Victor Phan
918 lines
33 KiB
Python
918 lines
33 KiB
Python
"""
|
|
API Server for Land Classification Model Training
|
|
Cho phép chọn dữ liệu và cấu hình training qua giao diện web
|
|
"""
|
|
|
|
from fastapi import FastAPI, BackgroundTasks, HTTPException
|
|
from fastapi.middleware.cors import CORSMiddleware
|
|
from fastapi.staticfiles import StaticFiles
|
|
from fastapi.responses import HTMLResponse, FileResponse
|
|
from pydantic import BaseModel
|
|
from typing import Optional, List
|
|
import uvicorn
|
|
import joblib
|
|
import json
|
|
from datetime import datetime
|
|
from pathlib import Path
|
|
import sys
|
|
|
|
# Import report generator
|
|
from report_generator import generate_training_report, generate_prediction_report
|
|
|
|
app = FastAPI(title="Land Classification Training API", version="1.0.0")
|
|
|
|
# Enable CORS
|
|
app.add_middleware(
|
|
CORSMiddleware,
|
|
allow_origins=["*"],
|
|
allow_credentials=True,
|
|
allow_methods=["*"],
|
|
allow_headers=["*"],
|
|
)
|
|
|
|
# Global training status``
|
|
training_status = {
|
|
"is_training": False,
|
|
"progress": "",
|
|
"error": None,
|
|
"result": None,
|
|
"start_time": None,
|
|
"end_time": None,
|
|
"cancel_requested": False
|
|
}
|
|
|
|
# Global prediction status
|
|
prediction_status = {
|
|
"is_predicting": False,
|
|
"progress": "",
|
|
"error": None,
|
|
"result": None,
|
|
"output_file": None,
|
|
"start_time": None,
|
|
"end_time": None
|
|
}
|
|
|
|
|
|
class TrainingConfig(BaseModel):
|
|
"""Cấu hình training"""
|
|
# Khu vực (bbox)
|
|
min_lon: float = 105.6
|
|
min_lat: float = 9.3
|
|
max_lon: float = 106.2
|
|
max_lat: float = 9.8
|
|
|
|
# Thời gian
|
|
start_date: str = "2023-03-01"
|
|
end_date: str = "2023-05-31"
|
|
|
|
# Dữ liệu
|
|
max_scenes: int = 12
|
|
cloud_cover: int = 30
|
|
resolution: int = 20 # 10m hoặc 20m
|
|
|
|
# Model parameters
|
|
model_type: str = "xgboost" # xgboost, random_forest, decision_tree, svm, cnn
|
|
n_estimators: int = 100
|
|
max_depth: int = 20
|
|
learning_rate: float = 0.1
|
|
use_gpu: bool = True
|
|
|
|
# Train/test split
|
|
test_size: float = 0.2 # Tỷ lệ dữ liệu dùng làm test (0-1)
|
|
|
|
# Cache
|
|
use_cache: bool = True # Cache dataset để test nhanh hơn
|
|
|
|
# Training data
|
|
training_shapefile: str = "train/ST_training data_updated_1130points_new.shp"
|
|
|
|
|
|
class PredictionConfig(BaseModel):
|
|
"""Cấu hình dự đoán"""
|
|
# Model to use
|
|
model_filename: str
|
|
|
|
# Khu vực (bbox)
|
|
min_lon: float = 105.6
|
|
min_lat: float = 9.3
|
|
max_lon: float = 106.2
|
|
max_lat: float = 9.8
|
|
|
|
# Thời gian
|
|
start_date: str = "2023-03-01"
|
|
end_date: str = "2023-05-31"
|
|
|
|
# Dữ liệu
|
|
max_scenes: int = 12
|
|
cloud_cover: int = 30
|
|
resolution: int = 20
|
|
|
|
|
|
class TrainingStatus(BaseModel):
|
|
"""Trạng thái training"""
|
|
is_training: bool
|
|
progress: str
|
|
error: Optional[str]
|
|
result: Optional[dict]
|
|
start_time: Optional[str]
|
|
end_time: Optional[str]
|
|
|
|
|
|
@app.get("/", response_class=HTMLResponse)
|
|
async def root():
|
|
"""Serve giao diện web"""
|
|
html_file = Path(__file__).parent / "training_interface.html"
|
|
if html_file.exists():
|
|
return FileResponse(html_file)
|
|
else:
|
|
return HTMLResponse("""
|
|
<html>
|
|
<head><title>Training Interface</title></head>
|
|
<body>
|
|
<h1>Land Classification Training API</h1>
|
|
<p>API Documentation: <a href="/docs">/docs</a></p>
|
|
<p>Training Interface: Tạo file training_interface.html</p>
|
|
</body>
|
|
</html>
|
|
""")
|
|
|
|
|
|
@app.get("/api/config/presets")
|
|
async def get_presets():
|
|
"""Lấy các preset cấu hình sẵn"""
|
|
return {
|
|
