Victor Phan
767 lines
49 KiB
Plaintext
767 lines
49 KiB
Plaintext
{
|
||
"cells": [
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 1,
|
||
"id": "17da4353",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"✅ Import thành công\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"# Import libraries\n",
|
||
"import numpy as np\n",
|
||
"import pandas as pd\n",
|
||
"import xarray as xr\n",
|
||
"import matplotlib.pyplot as plt\n",
|
||
"import seaborn as sns\n",
|
||
"from datetime import datetime\n",
|
||
"\n",
|
||
"# Element84 Earth Search STAC\n",
|
||
"import pystac_client\n",
|
||
"from odc.stac import load\n",
|
||
"\n",
|
||
"# Machine Learning\n",
|
||
"import torch\n",
|
||
"import torch.nn as nn\n",
|
||
"import torch.optim as optim\n",
|
||
"from torch.utils.data import TensorDataset, DataLoader\n",
|
||
"from sklearn.metrics import classification_report, confusion_matrix, accuracy_score\n",
|
||
"from sklearn.model_selection import train_test_split\n",
|
||
"\n",
|
||
"print(\"✅ Import thành công\")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 2,
|
||
"id": "9c063be3",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"✅ Kết nối Element84 Earth Search thành công\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"# Kết nối Element84 Earth Search (AWS-hosted STAC API)\n",
|
||
"catalog = pystac_client.Client.open(\n",
|
||
" \"https://earth-search.aws.element84.com/v1\"\n",
|
||
")\n",
|
||
"print(\"✅ Kết nối Element84 Earth Search thành công\")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 4,
|
||
"id": "d87beed2",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
"✅ Đã đọc shapefile: 1130 points\n",
|
||
" Columns: ['No', 'X', 'Y', 'LU2022', 'Hientrang', 'HT_code', 'geometry']\n",
|
||
" CRS: EPSG:32648\n",
|
||
"⚠️ Không tìm thấy column class, hiển thị 5 dòng đầu:\n",
|
||
" No X Y LU2022 Hientrang HT_code \\\n",
|
||
"0 1.0 603860.819 1081162.862 Pomelo CLN 3 \n",
|
||
"1 2.0 601306.410 1082782.940 Pomelo CLN 3 \n",
|
||
"2 3.0 601084.510 1081351.870 Pomelo CLN 3 \n",
|
||
"3 4.0 602193.760 1079205.220 Pomelo CLN 3 \n",
|
||
"4 5.0 602459.000 1080946.000 Pomelo CLN 3 \n",
|
||
"\n",
|
||
" geometry longitude latitude \n",
|
||
"0 POINT (603860.819 1081162.862) 603860.819 1081162.862 \n",
|
||
"1 POINT (601306.41 1082782.94) 601306.410 1082782.940 \n",
|
||
"2 POINT (601084.51 1081351.87) 601084.510 1081351.870 \n",
|
||
"3 POINT (602193.76 1079205.22) 602193.760 1079205.220 \n",
|
||
"4 POINT (602459 1080946) 602459.000 1080946.000 \n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"# Tạo file CSV training data từ shapefile\n",
|
||
"import geopandas as gpd\n",
|
||
"import pandas as pd\n",
|
||
"\n",
|
||
"# Đọc shapefile training data\n",
|
||
"shapefile_path = \"/home/jovyan/remote-sensing/train/ST_training_data_updated_1130points_new.shp\"\n",
|
||
"gdf = gpd.read_file(shapefile_path)\n",
|
||
"\n",
|
||
"print(f\"✅ Đã đọc shapefile: {len(gdf)} points\")\n",
|
||
"print(f\" Columns: {list(gdf.columns)}\")\n",
|
||
"print(f\" CRS: {gdf.crs}\")\n",
|
||
"\n",
|
||
"# Extract longitude, latitude từ geometry\n",
|
||
"gdf['longitude'] = gdf.geometry.x\n",
|
||
"gdf['latitude'] = gdf.geometry.y\n",
|
||
"\n",
|
||
"# Tìm column chứa class name (có thể là 'LULC', 'class', 'label', etc.)\n",
|
||
"class_column = None\n",
|
||
"for col in gdf.columns:\n",
|
||
" if col.lower() in ['lulc', 'class', 'label', 'class_name', 'type', 'landuse']:\n",
|
||
" class_column = col\n",
|
||
" break\n",
|
||
"\n",
|
||
"if class_column is None:\n",
|
||
" print(\"⚠️ Không tìm thấy column class, hiển thị 5 dòng đầu:\")\n",
|
||
" print(gdf.head())\n",
|
||
"else:\n",
|
||
" # Tạo DataFrame với các cột cần thiết\n",
|
||
" train_df = pd.DataFrame({\n",
|
||
" 'longitude': gdf['longitude'],\n",
|
||
" 'latitude': gdf['latitude'],\n",
|
||
" 'class_name': gdf[class_column]\n",
|
||
" })\n",
|
||
" \n",
|
||
" # Export ra CSV\n",
|
||
" csv_path = \"/media/x79/2A7D-FAA0/remote-sensing/train_data.csv\"\n",
|
||
" train_df.to_csv(csv_path, index=False)\n",
|
||
" \n",
|
||
" print(f\"\\n✅ Đã tạo file CSV: {csv_path}\")\n",
|
||
" print(f\" Số lượng points: {len(train_df)}\")\n",
|
||
" print(f\" Classes: {train_df['class_name'].unique()}\")\n",
|
||
" print(f\" Class distribution:\")\n",
|
||
" print(train_df['class_name'].value_counts())\n",
|
||
" print(f\"\\n📋 Preview 5 dòng đầu:\")\n",
|
||
" print(train_df.head())"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 5,
|
||
"id": "83784d01",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"name": "stdout",
|
||
"output_type": "stream",
|
||
"text": [
|
||
" Tìm thấy 45 scenes Sentinel-2\n",
|
||
"✅ Sentinel-2 raw: FrozenMappingWarningOnValuesAccess({'y': 8874, 'x': 9902, 'time': 28})\n",
|
||
" Variables: ['red', 'green', 'blue', 'nir', 'swir16', 'swir22', 'scl']\n"
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"# Cấu hình vùng và thời gian\n",
|
||
"date_range = (\"2022-09-01\", \"2023-10-01\")\n",
|
||
"longtitude_range = (105.5, 106.4)\n",
|
||
"latitude_range = (9.2, 10.0)\n",
|
||
"\n",
|
||
"bbox = (longtitude_range[0], latitude_range[0], longtitude_range[1], latitude_range[1])\n",
|
||
"\n",
|
||
"# Tìm kiếm Sentinel-2 L2A\n",
|
||
"search = catalog.search(\n",
|
||
" collections=[\"sentinel-2-l2a\"],\n",
|
||
" bbox=bbox,\n",
|
||
" datetime=f\"{date_range[0]}/{date_range[1]}\",\n",
|
||
" query={\"eo:cloud_cover\": {\"lt\": 30}}\n",
|
||
")\n",
|
||
"\n",
|
||
"items = search.item_collection()\n",
|
||
"print(f\" Tìm thấy {len(items)} scenes Sentinel-2\")\n",
|
||
"\n",
|
||
"if len(items) == 0:\n",
|
||
" raise ValueError(\"Không tìm thấy dữ liệu Sentinel-2 cho vùng và thời gian này\")\n",
