geoai-py 0.6.0__tar.gz → 0.7.0__tar.gz

{geoai_py-0.6.0 → geoai_py-0.7.0}/PKG-INFO

@@ -1,6 +1,6 @@
 Metadata-Version: 2.4
 Name: geoai-py
-Version: 0.6.0
+Version: 0.7.0
 Summary: A Python package for using Artificial Intelligence (AI) with geospatial data
 Author-email: Qiusheng Wu <giswqs@gmail.com>
 License: MIT License

{geoai_py-0.6.0 → geoai_py-0.7.0}/docs/examples/data_visualization.ipynb

@@ -334,7 +334,7 @@
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "Visualize the raster data on an interactive map with Google Satellite imagery as the background:"
+    "Visualize the raster data on an interactive map with Esri.WorldImagery imagery as the background:"
    ]
   },
   {
@@ -343,14 +343,14 @@
    "metadata": {},
    "outputs": [],
    "source": [
-    "view_raster(data, basemap=\"Google Satellite\")"
+    "view_raster(data, basemap=\"Esri.WorldImagery\")"
    ]
   },
   {
    "cell_type": "markdown",
    "metadata": {},
    "source": [
-    "This interactive visualization places the sampled data in its real-world geographic context, allowing you to see how it aligns with the Google Satellite imagery.\n",
+    "This interactive visualization places the sampled data in its real-world geographic context, allowing you to see how it aligns with the Esri.WorldImagery imagery.\n",
     "\n",
     "## Key Takeaways\n",
     "\n",

{geoai_py-0.6.0 → geoai_py-0.7.0}/docs/examples/download_data.ipynb

@@ -58,7 +58,7 @@
    "outputs": [],
    "source": [
     "m = leafmap.Map(center=[47.6526, -117.5923], zoom=16)\n",
-    "m.add_basemap(\"Google Satellite\")\n",
+    "m.add_basemap(\"Esri.WorldImagery\")\n",
     "m"
    ]
   },

{geoai_py-0.6.0 → geoai_py-0.7.0}/docs/examples/edit_vector.ipynb

@@ -51,7 +51,7 @@
    "outputs": [],
    "source": [
     "m = geoai.MapLibre()\n",
-    "m.add_basemap(\"Google Satellite\")\n",
+    "m.add_basemap(\"Esri.WorldImagery\")\n",
     "url = \"https://huggingface.co/datasets/giswqs/geospatial/resolve/main/naip_train_buildings.geojson\""
    ]
   },
@@ -102,7 +102,7 @@
  ],
  "metadata": {
   "kernelspec": {
-   "display_name": "Python 3 (ipykernel)",
+   "display_name": "geo",
    "language": "python",
    "name": "python3"
   },