"presets": [
|
|
{
|
|
"name": "PC - Nhỏ (3 tháng, 20m, 12 scenes)",
|
|
"config": {
|
|
"min_lon": 105.6, "min_lat": 9.3, "max_lon": 106.2, "max_lat": 9.8,
|
|
"start_date": "2023-03-01", "end_date": "2023-05-31",
|
|
"max_scenes": 12, "cloud_cover": 30, "resolution": 20,
|
|
"test_size": 0.2
|
|
}
|
|
},
|
|
{
|
|
"name": "Server - Trung bình (6 tháng, 10m, 30 scenes)",
|
|
"config": {
|
|
"min_lon": 105.5, "min_lat": 9.2, "max_lon": 106.4, "max_lat": 10.0,
|
|
"start_date": "2023-01-01", "end_date": "2023-06-30",
|
|
"max_scenes": 30, "cloud_cover": 30, "resolution": 10,
|
|
"test_size": 0.2
|
|
}
|
|
},
|
|
{
|
|
"name": "Full - Lớn (1 năm, 10m, 60 scenes)",
|
|
"config": {
|
|
"min_lon": 105.5, "min_lat": 9.2, "max_lon": 106.4, "max_lat": 10.0,
|
|
"start_date": "2022-09-01", "end_date": "2023-10-01",
|
|
"max_scenes": 60, "cloud_cover": 50, "resolution": 10,
|
|
"test_size": 0.2
|
|
}
|
|
}
|
|
]
|
|
}
|
|
|
|
|
|
@app.get("/api/training/status", response_model=TrainingStatus)
|
|
async def get_training_status():
|
|
"""Kiểm tra trạng thái training"""
|
|
return training_status
|
|
|
|
|
|
@app.post("/api/training/start")
|
|
async def start_training(config: TrainingConfig, background_tasks: BackgroundTasks):
|
|
"""Bắt đầu training với config đã chọn"""
|
|
global training_status
|
|
|
|
if training_status["is_training"]:
|
|
raise HTTPException(status_code=400, detail="Training đang chạy, vui lòng đợi")
|
|
|
|
# Reset status
|
|
training_status = {
|
|
"is_training": True,
|
|
"progress": "Đang khởi tạo...",
|
|
"error": None,
|
|
"result": None,
|
|
"start_time": datetime.now().isoformat(),
|
|
"end_time": None
|
|
}
|
|
|
|
# Run training in background
|
|
background_tasks.add_task(run_training, config)
|
|
|
|
return {"message": "Training đã bắt đầu", "status": training_status}
|
|
|
|
|
|
@app.post("/api/training/stop")
|
|
async def stop_training():
|
|
"""Dừng training (nếu đang chạy)"""
|
|
global training_status
|
|
|
|
if not training_status["is_training"]:
|
|
return {"message": "Không có training nào đang chạy"}
|
|
|
|
# Set cancel flag - the training will check this and stop
|
|
training_status["cancel_requested"] = True
|
|
training_status["progress"] = "Đang hủy training..."
|
|
|
|
return {"message": "Đang dừng training..."}
|
|
|
|
|
|
@app.post("/api/cache/clear")
|
|
async def clear_cache():
|
|
"""Xóa cache dataset"""
|
|
import shutil
|
|
cache_dir = Path("dataset_cache")
|
|
|
|
if not cache_dir.exists():
|
|
return {"message": "Không có cache để xóa", "deleted": 0}
|
|
|
|
# Count files
|
|
cache_files = list(cache_dir.glob("*.joblib"))
|
|
count = len(cache_files)
|
|
|
|
# Delete all cache files
|
|
for cache_file in cache_files:
|
|
try:
|
|
cache_file.unlink()
|
|
except:
|
|
pass
|
|
|
|
return {"message": f"Đã xóa {count} file cache", "deleted": count}
|
|
|
|
|
|
@app.get("/api/cache/info")
|
|
async def get_cache_info():
|
|
"""Lấy thông tin về cache với metadata đầy đủ"""
|
|
cache_dir = Path("dataset_cache")
|
|
|
|
if not cache_dir.exists():
|
|
return {"exists": False, "files": [], "total_size_mb": 0}
|
|
|
|
cache_files = []
|
|
total_size = 0
|
|
|
|
for cache_file in cache_dir.glob("*.joblib"):
|
|
size = cache_file.stat().st_size
|
|
total_size += size
|
|
|
|
# Try to load metadata from cache
|
|
metadata = {}
|
|
try:
|
|
cached_data = joblib.load(cache_file)
|
|
if isinstance(cached_data, dict):
|
|
metadata = {
|
|
"bbox": cached_data.get("bbox", []),
|
|
"time_range": cached_data.get("time_range", ""),
|
|
"resolution": cached_data.get("resolution", 20),
|
|
"n_samples": len(cached_data.get("features", [])),
|
|
"created": cached_data.get("timestamp", "")