|
||
"\n",
|
||
"# Load data với odc-stac\n",
|
||
"data_sen2 = load(\n",
|
||
" items,\n",
|
||
" bands=[\"red\", \"green\", \"blue\", \"nir\", \"swir16\", \"swir22\", \"scl\"],\n",
|
||
" bbox=bbox,\n",
|
||
" resolution=10,\n",
|
||
" chunks={\"time\": 1, \"x\": 2048, \"y\": 2048},\n",
|
||
" groupby=\"solar_day\"\n",
|
||
")\n",
|
||
"\n",
|
||
"print(f\"✅ Sentinel-2 raw: {data_sen2.dims}\")\n",
|
||
"print(f\" Variables: {list(data_sen2.data_vars)}\")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": 6,
|
||
"id": "c3faed92",
|
||
"metadata": {},
|
||
"outputs": [
|
||
{
|
||
"ename": "ValueError",
|
||
"evalue": "dimension time on 0th function argument to apply_ufunc with dask='parallelized' consists of multiple chunks, but is also a core dimension. To fix, either rechunk into a single array chunk along this dimension, i.e., ``.chunk(dict(time=-1))``, or pass ``allow_rechunk=True`` in ``dask_gufunc_kwargs`` but beware that this may significantly increase memory usage.",
|
||
"output_type": "error",
|
||
"traceback": [
|
||
"\u001b[0;31m---------------------------------------------------------------------------\u001b[0m",
|
||
"\u001b[0;31mValueError\u001b[0m Traceback (most recent call last)",
|
||
"Cell \u001b[0;32mIn[6], line 33\u001b[0m\n\u001b[1;32m 31\u001b[0m data_clean \u001b[38;5;241m=\u001b[39m mask_clean(data_sen2)\n\u001b[1;32m 32\u001b[0m data_ndvi \u001b[38;5;241m=\u001b[39m calculate_indices(data_clean, index\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mNDVI\u001b[39m\u001b[38;5;124m\"\u001b[39m, satellite_mission\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124ms2\u001b[39m\u001b[38;5;124m\"\u001b[39m)\n\u001b[0;32m---> 33\u001b[0m data_fill \u001b[38;5;241m=\u001b[39m \u001b[43mfill_nan\u001b[49m\u001b[43m(\u001b[49m\u001b[43mdata_ndvi\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 34\u001b[0m data_sen2_monthly \u001b[38;5;241m=\u001b[39m data_fill\u001b[38;5;241m.\u001b[39mresample(time\u001b[38;5;241m=\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m1MS\u001b[39m\u001b[38;5;124m\"\u001b[39m)\u001b[38;5;241m.\u001b[39mmean()\u001b[38;5;241m.\u001b[39mcompute()\n\u001b[1;32m 36\u001b[0m \u001b[38;5;28mprint\u001b[39m(\u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124m✅ S2 monthly shape: \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mdata_sen2_monthly\u001b[38;5;241m.\u001b[39mdims\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m\"\u001b[39m)\n",
|
||
"Cell \u001b[0;32mIn[6], line 28\u001b[0m, in \u001b[0;36mfill_nan\u001b[0;34m(ds)\u001b[0m\n\u001b[1;32m 26\u001b[0m \u001b[38;5;28;01mdef\u001b[39;00m \u001b[38;5;21mfill_nan\u001b[39m(ds):\n\u001b[1;32m 27\u001b[0m \u001b[38;5;250m \u001b[39m\u001b[38;5;124;03m\"\"\"Fill NaN bằng interpolation theo thời gian\"\"\"\u001b[39;00m\n\u001b[0;32m---> 28\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mds\u001b[49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43minterpolate_na\u001b[49m\u001b[43m(\u001b[49m\u001b[43mdim\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mtime\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mmethod\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mlinear\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mfill_value\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mextrapolate\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m)\u001b[49m\n",
|
||
"File \u001b[0;32m/env/lib/python3.12/site-packages/xarray/core/dataset.py:6773\u001b[0m, in \u001b[0;36mDataset.interpolate_na\u001b[0;34m(self, dim, method, limit, use_coordinate, max_gap, **kwargs)\u001b[0m\n\u001b[1;32m 6655\u001b[0m \u001b[38;5;250m\u001b[39m\u001b[38;5;124;03m\"\"\"Fill in NaNs by interpolating according to different methods.\u001b[39;00m\n\u001b[1;32m 6656\u001b[0m \n\u001b[1;32m 6657\u001b[0m \u001b[38;5;124;03mParameters\u001b[39;00m\n\u001b[0;32m (...)\u001b[0m\n\u001b[1;32m 6769\u001b[0m \u001b[38;5;124;03m D (x) float64 40B 5.0 3.0 1.0 -1.0 4.0\u001b[39;00m\n\u001b[1;32m 6770\u001b[0m \u001b[38;5;124;03m\"\"\"\u001b[39;00m\n\u001b[1;32m 6771\u001b[0m \u001b[38;5;28;01mfrom\u001b[39;00m \u001b[38;5;21;01mxarray\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mcore\u001b[39;00m\u001b[38;5;21;01m.\u001b[39;00m\u001b[38;5;21;01mmissing\u001b[39;00m \u001b[38;5;28;01mimport\u001b[39;00m _apply_over_vars_with_dim, interp_na\n\u001b[0;32m-> 6773\u001b[0m new \u001b[38;5;241m=\u001b[39m \u001b[43m_apply_over_vars_with_dim\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 6774\u001b[0m \u001b[43m \u001b[49m\u001b[43minterp_na\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 6775\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 6776\u001b[0m \u001b[43m \u001b[49m\u001b[43mdim\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdim\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 6777\u001b[0m \u001b[43m \u001b[49m\u001b[43mmethod\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmethod\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 6778\u001b[0m \u001b[43m \u001b[49m\u001b[43mlimit\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mlimit\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 6779\u001b[0m \u001b[43m \u001b[49m\u001b[43muse_coordinate\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43muse_coordinate\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 6780\u001b[0m \u001b[43m \u001b[49m\u001b[43mmax_gap\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mmax_gap\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 6781\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 6782\u001b[0m \u001b[43m\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 6783\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m new\n",