geoai_py-0.7.0/docs/examples/train_landcover_classification.ipynb

@@ -0,0 +1,271 @@
+{
+ "cells": [
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "vscode": {
+     "languageId": "raw"
+    }
+   },
+   "source": [
+    "# Train a Land Cover Classification Model\n",
+    "\n",
+    "[![image](https://colab.research.google.com/assets/colab-badge.svg)](https://colab.research.google.com/github/opengeos/geoai/blob/main/docs/examples/train_landcover_classification.ipynb)\n",
+    "\n",
+    "## Install packages\n",
+    "\n",
+    "To use the new functionality, ensure the required packages are installed."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# %pip install geoai-py"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "vscode": {
+     "languageId": "raw"
+    }
+   },
+   "source": [
+    "## Import libraries"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "import geoai"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Download sample data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "train_raster_url = \"https://huggingface.co/datasets/giswqs/geospatial/resolve/main/m_3807511_ne_18_060_20181104.tif\"\n",
+    "train_landcover_url = \"https://huggingface.co/datasets/giswqs/geospatial/resolve/main/m_3807511_ne_18_060_20181104_landcover.tif\"\n",
+    "test_raster_url = \"https://huggingface.co/datasets/giswqs/geospatial/resolve/main/m_3807511_se_18_060_20181104.tif\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "train_raster_path = geoai.download_file(train_raster_url)\n",
+    "train_landcover_path = geoai.download_file(train_landcover_url)\n",
+    "test_raster_path = geoai.download_file(test_raster_url)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Visualize sample data"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "geoai.view_raster(train_landcover_url, basemap=train_raster_url)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "geoai.view_raster(test_raster_url)"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "vscode": {
+     "languageId": "raw"
+    }
+   },
+   "source": [
+    "## Create training data\n",
+    "\n",
+    "We will use the NAIP dataset for land cover classification. The classification scheme is adopted from the [Chesapeake Land Cover](https://planetarycomputer.microsoft.com/dataset/chesapeake-lc-13) project.\n",
+    "\n",
+    "**Important Note for Land Cover Classification:**\n",
+    "- Your label images should contain integer class values (0, 1, 2, ..., 13 for 13 classes)\n",
+    "- Do NOT use binary masks - the training code now properly handles multi-class labels\n",
+    "- Class 0 is typically background, classes 1-12 are your land cover types"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "out_folder = \"landcover\"\n",
+    "tiles = geoai.export_geotiff_tiles(\n",
+    "    in_raster=train_raster_path,\n",
+    "    out_folder=out_folder,\n",
+    "    in_class_data=train_landcover_path,\n",
+    "    tile_size=512,\n",
+    "    stride=256,\n",
+    "    buffer_radius=0,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "vscode": {
+     "languageId": "raw"
+    }
+   },
+   "source": [
+    "## Train semantic segmentation model\n",
+    "\n",
+    "Now we'll train a semantic segmentation model using the new `train_object_detection` function. This function supports various architectures from `segmentation-models-pytorch`:\n",
+    "\n",
+    "- **Architectures**: `unet`, `deeplabv3`, `deeplabv3plus`, `fpn`, `pspnet`, `linknet`, `manet`\n",
+    "- **Encoders**: `resnet34`, `resnet50`, `efficientnet-b0`, `mobilenet_v2`, etc."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Train U-Net model\n",
+    "geoai.train_segmentation_model(\n",
+    "    images_dir=f\"{out_folder}/images\",\n",
+    "    labels_dir=f\"{out_folder}/labels\",\n",
+    "    output_dir=f\"{out_folder}/unet_models\",\n",
+    "    architecture=\"unet\",\n",
+    "    encoder_name=\"resnet34\",\n",
+    "    encoder_weights=\"imagenet\",\n",
+    "    num_channels=4,\n",
+    "    num_classes=13,\n",
+    "    batch_size=8,\n",
+    "    num_epochs=50,\n",
+    "    learning_rate=0.001,\n",
+    "    val_split=0.2,\n",
+    "    verbose=True,\n",
+    "    plot_curves=True,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {
+    "vscode": {
+     "languageId": "raw"
+    }
+   },
+   "source": [
+    "## Run inference\n",
+    "\n",
+    "Now we'll use the trained model to make predictions on the test image."
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Define paths\n",
+    "masks_path = \"naip_test_semantic_prediction.tif\"\n",
+    "model_path = f\"{out_folder}/unet_models/best_model.pth\""
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "# Run semantic segmentation inference\n",
+    "geoai.semantic_segmentation(\n",
+    "    input_path=test_raster_path,\n",
+    "    output_path=masks_path,\n",
+    "    model_path=model_path,\n",
+    "    architecture=\"unet\",\n",
+    "    encoder_name=\"resnet34\",\n",
+    "    num_channels=4,\n",
+    "    num_classes=13,\n",
+    "    window_size=512,\n",
+    "    overlap=256,\n",
+    "    batch_size=4,\n",
+    ")"
+   ]
+  },
+  {
+   "cell_type": "markdown",
+   "metadata": {},
+   "source": [
+    "## Visualize results"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "geoai.write_colormap(masks_path, train_landcover_path, output=masks_path)"
+   ]
+  },
+  {
+   "cell_type": "code",
+   "execution_count": null,
+   "metadata": {},
+   "outputs": [],
+   "source": [
+    "geoai.view_raster(masks_path, basemap=test_raster_url)"
+   ]
+  }
+ ],
+ "metadata": {
+  "kernelspec": {
+   "display_name": "geo",
+   "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": "3.12.2"
+  }
+ },
+ "nbformat": 4,
+ "nbformat_minor": 4
+}