|
|
}
|
|
# Parse time_range to get start/end dates
|
|
if metadata["time_range"]:
|
|
time_parts = metadata["time_range"].split("/")
|
|
if len(time_parts) == 2:
|
|
metadata["start_date"] = time_parts[0]
|
|
metadata["end_date"] = time_parts[1]
|
|
# Parse bbox to get min/max lon/lat
|
|
if metadata["bbox"] and len(metadata["bbox"]) == 4:
|
|
metadata["min_lon"] = metadata["bbox"][0]
|
|
metadata["min_lat"] = metadata["bbox"][1]
|
|
metadata["max_lon"] = metadata["bbox"][2]
|
|
metadata["max_lat"] = metadata["bbox"][3]
|
|
except Exception as e:
|
|
print(f"Error loading cache metadata: {e}")
|
|
|
|
cache_files.append({
|
|
"filename": cache_file.name,
|
|
"size_mb": round(size / 1024 / 1024, 2),
|
|
"modified": datetime.fromtimestamp(cache_file.stat().st_mtime).isoformat(),
|
|
"metadata": metadata
|
|
})
|
|
|
|
# Sort by modified time (newest first)
|
|
cache_files.sort(key=lambda x: x["modified"], reverse=True)
|
|
|
|
return {
|
|
"exists": True,
|
|
"files": cache_files,
|
|
"count": len(cache_files),
|
|
"total_size_mb": round(total_size / 1024 / 1024, 2)
|
|
}
|
|
|
|
|
|
|
|
@app.get("/api/models/list")
|
|
async def list_models():
|
|
"""Liệt kê các model đã train"""
|
|
model_dir = Path("model_train")
|
|
if not model_dir.exists():
|
|
return {"models": []}
|
|
|
|
models = []
|
|
for model_file in model_dir.glob("*.joblib"):
|
|
info_file = model_file.with_suffix('.json')
|
|
info = {}
|
|
if info_file.exists():
|
|
with open(info_file) as f:
|
|
info = json.load(f)
|
|
|
|
models.append({
|
|
"filename": model_file.name,
|
|
"created": datetime.fromtimestamp(model_file.stat().st_mtime).isoformat(),
|
|
"size_mb": round(model_file.stat().st_size / 1024 / 1024, 2),
|
|
"info": info
|
|
})
|
|
|
|
# Sort by creation time (newest first)
|
|
models.sort(key=lambda x: x["created"], reverse=True)
|
|
return {"models": models}
|
|
|
|
|
|
# ============ REPORTS API ============
|
|
|
|
@app.get("/api/reports/list")
|
|
async def list_reports():
|
|
"""Liệt kê các báo cáo đã tạo"""
|
|
reports_dir = Path("reports")
|
|
reports_dir.mkdir(exist_ok=True)
|
|
|
|
reports = []
|
|
for report_file in reports_dir.glob("*.html"):
|
|
# Determine report type from filename
|
|
if "training" in report_file.name:
|
|
report_type = "training"
|
|
elif "prediction" in report_file.name:
|
|
report_type = "prediction"
|
|
else:
|
|
report_type = "unknown"
|
|
|
|
reports.append({
|
|
"filename": report_file.name,
|
|
"type": report_type,
|
|
"created": datetime.fromtimestamp(report_file.stat().st_mtime).isoformat(),
|
|
"size_kb": round(report_file.stat().st_size / 1024, 2),
|
|
"view_url": f"/api/reports/view/{report_file.name}",
|
|
"download_url": f"/api/reports/download/{report_file.name}"
|
|
})
|
|
|
|
# Sort by creation time (newest first)
|
|
reports.sort(key=lambda x: x["created"], reverse=True)
|
|
return {"reports": reports, "count": len(reports)}
|
|
|
|
|
|
@app.get("/api/reports/view/{filename}", response_class=HTMLResponse)
|
|
async def view_report(filename: str):
|
|
"""Xem báo cáo HTML trực tiếp"""
|
|
reports_dir = Path("reports")
|
|
file_path = reports_dir / filename
|
|
|
|
# Security check
|
|
if ".." in filename or "/" in filename or "\\" in filename:
|
|
raise HTTPException(status_code=400, detail="Invalid filename")
|
|
|
|
if not file_path.exists():
|
|
raise HTTPException(status_code=404, detail=f"Report không tồn tại: {filename}")
|
|
|
|
with open(file_path, 'r', encoding='utf-8') as f:
|
|
html_content = f.read()
|
|
|
|
return HTMLResponse(content=html_content)
|
|
|
|
|
|
@app.get("/api/reports/download/{filename}")
|
|
async def download_report(filename: str):
|
|