|
||
"File \u001b[0;32m/env/lib/python3.12/site-packages/xarray/core/missing.py:222\u001b[0m, in \u001b[0;36m_apply_over_vars_with_dim\u001b[0;34m(func, self, dim, **kwargs)\u001b[0m\n\u001b[1;32m 220\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m name, var \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdata_vars\u001b[38;5;241m.\u001b[39mitems():\n\u001b[1;32m 221\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m dim \u001b[38;5;129;01min\u001b[39;00m var\u001b[38;5;241m.\u001b[39mdims:\n\u001b[0;32m--> 222\u001b[0m ds[name] \u001b[38;5;241m=\u001b[39m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[43mvar\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43mdim\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mdim\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mkwargs\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 223\u001b[0m \u001b[38;5;28;01melse\u001b[39;00m:\n\u001b[1;32m 224\u001b[0m ds[name] \u001b[38;5;241m=\u001b[39m var\n",
|
||
"File \u001b[0;32m/env/lib/python3.12/site-packages/xarray/core/missing.py:367\u001b[0m, in \u001b[0;36minterp_na\u001b[0;34m(self, dim, use_coordinate, method, limit, max_gap, keep_attrs, **kwargs)\u001b[0m\n\u001b[1;32m 365\u001b[0m warnings\u001b[38;5;241m.\u001b[39mfilterwarnings(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mignore\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124moverflow\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;167;01mRuntimeWarning\u001b[39;00m)\n\u001b[1;32m 366\u001b[0m warnings\u001b[38;5;241m.\u001b[39mfilterwarnings(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mignore\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124minvalid value\u001b[39m\u001b[38;5;124m\"\u001b[39m, \u001b[38;5;167;01mRuntimeWarning\u001b[39;00m)\n\u001b[0;32m--> 367\u001b[0m arr \u001b[38;5;241m=\u001b[39m \u001b[43mapply_ufunc\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 368\u001b[0m \u001b[43m \u001b[49m\u001b[43minterpolator\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 369\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 370\u001b[0m \u001b[43m \u001b[49m\u001b[43mindex\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 371\u001b[0m \u001b[43m \u001b[49m\u001b[43minput_core_dims\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m[\u001b[49m\u001b[43m[\u001b[49m\u001b[43mdim\u001b[49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\u001b[43m \u001b[49m\u001b[43m[\u001b[49m\u001b[43mdim\u001b[49m\u001b[43m]\u001b[49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 372\u001b[0m \u001b[43m \u001b[49m\u001b[43moutput_core_dims\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m[\u001b[49m\u001b[43m[\u001b[49m\u001b[43mdim\u001b[49m\u001b[43m]\u001b[49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 373\u001b[0m \u001b[43m \u001b[49m\u001b[43moutput_dtypes\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43m[\u001b[49m\u001b[38;5;28;43mself\u001b[39;49m\u001b[38;5;241;43m.\u001b[39;49m\u001b[43mdtype\u001b[49m\u001b[43m]\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 374\u001b[0m \u001b[43m \u001b[49m\u001b[43mdask\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[38;5;124;43mparallelized\u001b[39;49m\u001b[38;5;124;43m\"\u001b[39;49m\u001b[43m,\u001b[49m\n\u001b[1;32m 375\u001b[0m \u001b[43m \u001b[49m\u001b[43mvectorize\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[38;5;28;43;01mTrue\u001b[39;49;00m\u001b[43m,\u001b[49m\n\u001b[1;32m 376\u001b[0m \u001b[43m \u001b[49m\u001b[43mkeep_attrs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mkeep_attrs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 377\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\u001b[38;5;241m.\u001b[39mtranspose(\u001b[38;5;241m*\u001b[39m\u001b[38;5;28mself\u001b[39m\u001b[38;5;241m.\u001b[39mdims)\n\u001b[1;32m 379\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m limit \u001b[38;5;129;01mis\u001b[39;00m \u001b[38;5;129;01mnot\u001b[39;00m \u001b[38;5;28;01mNone\u001b[39;00m:\n\u001b[1;32m 380\u001b[0m arr \u001b[38;5;241m=\u001b[39m arr\u001b[38;5;241m.\u001b[39mwhere(valids)\n",
|
||
"File \u001b[0;32m/env/lib/python3.12/site-packages/xarray/core/computation.py:1265\u001b[0m, in \u001b[0;36mapply_ufunc\u001b[0;34m(func, input_core_dims, output_core_dims, exclude_dims, vectorize, join, dataset_join, dataset_fill_value, keep_attrs, kwargs, dask, output_dtypes, output_sizes, meta, dask_gufunc_kwargs, on_missing_core_dim, *args)\u001b[0m\n\u001b[1;32m 1263\u001b[0m \u001b[38;5;66;03m# feed DataArray apply_variable_ufunc through apply_dataarray_vfunc\u001b[39;00m\n\u001b[1;32m 1264\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28many\u001b[39m(\u001b[38;5;28misinstance\u001b[39m(a, DataArray) \u001b[38;5;28;01mfor\u001b[39;00m a \u001b[38;5;129;01min\u001b[39;00m args):\n\u001b[0;32m-> 1265\u001b[0m \u001b[38;5;28;01mreturn\u001b[39;00m \u001b[43mapply_dataarray_vfunc\u001b[49m\u001b[43m(\u001b[49m\n\u001b[1;32m 1266\u001b[0m \u001b[43m \u001b[49m\u001b[43mvariables_vfunc\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1267\u001b[0m \u001b[43m \u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43margs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1268\u001b[0m \u001b[43m \u001b[49m\u001b[43msignature\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43msignature\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1269\u001b[0m \u001b[43m \u001b[49m\u001b[43mjoin\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mjoin\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1270\u001b[0m \u001b[43m \u001b[49m\u001b[43mexclude_dims\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mexclude_dims\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1271\u001b[0m \u001b[43m \u001b[49m\u001b[43mkeep_attrs\u001b[49m\u001b[38;5;241;43m=\u001b[39;49m\u001b[43mkeep_attrs\u001b[49m\u001b[43m,\u001b[49m\n\u001b[1;32m 1272\u001b[0m \u001b[43m \u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 1273\u001b[0m \u001b[38;5;66;03m# feed Variables directly through apply_variable_ufunc\u001b[39;00m\n\u001b[1;32m 1274\u001b[0m \u001b[38;5;28;01melif\u001b[39;00m \u001b[38;5;28many\u001b[39m(\u001b[38;5;28misinstance\u001b[39m(a, Variable) \u001b[38;5;28;01mfor\u001b[39;00m a \u001b[38;5;129;01min\u001b[39;00m args):\n",
