 905 |
+
apiEndpoint = "/create-mask-and-inpaint-deepfillv2";
|
| 906 |
+
}
|
| 907 |
+
|
| 908 |
+
const url = "https://wired-kitten-adequately.ngrok-free.app" + apiEndpoint;
|
| 909 |
+
|
| 910 |
+
fetch(url, {
|
| 911 |
+
method: 'POST',
|
| 912 |
+
body: formData
|
| 913 |
+
})
|
| 914 |
+
.then(response => {
|
| 915 |
+
if (!response.ok) {
|
| 916 |
+
throw new Error("Network response was not ok");
|
| 917 |
+
}
|
| 918 |
+
return response.blob();
|
| 919 |
+
})
|
| 920 |
+
.then(blob => {
|
| 921 |
+
const objectURL = URL.createObjectURL(blob);
|
| 922 |
+
processedImage.src = objectURL;
|
| 923 |
+
downloadLink.href = objectURL;
|
| 924 |
+
resultDiv.style.display = "block";
|
| 925 |
+
})
|
| 926 |
+
.catch(error => {
|
| 927 |
+
console.error("画像処理に失敗しました。", error);
|
| 928 |
+
alert("画像処理に失敗しました。");
|
| 929 |
+
});
|
| 930 |
+
}
|
| 931 |
+
</script>
|
| 932 |
+
</body>
|
| 933 |
+
</html>
|
| 934 |
+
|
| 935 |
+
|
| 936 |
+
"""
|
| 937 |
+
return HTMLResponse(content=html_content)
|
| 938 |
+
if __name__ == "__main__":
|
| 939 |
+
|
| 940 |
+
app.run(host="0.0.0.0", port=7860)
|
| 941 |
+
|
main.png
ADDED
|
output_vectors.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|
requirements.txt
ADDED
|
@@ -0,0 +1,72 @@
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
|
| 1 |
+
annotated-types==0.7.0
|
| 2 |
+
anyio==4.6.2.post1
|
| 3 |
+
certifi==2024.8.30
|
| 4 |
+
charset-normalizer==3.4.0
|
| 5 |
+
click==8.1.7
|
| 6 |
+
colorama==0.4.6
|
| 7 |
+
contourpy==1.3.0
|
| 8 |
+
cycler==0.12.1
|
| 9 |
+
diffusers==0.31.0
|
| 10 |
+
fastapi==0.115.4
|
| 11 |
+
filelock==3.16.1
|
| 12 |
+
fire==0.5.0
|
| 13 |
+
fonttools==4.54.1
|
| 14 |
+
fsspec==2024.10.0
|
| 15 |
+
futures==3.0.5
|
| 16 |
+
h11==0.14.0
|
| 17 |
+
huggingface-hub==0.26.2
|
| 18 |
+
idna==3.10
|
| 19 |
+
importlib_metadata==8.5.0
|
| 20 |
+
Jinja2==3.1.4
|
| 21 |
+
joblib==1.4.2
|
| 22 |
+
kiwisolver==1.4.7
|
| 23 |
+
MarkupSafe==3.0.2
|
| 24 |
+
matplotlib==3.9.2
|
| 25 |
+
mpmath==1.3.0
|
| 26 |
+
nest-asyncio==1.6.0
|
| 27 |
+
networkx==3.4.2
|
| 28 |
+
numpy==1.26.4
|
| 29 |
+
opencv-python==4.10.0.84
|
| 30 |
+
opencv-python-headless==4.10.0.84
|
| 31 |
+
packaging==24.1
|
| 32 |
+
pandas==2.2.3
|
| 33 |
+
Pillow==9.5.0
|
| 34 |
+
psutil==6.1.0
|
| 35 |
+
py-cpuinfo==9.0.0
|
| 36 |
+
pycocotools==2.0.8
|
| 37 |
+
pydantic==2.9.2
|
| 38 |
+
pydantic_core==2.23.4
|
| 39 |
+
pyngrok==7.2.1
|
| 40 |
+
pyparsing==3.2.0
|
| 41 |
+
python-dateutil==2.9.0.post0
|
| 42 |
+
python-multipart==0.0.17
|
| 43 |
+
pytz==2024.2
|
| 44 |
+
PyYAML==6.0.2
|
| 45 |
+
regex==2024.9.11
|
| 46 |
+
requests==2.32.3
|
| 47 |
+
safetensors==0.4.5
|
| 48 |
+
scikit-learn==1.5.2
|
| 49 |
+
scipy==1.14.1
|
| 50 |
+
seaborn==0.13.2
|
| 51 |
+
setuptools==75.3.0
|
| 52 |
+
simple-lama-inpainting==0.1.2
|
| 53 |
+
six==1.16.0
|
| 54 |
+
sniffio==1.3.1
|
| 55 |
+
starlette==0.41.2
|
| 56 |
+
supervision==0.9.0
|
| 57 |
+
sympy==1.13.1
|
| 58 |
+
termcolor==2.5.0
|
| 59 |
+
threadpoolctl==3.5.0
|
| 60 |
+
tokenizers==0.20.3
|
| 61 |
+
torch==2.5.1
|
| 62 |
+
torchvision==0.20.1
|
| 63 |
+
tqdm==4.66.6
|
| 64 |
+
transformers==4.46.2
|
| 65 |
+
typing_extensions==4.12.2
|
| 66 |
+
tzdata==2024.2
|
| 67 |
+
ultralytics==8.3.23
|
| 68 |
+
ultralytics-thop==2.0.10
|
| 69 |
+
urllib3==2.2.3
|
| 70 |
+
uvicorn==0.32.0
|
| 71 |
+
zipp==3.20.2
|
| 72 |
+
supervision
|
sums_data.json
ADDED
|
The diff for this file is too large to render.
See raw diff
|
|
|