"""Download báo cáo HTML"""
|
|
reports_dir = Path("reports")
|
|
file_path = reports_dir / filename
|
|
|
|
# Security check
|
|
if ".." in filename or "/" in filename or "\\" in filename:
|
|
raise HTTPException(status_code=400, detail="Invalid filename")
|
|
|
|
if not file_path.exists():
|
|
raise HTTPException(status_code=404, detail=f"Report không tồn tại: {filename}")
|
|
|
|
return FileResponse(
|
|
path=str(file_path),
|
|
filename=filename,
|
|
media_type="text/html",
|
|
headers={
|
|
"Content-Disposition": f"attachment; filename={filename}"
|
|
}
|
|
)
|
|
|
|
|
|
@app.delete("/api/reports/delete/{filename}")
|
|
async def delete_report(filename: str):
|
|
"""Xóa một báo cáo"""
|
|
reports_dir = Path("reports")
|
|
file_path = reports_dir / filename
|
|
|
|
# Security check
|
|
if ".." in filename or "/" in filename or "\\" in filename:
|
|
raise HTTPException(status_code=400, detail="Invalid filename")
|
|
|
|
if not file_path.exists():
|
|
raise HTTPException(status_code=404, detail=f"Report không tồn tại: {filename}")
|
|
|
|
try:
|
|
file_path.unlink()
|
|
return {"message": f"Đã xóa báo cáo: {filename}", "success": True}
|
|
except Exception as e:
|
|
raise HTTPException(status_code=500, detail=f"Không thể xóa: {str(e)}")
|
|
|
|
|
|
@app.post("/api/prediction/start")
|
|
async def start_prediction(config: PredictionConfig, background_tasks: BackgroundTasks):
|
|
"""Bắt đầu dự đoán"""
|
|
global prediction_status
|
|
|
|
if prediction_status["is_predicting"]:
|
|
raise HTTPException(status_code=400, detail="Đang có dự đoán khác đang chạy")
|
|
|
|
# Reset status
|
|
prediction_status = {
|
|
"is_predicting": True,
|
|
"progress": "Đang khởi động...",
|
|
"error": None,
|
|
"result": None,
|
|
"output_file": None,
|
|
"start_time": datetime.now().isoformat(),
|
|
"end_time": None
|
|
}
|
|
|
|
# Run prediction in background
|
|
background_tasks.add_task(run_prediction, config)
|
|
|
|
return {"message": "Đã bắt đầu dự đoán", "status": prediction_status}
|
|
|
|
|
|
@app.get("/api/prediction/status")
|
|
async def get_prediction_status():
|
|
"""Kiểm tra trạng thái dự đoán"""
|
|
return prediction_status
|
|
|
|
|
|
async def run_training(config: TrainingConfig):
|
|
"""Chạy training process"""
|
|
global training_status
|
|
|
|
try:
|
|
training_status["cancel_requested"] = False
|
|
training_status["progress"] = "Đang import thư viện..."
|
|
|
|
# Import training module
|
|
from train_module import train_model
|
|
|
|
training_status["progress"] = "Đang load dữ liệu Sentinel-2..."
|
|
|
|
# Function to check if training should be cancelled
|
|
def should_cancel():
|
|
return training_status.get("cancel_requested", False)
|
|
|
|
# Run training
|
|
result = train_model(
|
|
bbox=[config.min_lon, config.min_lat, config.max_lon, config.max_lat],
|
|
time_range=f"{config.start_date}/{config.end_date}",
|
|
max_scenes=config.max_scenes,
|
|
cloud_cover=config.cloud_cover,
|
|
resolution=config.resolution,
|
|
training_shapefile=config.training_shapefile,
|
|
model_type=config.model_type,
|
|
n_estimators=config.n_estimators,
|
|
max_depth=config.max_depth,
|
|
learning_rate=config.learning_rate,
|
|
use_gpu=config.use_gpu,
|
|
use_cache=config.use_cache,
|
|
test_size=config.test_size,
|
|
status_callback=lambda msg: update_progress(msg),
|
|
cancel_check=should_cancel
|
|
)
|
|
|
|
if training_status.get("cancel_requested", False):
|
|
training_status["is_training"] = False
|
|
training_status["progress"] = "Đã hủy training"
|
|
training_status["error"] = "Training cancelled by user"
|
|
else:
|
|
training_status["is_training"] = False
|
|
training_status["progress"] = "Hoàn thành! Đang tạo báo cáo..."