|
||
"File \u001b[0;32m/env/lib/python3.12/site-packages/xarray/core/computation.py:307\u001b[0m, in \u001b[0;36mapply_dataarray_vfunc\u001b[0;34m(func, signature, join, exclude_dims, keep_attrs, *args)\u001b[0m\n\u001b[1;32m 302\u001b[0m result_coords, result_indexes \u001b[38;5;241m=\u001b[39m build_output_coords_and_indexes(\n\u001b[1;32m 303\u001b[0m args, signature, exclude_dims, combine_attrs\u001b[38;5;241m=\u001b[39mkeep_attrs\n\u001b[1;32m 304\u001b[0m )\n\u001b[1;32m 306\u001b[0m data_vars \u001b[38;5;241m=\u001b[39m [\u001b[38;5;28mgetattr\u001b[39m(a, \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mvariable\u001b[39m\u001b[38;5;124m\"\u001b[39m, a) \u001b[38;5;28;01mfor\u001b[39;00m a \u001b[38;5;129;01min\u001b[39;00m args]\n\u001b[0;32m--> 307\u001b[0m result_var \u001b[38;5;241m=\u001b[39m \u001b[43mfunc\u001b[49m\u001b[43m(\u001b[49m\u001b[38;5;241;43m*\u001b[39;49m\u001b[43mdata_vars\u001b[49m\u001b[43m)\u001b[49m\n\u001b[1;32m 309\u001b[0m out: \u001b[38;5;28mtuple\u001b[39m[DataArray, \u001b[38;5;241m.\u001b[39m\u001b[38;5;241m.\u001b[39m\u001b[38;5;241m.\u001b[39m] \u001b[38;5;241m|\u001b[39m DataArray\n\u001b[1;32m 310\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m signature\u001b[38;5;241m.\u001b[39mnum_outputs \u001b[38;5;241m>\u001b[39m \u001b[38;5;241m1\u001b[39m:\n",
|
||
"File \u001b[0;32m/env/lib/python3.12/site-packages/xarray/core/computation.py:764\u001b[0m, in \u001b[0;36mapply_variable_ufunc\u001b[0;34m(func, signature, exclude_dims, dask, output_dtypes, vectorize, keep_attrs, dask_gufunc_kwargs, *args)\u001b[0m\n\u001b[1;32m 762\u001b[0m \u001b[38;5;28;01mfor\u001b[39;00m axis, dim \u001b[38;5;129;01min\u001b[39;00m \u001b[38;5;28menumerate\u001b[39m(core_dims, start\u001b[38;5;241m=\u001b[39m\u001b[38;5;241m-\u001b[39m\u001b[38;5;28mlen\u001b[39m(core_dims)):\n\u001b[1;32m 763\u001b[0m \u001b[38;5;28;01mif\u001b[39;00m \u001b[38;5;28mlen\u001b[39m(data\u001b[38;5;241m.\u001b[39mchunks[axis]) \u001b[38;5;241m!=\u001b[39m \u001b[38;5;241m1\u001b[39m:\n\u001b[0;32m--> 764\u001b[0m \u001b[38;5;28;01mraise\u001b[39;00m \u001b[38;5;167;01mValueError\u001b[39;00m(\n\u001b[1;32m 765\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mdimension \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mdim\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m on \u001b[39m\u001b[38;5;132;01m{\u001b[39;00mn\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124mth function argument to \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 766\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mapply_ufunc with dask=\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124mparallelized\u001b[39m\u001b[38;5;124m'\u001b[39m\u001b[38;5;124m consists of \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 767\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mmultiple chunks, but is also a core dimension. To \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 768\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mfix, either rechunk into a single array chunk along \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 769\u001b[0m \u001b[38;5;124mf\u001b[39m\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mthis dimension, i.e., ``.chunk(dict(\u001b[39m\u001b[38;5;132;01m{\u001b[39;00mdim\u001b[38;5;132;01m}\u001b[39;00m\u001b[38;5;124m=-1))``, or \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 770\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mpass ``allow_rechunk=True`` in ``dask_gufunc_kwargs`` \u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 771\u001b[0m \u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mbut beware that this may significantly increase memory usage.\u001b[39m\u001b[38;5;124m\"\u001b[39m\n\u001b[1;32m 772\u001b[0m )\n\u001b[1;32m 773\u001b[0m dask_gufunc_kwargs[\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124mallow_rechunk\u001b[39m\u001b[38;5;124m\"\u001b[39m] \u001b[38;5;241m=\u001b[39m \u001b[38;5;28;01mTrue\u001b[39;00m\n\u001b[1;32m 775\u001b[0m output_sizes \u001b[38;5;241m=\u001b[39m dask_gufunc_kwargs\u001b[38;5;241m.\u001b[39mpop(\u001b[38;5;124m\"\u001b[39m\u001b[38;5;124moutput_sizes\u001b[39m\u001b[38;5;124m\"\u001b[39m, {})\n",
|
||
"\u001b[0;31mValueError\u001b[0m: dimension time on 0th function argument to apply_ufunc with dask='parallelized' consists of multiple chunks, but is also a core dimension. To fix, either rechunk into a single array chunk along this dimension, i.e., ``.chunk(dict(time=-1))``, or pass ``allow_rechunk=True`` in ``dask_gufunc_kwargs`` but beware that this may significantly increase memory usage."
|
||
]
|
||
}
|
||
],
|
||
"source": [
|
||
"# Tiền xử lý Sentinel-2: cloud mask + NDVI + resampling\n",
|
||
"\n",
|
||
"def mask_clean(ds):\n",
|
||
" \"\"\"Cloud masking sử dụng SCL band (Scene Classification Layer)\"\"\"\n",
|
||
" if \"scl\" not in ds:\n",
|
||
" print(\"⚠️ Không có SCL band, bỏ qua cloud masking\")\n",