|
|
training_status["result"] = result
|
|
|
|
# Auto generate report
|
|
if result.get("success", False):
|
|
try:
|
|
report_path, _ = generate_training_report(result)
|
|
training_status["result"]["report_path"] = report_path
|
|
training_status["result"]["report_filename"] = Path(report_path).name
|
|
training_status["progress"] = "Hoàn thành! Báo cáo đã được tạo."
|
|
print(f"[REPORT] Generated: {report_path}")
|
|
except Exception as e:
|
|
print(f"[REPORT ERROR] Failed to generate report: {e}")
|
|
training_status["progress"] = "Hoàn thành! (Không thể tạo báo cáo)"
|
|
|
|
training_status["end_time"] = datetime.now().isoformat()
|
|
|
|
except Exception as e:
|
|
training_status["is_training"] = False
|
|
training_status["error"] = str(e)
|
|
training_status["progress"] = f"Lỗi: {str(e)}"
|
|
training_status["end_time"] = datetime.now().isoformat()
|
|
import traceback
|
|
print(traceback.format_exc())
|
|
|
|
|
|
def update_progress(message: str):
|
|
"""Cập nhật progress message"""
|
|
global training_status
|
|
training_status["progress"] = message
|
|
print(f"[PROGRESS] {message}")
|
|
|
|
|
|
def update_prediction_progress(message: str):
|
|
"""Cập nhật prediction progress message"""
|
|
global prediction_status
|
|
prediction_status["progress"] = message
|
|
print(f"[PREDICTION PROGRESS] {message}")
|
|
|
|
|
|
async def run_prediction(config: PredictionConfig):
|
|
"""Chạy prediction process - Áp dụng phương pháp từ 02.predict_ODC.ipynb"""
|
|
global prediction_status
|
|
|
|
try:
|
|
prediction_status["progress"] = "Đang import thư viện..."
|
|
|
|
# Import required libraries
|
|
import xarray as xr
|
|
import numpy as np
|
|
from datetime import datetime as dt
|
|
import rioxarray
|
|
import dask.array as da
|
|
|
|
prediction_status["progress"] = "Đang load model..."
|
|
|
|
# Load model
|
|
model_path = Path("model_train") / config.model_filename
|
|
if not model_path.exists():
|
|
raise FileNotFoundError(f"Model không tồn tại: {config.model_filename}")
|
|
|
|
model_data = joblib.load(model_path)
|
|
|
|
# Extract model from dict (models are saved as {'model': xgb_model, 'label_encoder': encoder})
|
|
if isinstance(model_data, dict):
|
|
model = model_data.get('model')
|
|
label_encoder = model_data.get('label_encoder')
|
|
else:
|
|
model = model_data
|
|
label_encoder = None
|
|
|
|
# Check if it's a CNN model (PyTorch)
|
|
is_cnn_model = hasattr(model, '__class__') and 'CNN' in model.__class__.__name__
|
|
if is_cnn_model:
|
|
prediction_status["progress"] = "Phát hiện PyTorch CNN model..."
|
|
# Import PyTorch if needed
|
|
try:
|
|
import torch
|
|
except ImportError:
|
|
raise ImportError("PyTorch is required for CNN prediction. Install: pip install torch")
|
|
|
|
prediction_status["progress"] = "Đang kết nối Microsoft Planetary Computer..."
|
|
|
|
# Import and use Microsoft Planetary Computer STAC API
|
|
import pystac_client
|
|
import planetary_computer
|
|
from odc.stac import load
|
|
|
|
catalog = pystac_client.Client.open(
|
|
"https://planetarycomputer.microsoft.com/api/stac/v1",
|
|
modifier=planetary_computer.sign_inplace,
|
|
)
|
|
|
|
bbox = [config.min_lon, config.min_lat, config.max_lon, config.max_lat]
|
|
time_range = f"{config.start_date}/{config.end_date}"
|
|
|
|
# ============ BƯỚC 1: TẢI DỮ LIỆU SENTINEL-2 ============
|
|
prediction_status["progress"] = "Đang tải dữ liệu Sentinel-2..."
|
|
|
|
# Search Sentinel-2 data
|
|
s2_search = catalog.search(
|
|
collections=["sentinel-2-l2a"],
|
|
bbox=bbox,
|
|
datetime=time_range,
|
|
query={"eo:cloud_cover": {"lt": config.cloud_cover}}
|
|
)
|
|
|
|
s2_items = list(s2_search.items())
|
|
if not s2_items:
|
|
raise ValueError("Không tìm thấy dữ liệu Sentinel-2 cho khu vực và thời gian này")
|
|
|
|
s2_items = s2_items[:config.max_scenes]
|
|
prediction_status["progress"] = f"Đang xử lý {len(s2_items)} scenes Sentinel-2..."
|
|
|
|
# Load Sentinel-2 data
|
|
s2_data = load(
|
|
s2_items,
|
|
bbox=bbox,
|
|
chunks={"time": 1, "x": 2048, "y": 2048},
|
|
groupby="solar_day",
|
|
resolution=config.resolution
|
|
)
|
|
|
|
# ============ BƯỚC 2: TÍNH NDVI VÀ XỬ LÝ MÂY ============
|
|
prediction_status["progress"] = "Đang tính toán NDVI và xử lý mây..."
|
|
|
|
# Calculate NDVI using Sentinel-2 band names (B08 = NIR, B04 = Red)
|
|
nir = s2_data["B08"].astype('float32')
|
|
red = s2_data["B04"].astype('float32')
|
|
ndvi = (nir - red) / (nir + red + 1e-8)
|
|
|
|
# Mask clouds using SCL band if available
|
|
if "SCL" in s2_data:
|
|
scl = s2_data["SCL"]
|
|
# SCL values: 4=vegetation, 5=bare soil, 6=water - these are clear
|
|
# 3=cloud shadow, 8=cloud medium, 9=cloud high, 10=cirrus - mask these
|
|
cloud_mask = (scl == 3) | (scl == 8) | (scl == 9) | (scl == 10)
|
|
ndvi = ndvi.where(~cloud_mask)
|
|
|
|
# ============ BƯỚC 3: ĐIỀN GIÁ TRỊ NAN (FILL NAN) ============
|
|
prediction_status["progress"] = "Đang điền giá trị bị che mây..."
|
|
|
|
# Fill NaN using forward fill and backward fill
|
|
ndvi_filled = ndvi.ffill(dim='time').bfill(dim='time')
|
|
|
|
# Resample to monthly average
|
|
prediction_status["progress"] = "Đang tính trung bình NDVI theo tháng..."
|
|
ndvi_monthly = ndvi_filled.resample(time="1ME").mean()
|
|
|
|
# Compute NDVI (convert from dask to numpy)
|
|
ndvi_monthly = ndvi_monthly.compute()
|
|
|
|
# ============ BƯỚC 4: TẢI DỮ LIỆU SENTINEL-1 (VH, VV) ============
|
|
prediction_status["progress"] = "Đang tải dữ liệu Sentinel-1 (Radar)..."
|
|
|
|
# Search Sentinel-1 data
|
|
s1_search = catalog.search(
|
|
collections=["sentinel-1-rtc"],
|
|
bbox=bbox,
|
|
datetime=time_range,
|
|
)
|
|
|
|
s1_items = list(s1_search.items())
|
|
|
|
if s1_items:
|
|
s1_items = s1_items[:config.max_scenes]
|
|
prediction_status["progress"] = f"Đang xử lý {len(s1_items)} scenes Sentinel-1..."
|
|
|
|
# Load Sentinel-1 data (without like= to avoid conflict with bbox/resolution)
|
|
s1_data = load(
|
|
s1_items,
|
|
bbox=bbox,
|
|
chunks={"time": 1, "x": 2048, "y": 2048},
|
|
groupby="sat:absolute_orbit",
|
|
resolution=config.resolution
|
|
)
|
|
|
|
# Extract VH and VV bands
|
|
if "vh" in s1_data and "vv" in s1_data:
|
|
vh = s1_data["vh"].astype('float32')
|
|
vv = s1_data["vv"].astype('float32')
|
|
|
|
# Resample to monthly average
|
|
prediction_status["progress"] = "Đang tính trung bình VH/VV theo tháng..."
|
|
vh_monthly = vh.resample(time="1ME").mean().compute()
|
|
vv_monthly = vv.resample(time="1ME").mean().compute()
|
|
|
|
use_radar = True
|
|
else:
|
|
prediction_status["progress"] = "Không tìm thấy bands VH/VV, tiếp tục với NDVI..."
|
|
use_radar = False
|
|
else:
|
|
prediction_status["progress"] = "Không có dữ liệu Sentinel-1, tiếp tục với NDVI..."
|
|
use_radar = False
|
|
|
|
# ============ BƯỚC 5: CHUẨN BỊ FEATURES CHO DỰ ĐOÁN ============
|
|
prediction_status["progress"] = "Đang chuẩn bị features cho dự đoán..."