|
||
" return ds\n",
|
||
" \n",
|
||
" cloud_mask = (\n",
|
||
" (ds[\"scl\"] == 3) | # cloud shadow\n",
|
||
" (ds[\"scl\"] == 8) | # cloud medium probability\n",
|
||
" (ds[\"scl\"] == 9) | # cloud high probability\n",
|
||
" (ds[\"scl\"] == 10) # thin cirrus\n",
|
||
" )\n",
|
||
" \n",
|
||
" ds_masked = ds.where(~cloud_mask)\n",
|
||
" return ds_masked.drop_vars(\"scl\", errors=\"ignore\")\n",
|
||
"\n",
|
||
"def calculate_indices(ds, index=\"NDVI\", satellite_mission=\"s2\"):\n",
|
||
" \"\"\"Tính chỉ số NDVI\"\"\"\n",
|
||
" if index == \"NDVI\":\n",
|
||
" ndvi = (ds[\"nir\"] - ds[\"red\"]) / (ds[\"nir\"] + ds[\"red\"] + 1e-8)\n",
|
||
" ds[\"NDVI\"] = ndvi\n",
|
||
" return ds\n",
|
||
"\n",
|
||
"def fill_nan(ds):\n",
|
||
" \"\"\"Fill NaN bằng interpolation theo thời gian\"\"\"\n",
|
||
" return ds.interpolate_na(dim=\"time\", method=\"linear\", fill_value=\"extrapolate\")\n",
|
||
"\n",
|
||
"# Áp dụng tiền xử lý\n",
|
||
"data_clean = mask_clean(data_sen2)\n",
|
||
"data_ndvi = calculate_indices(data_clean, index=\"NDVI\", satellite_mission=\"s2\")\n",
|
||
"data_fill = fill_nan(data_ndvi)\n",
|
||
"data_sen2_monthly = data_fill.resample(time=\"1MS\").mean().compute()\n",
|
||
"\n",
|
||
"print(f\"✅ S2 monthly shape: {data_sen2_monthly.dims}\")\n",
|
||
"print(f\" Variables: {list(data_sen2_monthly.data_vars)}\")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "569bfebb",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"# Tải Sentinel-1 (SAR VV/VH) từ Element84\n",
|
||
"\n",
|
||
"search_s1 = catalog.search(\n",
|
||
" collections=[\"sentinel-1-grd\"],\n",
|
||
" bbox=bbox,\n",
|
||
" datetime=f\"{date_range[0]}/{date_range[1]}\",\n",
|
||
" query={\n",
|
||
" \"sat:orbit_state\": {\"eq\": \"descending\"},\n",
|
||
" \"sar:product_type\": {\"eq\": \"GRD\"}\n",
|
||
" }\n",
|
||
")\n",
|
||
"\n",
|
||
"items_s1 = search_s1.item_collection()\n",
|
||
"print(f\" Tìm thấy {len(items_s1)} scenes Sentinel-1\")\n",
|
||
"\n",
|
||
"if len(items_s1) == 0:\n",
|
||
" print(\"⚠️ Không tìm thấy Sentinel-1, tạo dummy data\")\n",
|
||
" # Tạo dummy data với cùng kích thước như S2\n",
|
||
" data_sen1_monthly = xr.Dataset({\n",
|
||
" \"VV\": xr.DataArray(\n",
|
||
" np.zeros_like(data_sen2_monthly[\"red\"].values),\n",
|
||
" coords=data_sen2_monthly[\"red\"].coords,\n",
|
||
" dims=data_sen2_monthly[\"red\"].dims\n",
|
||
" ),\n",
|
||
" \"VH\": xr.DataArray(\n",
|
||
" np.zeros_like(data_sen2_monthly[\"red\"].values),\n",
|
||
" coords=data_sen2_monthly[\"red\"].coords,\n",
|
||
" dims=data_sen2_monthly[\"red\"].dims\n",
|
||
" )\n",
|
||
" })\n",
|
||
"else:\n",
|
||
" # Load Sentinel-1 data\n",
|
||
" data_sen1 = load(\n",
|
||
" items_s1,\n",
|
||
" bands=[\"vv\", \"vh\"],\n",
|
||
" bbox=bbox,\n",
|
||
" resolution=10,\n",
|
||
" chunks={\"time\": 1, \"x\": 2048, \"y\": 2048},\n",
|
||
" groupby=\"solar_day\"\n",
|
||
" )\n",
|
||
" \n",
|
||
" # Rename bands to uppercase (VV, VH)\n",
|
||
" data_sen1 = data_sen1.rename({\"vv\": \"VV\", \"vh\": \"VH\"})\n",
|
||
" data_sen1_monthly = data_sen1.resample(time=\"1MS\").mean().compute()\n",
|
||
"\n",
|
||
"print(f\"✅ S1 monthly shape: {data_sen1_monthly.dims}\")\n",
|
||
"print(f\" Variables: {list(data_sen1_monthly.data_vars)}\")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "ecc56c2f",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"import numpy as np\n",
|
||
"\n",
|
||
"# Ánh xạ nhãn lớp đất\n",
|
||
"label_mapping = {\n",
|
||
" \"Lua tom\": \"0\", \"Lua\": \"1\", \"CHN\": \"2\", \"CLN\": \"3\",\n",
|
||
" \"TS\": \"4\", \"Song\": \"5\", \"Dat xay dung\": \"6\", \"Rung\": \"7\",\n",
|
||
"}\n",
|
||
"\n",
|
||
"def load_train_data(csv_path=\"/media/x79/2A7D-FAA0/remote-sensing/train_data.csv\", label_mapping=None):\n",
|
||
" \"\"\"Load training points từ CSV\"\"\"\n",
|
||
" df = pd.read_csv(csv_path)\n",
|
||
" if label_mapping:\n",
|
||
" df[\"label\"] = df[\"class_name\"].map(label_mapping).astype(str)\n",
|
||
" return df\n",
|
||
"\n",
|
||
"def get_data_sen1_and_sen2(train_df, sen2_data, sen1_data):\n",
|
||
" \"\"\"Extract features từ S2 và S1 tại các điểm training\"\"\"\n",
|
||
" X_list = []\n",
|
||
" y_list = []\n",
|
||
" \n",
|
||
" for idx, row in train_df.iterrows():\n",
|
||
" try:\n",
|
||
" lon, lat = float(row[\"longitude\"]), float(row[\"latitude\"])\n",
|
||
" label = int(row[\"label\"])\n",
|
||
" \n",
|
||
" # Extract S2 features (mean, std, min, max theo time)\n",
|
||
" s2_point = sen2_data.sel(x=lon, y=lat, method=\"nearest\")\n",
|
||
" s2_features = []\n",
|
||
" \n",
|
||
" for var in [\"red\", \"green\", \"blue\", \"nir\", \"swir16\", \"swir22\", \"NDVI\"]:\n",
|
||
" if var in s2_point:\n",
|
||
" vals = s2_point[var].values\n",
|
||
" if vals.size > 0:\n",
|
||
" s2_features.extend([\n",
|
||
" np.nanmean(vals), np.nanstd(vals),\n",
|
||
" np.nanmin(vals), np.nanmax(vals)\n",
|
||
" ])\n",
|
||
" else:\n",
|
||
" s2_features.extend([0, 0, 0, 0])\n",
|
||
" \n",
|
||
" # Extract S1 features\n",
|
||
" s1_point = sen1_data.sel(x=lon, y=lat, method=\"nearest\")\n",
|
||
" s1_features = []\n",
|
||
" \n",
|
||
" for var in [\"VV\", \"VH\"]:\n",
|
||
" if var in s1_point:\n",
|
||
" vals = s1_point[var].values\n",
|
||
" if vals.size > 0:\n",
|
||
" s1_features.extend([np.nanmean(vals), np.nanstd(vals)])\n",
|
||
" else:\n",
|
||
" s1_features.extend([0, 0])\n",
|
||
" \n",
|
||
" features = s2_features + s1_features\n",
|
||
" \n",
|
||
" # Bỏ qua nếu có NaN\n",
|
||
" if not np.isnan(features).any() and not np.isinf(features).any():\n",
|
||
" X_list.append(features)\n",
|
||
" y_list.append(label)\n",
|
||
" except Exception as e:\n",
|
||
" print(f\"⚠️ Lỗi tại row {idx}: {e}\")\n",
|
||
" continue\n",
|
||
" \n",
|
||
" return X_list, y_list\n",
|
||
"\n",
|
||
"def split_train_data(X, y, test_size=0.2, val_size=0.1, random_state=42):\n",
|
||
" \"\"\"Split data thành train/val/test\"\"\"\n",
|
||
" X = np.array(X, dtype=np.float32)\n",
|
||
" y = np.array(y, dtype=np.int64)\n",
|
||
" \n",
|
||
" # Train + temp\n",
|
||
" X_train, X_temp, y_train, y_temp = train_test_split(\n",
|
||
" X, y, test_size=test_size + val_size, random_state=random_state, stratify=y\n",
|
||
" )\n",
|
||
" \n",
|
||
" # Val + test\n",
|
||
" val_ratio = val_size / (test_size + val_size)\n",
|
||
" X_val, X_test, y_val, y_test = train_test_split(\n",
|
||
" X_temp, y_temp, test_size=(1 - val_ratio), random_state=random_state, stratify=y_temp\n",
|
||
" )\n",
|
||
" \n",
|
||
" return X_train, X_val, X_test, y_train, y_val, y_test\n",
|
||
"\n",
|
||
"# Load và extract features\n",
|
||
"train_data = load_train_data(label_mapping=label_mapping)\n",
|
||
"X, y = get_data_sen1_and_sen2(train_data, data_sen2_monthly, data_sen1_monthly)\n",
|
||
"X_train, X_val, X_test, y_train, y_val, y_test = split_train_data(X, y, test_size=0.2, val_size=0.1)\n",
|
||
"\n",
|
||
"X_train_np = np.array(X_train, dtype=np.float32)\n",
|
||
"X_val_np = np.array(X_val, dtype=np.float32)\n",
|
||
"X_test_np = np.array(X_test, dtype=np.float32)\n",
|
||
"y_train_np = np.array(y_train, dtype=np.int64)\n",
|
||
"y_val_np = np.array(y_val, dtype=np.int64)\n",
|
||
"y_test_np = np.array(y_test, dtype=np.int64)\n",
|
||
"\n",
|
||
"n_features = X_train_np.shape[1]\n",
|
||
"n_classes = len(np.unique(y_train_np))\n",
|
||
"\n",
|
||
"print(f\"✅ Train: {X_train_np.shape} Val: {X_val_np.shape} Test: {X_test_np.shape}\")\n",
|
||
"print(f\" n_features={n_features} n_classes={n_classes}\")"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "5492528b",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"import torch\n",
|
||
"import torch.nn as nn\n",
|
||
"import torch.optim as optim\n",
|
||
"from torch.utils.data import TensorDataset, DataLoader\n",
|
||
"\n",
|
||
"# ── MobileNetV3 + LR-ASPP classifier ──────────────────────────────────────────\n",
|
||
"class MobileNetLRASPPClassifier(nn.Module):\n",
|
||
" \"\"\"\n",
|
||
" MobileNetV3-inspired backbone with LR-ASPP (Lite Reduced ASPP) head\n",
|
||
" for land-use classification on flat feature vectors.\n",
|
||
" \"\"\"\n",
|
||
" def __init__(self, n_features, n_classes):\n",
|
||
" super().__init__()\n",
|
||
" # Feature extraction backbone\n",
|
||
" self.feature_extractor = nn.Sequential(\n",
|
||
" nn.Linear(n_features, 128), nn.BatchNorm1d(128), nn.ReLU(inplace=True), nn.Dropout(0.2),\n",
|
||
" nn.Linear(128, 256), nn.BatchNorm1d(256), nn.ReLU(inplace=True), nn.Dropout(0.3),\n",
|
||
" nn.Linear(256, 512), nn.BatchNorm1d(512), nn.ReLU(inplace=True), nn.Dropout(0.3),\n",
|
||
" )\n",
|
||
" # LR-ASPP Branch 1: global pooling → 128\n",
|
||
" self.global_pool = nn.AdaptiveAvgPool1d(1)\n",
|
||
" self.global_conv = nn.Sequential(nn.Linear(512, 128), nn.ReLU(inplace=True))\n",
|
||
" # LR-ASPP Branch 2: direct 1×1 → 128\n",
|
||
" self.branch_conv = nn.Sequential(nn.Linear(512, 128), nn.BatchNorm1d(128), nn.ReLU(inplace=True))\n",
|
||
" # Fusion → n_classes\n",
|
||
" self.classifier = nn.Sequential(\n",
|
||
" nn.Linear(256, 128), nn.BatchNorm1d(128), nn.ReLU(inplace=True), nn.Dropout(0.4),\n",
|
||
" nn.Linear(128, n_classes),\n",
|
||
" )\n",
|
||
"\n",
|
||
" def forward(self, x):\n",
|
||
" feat = self.feature_extractor(x)\n",
|
||
" global_feat = self.global_pool(feat.unsqueeze(-1)).squeeze(-1)\n",
|
||
" global_feat = self.global_conv(global_feat)\n",
|
||
" branch_feat = self.branch_conv(feat)\n",
|
||
" fused = torch.cat([global_feat, branch_feat], dim=1)\n",
|
||
" return self.classifier(fused)\n",
|
||
"\n",
|
||
"device = torch.device(\"cuda\" if torch.cuda.is_available() else \"cpu\")\n",
|
||
"print(f\"✅ Device: {device}\")\n",
|
||
"model = MobileNetLRASPPClassifier(n_features, n_classes).to(device)\n",
|
||
"print(model)\n",
|
||
"total_params = sum(p.numel() for p in model.parameters() if p.requires_grad)\n",
|
||
"print(f\" Trainable params: {total_params:,}\")\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "9da40f5a",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"%%time\n",
|
||
"import matplotlib.pyplot as plt\n",
|
||
"\n",
|
||
"# ── Hyper-parameters ───────────────────────────────────────────────────────────\n",
|
||
"LEARNING_RATE = 1e-3\n",
|
||
"BATCH_SIZE = 64\n",
|
||
"N_EPOCHS = 60\n",
|
||
"PATIENCE = 10\n",
|
||
"CONV_THRESHOLD = 1e-4 # cải thiện val_loss < THRESHOLD → đánh dấu hội tụ\n",
|
||
"CONV_WINDOW = 3 # cần CONV_WINDOW bước liên tiếp thỏa mãn\n",
|
||
"\n",
|
||
"# ── Tensors & DataLoaders ──────────────────────────────────────────────────────\n",
|
||
"X_tr_t = torch.FloatTensor(X_train_np)\n",
|
||
"y_tr_t = torch.LongTensor(y_train_np)\n",
|
||
"X_va_t = torch.FloatTensor(X_val_np)\n",
|
||
"y_va_t = torch.LongTensor(y_val_np)\n",
|
||
"\n",
|
||
"train_loader = DataLoader(TensorDataset(X_tr_t, y_tr_t), batch_size=BATCH_SIZE, shuffle=True)\n",
|
||
"val_loader = DataLoader(TensorDataset(X_va_t, y_va_t), batch_size=BATCH_SIZE, shuffle=False)\n",
|
||
"\n",
|
||
"# ── Class-weighted loss ────────────────────────────────────────────────────────\n",
|
||
"class_counts = np.bincount(y_train_np)\n",
|
||
"class_weights = 1.0 / (class_counts + 1e-6)\n",
|
||
"class_weights = class_weights / class_weights.sum() * n_classes\n",
|
||
"criterion = nn.CrossEntropyLoss(weight=torch.FloatTensor(class_weights).to(device))\n",
|
||
"\n",
|
||