|
|
|
|
# Get shape information
|
|
n_times_ndvi = len(ndvi_monthly.time)
|
|
y_size = len(ndvi_monthly.y)
|
|
x_size = len(ndvi_monthly.x)
|
|
n_pixels = y_size * x_size
|
|
|
|
# Prepare NDVI features (flatten each time step)
|
|
ndvi_features = []
|
|
for t in range(n_times_ndvi):
|
|
ndvi_t = ndvi_monthly.isel(time=t).values.flatten()
|
|
ndvi_features.append(ndvi_t)
|
|
|
|
# Stack NDVI features
|
|
features = np.column_stack(ndvi_features)
|
|
|
|
# Add radar features if available
|
|
if use_radar:
|
|
n_times_vh = len(vh_monthly.time)
|
|
n_times_vv = len(vv_monthly.time)
|
|
|
|
# Add VH features
|
|
for t in range(min(n_times_vh, n_times_ndvi)):
|
|
vh_t = vh_monthly.isel(time=t).values.flatten()
|
|
# Resize if needed
|
|
if len(vh_t) != n_pixels:
|
|
vh_t = np.resize(vh_t, n_pixels)
|
|
features = np.column_stack([features, vh_t])
|
|
|
|
# Add VV features
|
|
for t in range(min(n_times_vv, n_times_ndvi)):
|
|
vv_t = vv_monthly.isel(time=t).values.flatten()
|
|
# Resize if needed
|
|
if len(vv_t) != n_pixels:
|
|
vv_t = np.resize(vv_t, n_pixels)
|
|
features = np.column_stack([features, vv_t])
|
|
|
|
# Handle NaN values in features✓ CNN PyTorch: Mạnh nhất với ảnh vệ tinh, tự học features, tương thích GPU tốt, cần pip install torch
|
|
features = np.nan_to_num(features, nan=0.0)
|
|
|
|
# ============ BƯỚC 6: DỰ ĐOÁN ============
|
|
# Check model's expected feature count and adjust
|
|
try:
|
|
# Get expected number of features from model
|
|
if is_cnn_model:
|
|
# For PyTorch CNN, get n_features from model
|
|
expected_features = model.n_features
|
|
elif hasattr(model, 'n_features_in_'):
|
|
expected_features = model.n_features_in_
|
|
elif hasattr(model, 'feature_names_in_'):
|
|
expected_features = len(model.feature_names_in_)
|
|
else:
|
|
# Try to get from booster for XGBoost
|
|
try:
|
|
expected_features = model.get_booster().num_features()
|
|
except:
|
|
expected_features = features.shape[1]
|
|
|
|
prediction_status["progress"] = f"Model cần {expected_features} features, đang có {features.shape[1]} features..."
|
|
|
|
# Adjust features to match model
|
|
if features.shape[1] > expected_features:
|
|
# Trim to expected number (use only first N features - NDVI only)
|
|
prediction_status["progress"] = f"Cắt bớt features từ {features.shape[1]} xuống {expected_features}..."
|
|
features = features[:, :expected_features]
|
|
elif features.shape[1] < expected_features:
|
|
# Pad with zeros or repeat last features
|
|
prediction_status["progress"] = f"Thêm features từ {features.shape[1]} lên {expected_features}..."
|
|
n_missing = expected_features - features.shape[1]
|
|
# Repeat last feature column to fill
|
|
padding = np.tile(features[:, -1:], (1, n_missing))
|
|
features = np.column_stack([features, padding])
|
|
except Exception as e:
|
|
prediction_status["progress"] = f"Không thể xác định số features của model, tiếp tục với {features.shape[1]} features..."
|
|
|
|
prediction_status["progress"] = f"Đang dự đoán với {features.shape[1]} features..."
|
|
|
|
# Make prediction
|
|
if is_cnn_model:
|
|
# PyTorch CNN prediction
|
|
predictions = model.predict(features)
|
|
else:
|
|
predictions = model.predict(features)
|
|
|
|
# Decode labels if label_encoder exists
|
|
if label_encoder is not None:
|
|
try:
|
|
predictions = label_encoder.inverse_transform(predictions)
|
|
except:
|
|
pass # Keep numeric predictions if inverse_transform fails
|
|
|
|
# Reshape to original shape
|
|
pred_shape = (y_size, x_size)
|
|
predictions_2d = predictions.reshape(pred_shape)
|
|
|
|
# ============ BƯỚC 7: TẠO OUTPUT VÀ LƯU KẾT QUẢ ============
|
|
prediction_status["progress"] = "Đang tạo bản đồ phân loại..."
|
|
|
|
# Create output xarray
|
|
prediction_da = xr.DataArray(
|
|
predictions_2d,
|
|
coords={
|
|
"y": ndvi_monthly.y,
|
|
"x": ndvi_monthly.x
|
|
},
|
|
dims=["y", "x"],
|
|
name="classification"
|
|
)
|
|
|
|
# Save output
|
|
output_dir = Path("predictions")
|
|
output_dir.mkdir(exist_ok=True)
|
|
|
|
timestamp = dt.now().strftime("%Y%m%d_%H%M%S")
|
|
output_file = output_dir / f"prediction_{timestamp}.tif"
|
|
|
|
prediction_status["progress"] = "Đang lưu kết quả GeoTIFF..."