"optimizer = optim.Adam(model.parameters(), lr=LEARNING_RATE, weight_decay=1e-4)\n",
|
||
"scheduler = optim.lr_scheduler.ReduceLROnPlateau(optimizer, mode=\"min\", factor=0.5, patience=5)\n",
|
||
"\n",
|
||
"# ── Training loop ──────────────────────────────────────────────────────────────\n",
|
||
"train_losses, val_losses, val_accs, lr_history = [], [], [], []\n",
|
||
"best_val_loss = float(\"inf\")\n",
|
||
"best_epoch = 1\n",
|
||
"best_state_dict = None\n",
|
||
"patience_counter = 0\n",
|
||
"convergence_epoch = None # ← điểm hội tụ sẽ được ghi lại ở đây\n",
|
||
"early_stop_epoch = None\n",
|
||
"\n",
|
||
"print(\"🚀 Training MobileNetV3 + LR-ASPP...\")\n",
|
||
"print(f\" conv_threshold={CONV_THRESHOLD} conv_window={CONV_WINDOW} patience={PATIENCE}\")\n",
|
||
"for epoch in range(1, N_EPOCHS + 1):\n",
|
||
" # --- Train ---\n",
|
||
" model.train()\n",
|
||
" epoch_loss = 0.0\n",
|
||
" for bx, by in train_loader:\n",
|
||
" bx, by = bx.to(device), by.to(device)\n",
|
||
" optimizer.zero_grad()\n",
|
||
" loss = criterion(model(bx), by)\n",
|
||
" loss.backward()\n",
|
||
" torch.nn.utils.clip_grad_norm_(model.parameters(), max_norm=1.0)\n",
|
||
" optimizer.step()\n",
|
||
" epoch_loss += loss.item()\n",
|
||
" avg_train_loss = epoch_loss / len(train_loader)\n",
|
||
"\n",
|
||
" # --- Validate ---\n",
|
||
" model.eval()\n",
|
||
" val_loss = 0.0; correct = 0; total = 0\n",
|
||
" with torch.no_grad():\n",
|
||
" for bx, by in val_loader:\n",
|
||
" bx, by = bx.to(device), by.to(device)\n",
|
||
" out = model(bx)\n",
|
||
" val_loss += criterion(out, by).item()\n",
|
||
" pred = out.argmax(1)\n",
|
||
" correct += (pred == by).sum().item()\n",
|
||
" total += by.size(0)\n",
|
||
" avg_val_loss = val_loss / len(val_loader)\n",
|
||
" val_acc = correct / total\n",
|
||
"\n",
|
||
" scheduler.step(avg_val_loss)\n",
|
||
" lr = optimizer.param_groups[0][\"lr\"]\n",
|
||
" lr_history.append(lr)\n",
|
||
"\n",
|
||
" train_losses.append(avg_train_loss)\n",
|
||
" val_losses.append(avg_val_loss)\n",
|
||
" val_accs.append(val_acc)\n",
|
||
"\n",
|
||
" # ── Phát hiện điểm hội tụ (sliding window trên val_loss) ──────────────\n",
|
||
" if convergence_epoch is None and epoch >= CONV_WINDOW + 1:\n",
|
||
" window = val_losses[-(CONV_WINDOW + 1):]\n",
|
||
" improvements = [abs(window[i] - window[i - 1]) for i in range(1, len(window))]\n",
|
||
" if all(imp < CONV_THRESHOLD for imp in improvements):\n",
|
||
" convergence_epoch = epoch - CONV_WINDOW + 1\n",
|
||
" print(f\" 📍 Hội tụ phát hiện tại epoch {convergence_epoch} \"\n",
|
||
" f\"(val_loss={val_losses[convergence_epoch-1]:.4f})\")\n",
|
||
"\n",
|
||
" if epoch % 5 == 0 or epoch == 1:\n",
|
||
" print(f\" Epoch {epoch:3d}/{N_EPOCHS} train={avg_train_loss:.4f} \"\n",
|
||
" f\"val={avg_val_loss:.4f} acc={val_acc:.4f} lr={lr:.2e}\")\n",
|
||
"\n",
|
||
" # ── Early stopping ─────────────────────────────────────────────────────\n",
|
||
" if avg_val_loss < best_val_loss:\n",
|
||
" best_val_loss = avg_val_loss\n",
|
||
" best_epoch = epoch\n",
|
||
" best_state_dict = {k: v.clone() for k, v in model.state_dict().items()}\n",
|
||
" patience_counter = 0\n",
|
||
" else:\n",
|
||
" patience_counter += 1\n",
|
||
" if patience_counter >= PATIENCE:\n",
|
||
" early_stop_epoch = epoch\n",
|
||
" print(f\"⏹ Early stopping tại epoch {epoch} (patience={PATIENCE})\")\n",
|
||
" break\n",
|
||
"\n",
|
||
"# Restore best weights\n",
|
||
"model.load_state_dict(best_state_dict)\n",
|
||
"total_epochs = len(train_losses)\n",
|
||
"print(f\"\\n✅ Training hoàn tất! Best epoch={best_epoch} Best val_loss={best_val_loss:.4f}\")\n",
|
||
"if convergence_epoch:\n",
|
||
" print(f\" Điểm hội tụ : epoch {convergence_epoch}\")\n",
|
||
"\n",
|
||
"# ═══════════════════════════════════════════════════════════════════════════════\n",
|
||
"# PHÂN TÍCH ĐIỂM HỘI TỤ — MobileNetV3 + LR-ASPP\n",
|
||
"# EMA-smoothed curves + annotated convergence / best / early-stop markers\n",
|
||
"# ═══════════════════════════════════════════════════════════════════════════════\n",
|
||
"epochs_axis = list(range(1, total_epochs + 1))\n",
|
||
"\n",
|
||
"# Exponential Moving Average smoothing\n",
|
||
"def ema(values, alpha=0.2):\n",
|
||
" s = [values[0]]\n",
|
||
" for v in values[1:]:\n",
|
||
" s.append(alpha * v + (1 - alpha) * s[-1])\n",
|
||
" return s\n",
|
||
"\n",
|
||
"val_losses_ema = ema(val_losses, alpha=0.3)\n",
|
||
"train_losses_ema = ema(train_losses, alpha=0.3)\n",
|
||
"val_accs_ema = ema(val_accs, alpha=0.3)\n",
|
||
"\n",
|
||
"# ── Tính ΔVal-loss per epoch ──────────────────────────────────────────────────\n",
|
||
"delta_val = [abs(val_losses_ema[i] - val_losses_ema[i-1])\n",
|
||
" for i in range(1, len(val_losses_ema))]\n",
|
||
"\n",
|
||
"fig, axes = plt.subplots(2, 2, figsize=(16, 10))\n",
|
||
"\n",
|
||
"# --- Top-left: Loss curves ---\n",
|
||
"ax = axes[0, 0]\n",
|
||
"ax.plot(epochs_axis, train_losses, \"b-\", alpha=0.25, linewidth=0.8)\n",
|
||
"ax.plot(epochs_axis, train_losses_ema, \"b-\", linewidth=2, label=\"Train loss (EMA)\")\n",
|
||
"ax.plot(epochs_axis, val_losses, \"g-\", alpha=0.25, linewidth=0.8)\n",
|
||
"ax.plot(epochs_axis, val_losses_ema, \"g-\", linewidth=2, label=\"Val loss (EMA)\")\n",
|
||
"ax.axvline(x=best_epoch, color=\"red\", linestyle=\"--\", linewidth=1.5,\n",
|
||
" label=f\"Best epoch={best_epoch}\")\n",
|
||
"if convergence_epoch:\n",
|
||
" ax.axvline(x=convergence_epoch, color=\"orange\", linestyle=\":\", linewidth=1.5,\n",
|
||
" label=f\"HỘI TỤ epoch={convergence_epoch}\")\n",
|
||
"if early_stop_epoch:\n",
|
||
" ax.axvline(x=early_stop_epoch, color=\"gray\", linestyle=\"-.\", linewidth=1.5,\n",
|
||
" label=f\"Early stop epoch={early_stop_epoch}\")\n",
|
||
"ax.set_xlabel(\"Epoch\")\n",
|
||
"ax.set_ylabel(\"Loss\")\n",
|
||
"ax.set_title(\"Loss Curves (raw + EMA)\")\n",
|
||
"ax.legend(fontsize=8)\n",
|
||
"ax.grid(True, alpha=0.3)\n",
|
||
"\n",
|
||
"# --- Top-right: Val accuracy ---\n",
|
||
"ax = axes[0, 1]\n",
|
||
"ax.plot(epochs_axis, val_accs, \"g-\", alpha=0.3, linewidth=0.8)\n",
|
||
"ax.plot(epochs_axis, val_accs_ema, \"g-\", linewidth=2, label=\"Val acc (EMA)\")\n",
|
||
"ax.axvline(x=best_epoch, color=\"red\", linestyle=\"--\", linewidth=1.5,\n",
|
||
" label=f\"Best epoch={best_epoch} ({val_accs[best_epoch-1]*100:.2f}%)\")\n",
|
||
"if convergence_epoch:\n",
|
||
" ax.axvline(x=convergence_epoch, color=\"orange\", linestyle=\":\", linewidth=1.5,\n",
|
||
" label=f\"HỘI TỤ epoch={convergence_epoch} ({val_accs[convergence_epoch-1]*100:.2f}%)\")\n",
|
||
"if early_stop_epoch:\n",
|
||
" ax.axvline(x=early_stop_epoch, color=\"gray\", linestyle=\"-.\", linewidth=1.5,\n",
|
||
" label=f\"Early stop\")\n",
|
||
"ax.set_xlabel(\"Epoch\")\n",
|
||
"ax.set_ylabel(\"Accuracy\")\n",
|
||
"ax.set_title(\"Val Accuracy Curve\")\n",
|
||
"ax.legend(fontsize=8)\n",
|
||
"ax.grid(True, alpha=0.3)\n",
|
||
"\n",
|
||
"# --- Bottom-left: ΔVal-loss (marginal improvement) ---\n",
|
||
"ax = axes[1, 0]\n",
|
||
"ax.bar(epochs_axis[1:], delta_val,\n",
|
||
" color=[\"green\" if d > CONV_THRESHOLD else \"salmon\" for d in delta_val],\n",
|
||
" alpha=0.75)\n",
|
||
"ax.axhline(y=CONV_THRESHOLD, color=\"red\", linestyle=\"--\",\n",
|
||
" label=f\"Threshold = {CONV_THRESHOLD:.0e}\")\n",
|
||
"if convergence_epoch:\n",
|
||
" ax.axvline(x=convergence_epoch, color=\"orange\", linestyle=\":\", linewidth=1.5,\n",
|
||
" label=f\"HỘI TỤ epoch={convergence_epoch}\")\n",
|
||
"ax.set_xlabel(\"Epoch\")\n",
|
||
"ax.set_ylabel(\"|ΔVal Loss|\")\n",
|
||
"ax.set_title(\"Marginal Val-Loss Improvement per Epoch\")\n",
|
||
"ax.legend(fontsize=8)\n",
|
||
"ax.grid(True, alpha=0.3)\n",
|
||
"\n",
|
||
"# --- Bottom-right: Learning rate schedule ---\n",
|
||
"ax = axes[1, 1]\n",
|
||
"ax.semilogy(epochs_axis, lr_history, \"purple\", linewidth=2)\n",
|
||
"if convergence_epoch:\n",
|
||
" ax.axvline(x=convergence_epoch, color=\"orange\", linestyle=\":\", linewidth=1.5,\n",
|
||
" label=f\"HỘI TỤ epoch={convergence_epoch}\")\n",
|
||
"ax.axvline(x=best_epoch, color=\"red\", linestyle=\"--\", linewidth=1.5,\n",
|
||
" label=f\"Best epoch={best_epoch}\")\n",
|
||
"ax.set_xlabel(\"Epoch\")\n",
|
||
"ax.set_ylabel(\"Learning Rate (log)\")\n",
|
||
"ax.set_title(\"Learning Rate Schedule (ReduceLROnPlateau)\")\n",
|
||
"ax.legend(fontsize=8)\n",
|
||
"ax.grid(True, alpha=0.3)\n",
|
||
"\n",
|
||
"plt.suptitle(\"MobileNetV3 + LR-ASPP — Convergence Analysis\", fontsize=13, fontweight=\"bold\")\n",
|
||
"plt.tight_layout()\n",
|
||
"plt.show()\n",
|
||
"\n",
|
||
"# ── Tổng kết ──────────────────────────────────────────────────────────────────\n",
|
||
"print(f\"\\n{'═'*60}\")\n",
|
||
"print(f\" Tổng số epoch : {total_epochs}\")\n",
|
||
"print(f\" Best epoch : {best_epoch} (val_loss={best_val_loss:.4f})\")\n",
|
||
"print(f\" Best val accuracy : {val_accs[best_epoch-1]*100:.4f}%\")\n",
|
||
"if convergence_epoch:\n",
|
||
" print(f\" Điểm HỘI TỤ : epoch {convergence_epoch} \"\n",
|
||
" f\"(val_acc={val_accs[convergence_epoch-1]*100:.2f}%)\")\n",
|
||
" wasted = total_epochs - convergence_epoch\n",
|
||
" print(f\" Epochs sau hội tụ : {wasted} \"\n",
|
||
" f\"(có thể giảm N_EPOCHS không ảnh hưởng nhiều đến kết quả)\")\n",
|
||
"if early_stop_epoch:\n",
|
||
" print(f\" Early stop tại epoch: {early_stop_epoch}\")\n",
|
||
"print(f\"{'═'*60}\")\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "bc690b92",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": [
|
||
"from sklearn.metrics import classification_report, confusion_matrix, accuracy_score\n",
|
||
"import seaborn as sns\n",
|
||
"\n",
|
||
"# ── Đánh giá trên tập test ─────────────────────────────────────────────────────\n",
|
||
"model.eval()\n",
|
||
"with torch.no_grad():\n",
|
||
" X_te_t = torch.FloatTensor(X_test_np).to(device)\n",
|
||
" logits = model(X_te_t)\n",
|
||
" y_pred = logits.argmax(1).cpu().numpy()\n",
|
||
"\n",
|
||
"acc = accuracy_score(y_test_np, y_pred)\n",
|
||
"print(f\"Test Accuracy : {acc:.4f} ({acc*100:.2f}%)\\n\")\n",
|
||
"print(classification_report(y_test_np, y_pred, digits=4))\n",
|
||
"\n",
|
||
"# ── Confusion matrix ────────────────────────────────────────────────────────────\n",
|
||
"class_names = list(label_mapping.keys())\n",
|
||
"cm = confusion_matrix(y_test_np, y_pred)\n",
|
||
"plt.figure(figsize=(9, 7))\n",
|
||
"sns.heatmap(cm, annot=True, fmt=\"d\", cmap=\"Purples\",\n",
|
||
" xticklabels=class_names, yticklabels=class_names)\n",
|
||
"plt.xlabel(\"Predicted\")\n",
|
||
"plt.ylabel(\"Actual\")\n",
|
||
"plt.title(\"Confusion Matrix — MobileNetV3 + LR-ASPP\")\n",
|
||
"plt.tight_layout()\n",
|
||
"plt.show()\n"
|
||
]
|
||
},
|
||
{
|
||
"cell_type": "code",
|
||
"execution_count": null,
|
||
"id": "d4805767-4f58-4464-930c-66fcbb341cc2",
|
||
"metadata": {},
|
||
"outputs": [],
|
||
"source": []
|
||
}
|
||
],
|
||
"metadata": {
|
||
"kernelspec": {
|
||
"display_name": "Python 3 (ipykernel)",
|
||
"language": "python",
|
||
"name": "python3"
|
||
},
|
||
"language_info": {
|
||
"codemirror_mode": {
|
||
"name": "ipython",
|
||
"version": 3
|
||
},
|
||
"file_extension": ".py",
|
||
"mimetype": "text/x-python",
|
||
"name": "python",
|
||
"nbconvert_exporter": "python",
|
||
"pygments_lexer": "ipython3",
|
||
"version": "3.12.3"
|
||
}
|
||
},
|
||
"nbformat": 4,
|
||
"nbformat_minor": 5
|
||
}
|