|
|
|
|
# Set CRS and save as GeoTIFF
|
|
if hasattr(s2_data, 'rio') and s2_data.rio.crs is not None:
|
|
prediction_da.rio.write_crs(s2_data.rio.crs, inplace=True)
|
|
else:
|
|
prediction_da.rio.write_crs("EPSG:4326", inplace=True)
|
|
|
|
prediction_da.rio.to_raster(str(output_file), driver="GTiff")
|
|
|
|
# Get unique classes for result
|
|
unique_classes = np.unique(predictions_2d)
|
|
unique_classes = unique_classes[~np.isnan(unique_classes)].tolist()
|
|
|
|
prediction_status["is_predicting"] = False
|
|
prediction_status["progress"] = "Hoàn thành! Đang tạo báo cáo..."
|
|
prediction_status["output_file"] = str(output_file)
|
|
prediction_status["result"] = {
|
|
"output_file": str(output_file),
|
|
"shape": list(pred_shape),
|
|
"unique_classes": unique_classes,
|
|
"bbox": bbox,
|
|
"time_range": time_range,
|
|
"n_features": features.shape[1],
|
|
"n_times_ndvi": n_times_ndvi,
|
|
"used_radar": use_radar,
|
|
"model_used": config.model_filename
|
|
}
|
|
|
|
# Auto generate prediction report
|
|
try:
|
|
report_path, _ = generate_prediction_report(prediction_status["result"])
|
|
prediction_status["result"]["report_path"] = report_path
|
|
prediction_status["result"]["report_filename"] = Path(report_path).name
|
|
prediction_status["progress"] = "Hoàn thành! Báo cáo đã được tạo."
|
|
print(f"[PREDICTION REPORT] Generated: {report_path}")
|
|
except Exception as e:
|
|
print(f"[PREDICTION REPORT ERROR] Failed to generate report: {e}")
|
|
prediction_status["progress"] = "Hoàn thành! (Không thể tạo báo cáo)"
|
|
|
|
prediction_status["end_time"] = dt.now().isoformat()
|
|
|
|
except Exception as e:
|
|
prediction_status["is_predicting"] = False
|
|
prediction_status["error"] = str(e)
|
|
prediction_status["progress"] = f"Lỗi: {str(e)}"
|
|
prediction_status["end_time"] = dt.now().isoformat()
|
|
import traceback
|
|
print(traceback.format_exc())
|
|
|
|
|
|
@app.get("/api/predictions/list")
|
|
async def list_predictions():
|
|
"""Lấy danh sách các file prediction đã tạo"""
|
|
predictions_dir = Path("predictions")
|
|
predictions_dir.mkdir(exist_ok=True)
|
|
|
|
predictions = []
|
|
for pred_file in predictions_dir.glob("*.tif"):
|
|
predictions.append({
|
|
"filename": pred_file.name,
|
|
"created": datetime.fromtimestamp(pred_file.stat().st_mtime).isoformat(),
|
|
"size_mb": round(pred_file.stat().st_size / 1024 / 1024, 2),
|
|
"download_url": f"/api/predictions/download/{pred_file.name}"
|
|
})
|
|
|
|
# Sort by creation time (newest first)
|
|
predictions.sort(key=lambda x: x["created"], reverse=True)
|
|
return {"predictions": predictions}
|
|
|
|
|
|
@app.get("/api/predictions/download/{filename}")
|
|
async def download_prediction(filename: str):
|
|
"""Download file prediction GeoTIFF"""
|
|
predictions_dir = Path("predictions")
|
|
file_path = predictions_dir / filename
|
|
|
|
# Security check: ensure filename doesn't contain path traversal
|
|
if ".." in filename or "/" in filename or "\\" in filename:
|
|
raise HTTPException(status_code=400, detail="Invalid filename")
|
|
|
|
if not file_path.exists():
|
|
raise HTTPException(status_code=404, detail=f"File không tồn tại: {filename}")
|
|
|
|
return FileResponse(
|
|
path=str(file_path),
|
|
filename=filename,
|
|
media_type="image/tiff",
|
|
headers={
|
|
"Content-Disposition": f"attachment; filename={filename}"
|
|
}
|
|
)
|
|
|
|
|
|
if __name__ == "__main__":
|
|
print("=" * 70)
|
|
print("🚀 LAND CLASSIFICATION TRAINING API SERVER")
|
|
print("=" * 70)
|
|
print("\n📍 Endpoints:")
|
|
print(" - Web Interface: http://localhost:8000")
|
|
print(" - API Docs: http://localhost:8000/docs")
|
|
print(" - Start Training: POST http://localhost:8000/api/training/start")
|
|
print(" - Check Status: GET http://localhost:8000/api/training/status")
|
|
print("\n" + "=" * 70)
|
|
|
|
uvicorn.run(app, host="0.0.0.0", port=8000, log_level="info")
|