Export.classifier.toAsset
Sử dụng bộ sưu tập để sắp xếp ngăn nắp các trang
Lưu và phân loại nội dung dựa trên lựa chọn ưu tiên của bạn.
Tạo một tác vụ hàng loạt để xuất ee.Classifier dưới dạng một tài sản Earth Engine.
Chỉ hỗ trợ cho ee.Classifier.smileRandomForest, ee.Classifier.smileCart, ee.Classifier.DecisionTree và ee.Classifier.DecisionTreeEnsemble.
Cách sử dụng | Giá trị trả về |
---|
Export.classifier.toAsset(classifier, description, assetId, priority) | |
Đối số | Loại | Thông tin chi tiết |
---|
classifier | ComputedObject | Trình phân loại cần xuất. |
description | Chuỗi, không bắt buộc | Tên công việc mà con người đọc được. Giá trị mặc định là "myExportClassifierTask". |
assetId | Chuỗi, không bắt buộc | Mã thành phần đích. |
priority | Số, không bắt buộc | Mức độ ưu tiên của công việc trong dự án. Các tác vụ có mức độ ưu tiên cao hơn sẽ được lên lịch sớm hơn. Phải là số nguyên từ 0 đến 9999. Giá trị mặc định là 100. |
Ví dụ
Trình soạn thảo mã (JavaScript)
// First gather the training data for a random forest classifier.
// Let's use MCD12Q1 yearly landcover for the labels.
var landcover = ee.ImageCollection('MODIS/061/MCD12Q1')
.filterDate('2022-01-01', '2022-12-31')
.first()
.select('LC_Type1');
// A region of interest for training our classifier.
var region = ee.Geometry.BBox(17.33, 36.07, 26.13, 43.28);
// Training features will be based on a Landsat 8 composite.
var l8 = ee.ImageCollection('LANDSAT/LC08/C02/T1')
.filterBounds(region)
.filterDate('2022-01-01', '2023-01-01');
// Draw the Landsat composite, visualizing true color bands.
var landsatComposite = ee.Algorithms.Landsat.simpleComposite({
collection: l8,
asFloat: true
});
Map.addLayer(landsatComposite, {
min: 0,
max: 0.3,
bands: ['B3', 'B2', 'B1']
}, 'Landsat composite');
// Make a training dataset by sampling the stacked images.
var training = landcover.addBands(landsatComposite).sample({
region: region,
scale: 30,
// With export to Classifier we can bump this higher to say 10,000.
numPixels: 1000
});
var classifier = ee.Classifier.smileRandomForest({
// We can also increase the number of trees higher to ~100 if needed.
numberOfTrees: 3
}).train({features: training, classProperty: 'LC_Type1'});
// Create an export classifier task to run.
var assetId = 'projects/<project-name>/assets/<asset-name>'; // <> modify these
Export.classifier.toAsset({
classifier: classifier,
description: 'classifier_export',
assetId: assetId
});
// Load the classifier after the export finishes and visualize.
var savedClassifier = ee.Classifier.load(assetId)
var landcoverPalette = '05450a,086a10,54a708,78d203,009900,c6b044,dcd159,' +
'dade48,fbff13,b6ff05,27ff87,c24f44,a5a5a5,ff6d4c,69fff8,f9ffa4,1c0dff';
var landcoverVisualization = {
palette: landcoverPalette,
min: 0,
max: 16,
format: 'png'
};
Map.addLayer(
landsatComposite.classify(savedClassifier),
landcoverVisualization,
'Upsampled landcover, saved');
Thiết lập Python
Hãy xem trang
Môi trường Python để biết thông tin về API Python và cách sử dụng geemap
để phát triển tương tác.
import ee
import geemap.core as geemap
Colab (Python)
# First gather the training data for a random forest classifier.
# Let's use MCD12Q1 yearly landcover for the labels.
landcover = (ee.ImageCollection('MODIS/061/MCD12Q1')
.filterDate('2022-01-01', '2022-12-31')
.first()
.select('LC_Type1'))
# A region of interest for training our classifier.
region = ee.Geometry.BBox(17.33, 36.07, 26.13, 43.28)
# Training features will be based on a Landsat 8 composite.
l8 = (ee.ImageCollection('LANDSAT/LC08/C02/T1')
.filterBounds(region)
.filterDate('2022-01-01', '2023-01-01'))
# Draw the Landsat composite, visualizing true color bands.
landsatComposite = ee.Algorithms.Landsat.simpleComposite(
collection=l8, asFloat=True)
Map = geemap.Map()
Map # Render the map in the notebook.
Map.addLayer(landsatComposite, {
'min': 0,
'max': 0.3,
'bands': ['B3', 'B2', 'B1']
}, 'Landsat composite')
# Make a training dataset by sampling the stacked images.
training = landcover.addBands(landsatComposite).sample(
region=region,
scale=30,
# With export to Classifier we can bump this higher to say 10,000.
numPixels=1000
)
# We can also increase the number of trees higher to ~100 if needed.
classifier = ee.Classifier.smileRandomForest(
numberOfTrees=3).train(features=training, classProperty='LC_Type1')
# Create an export classifier task to run.
asset_id = 'projects/<project-name>/assets/<asset-name>' # <> modify these
ee.batch.Export.classifier.toAsset(
classifier=classifier,
description='classifier_export',
assetId=asset_id
)
# Load the classifier after the export finishes and visualize.
savedClassifier = ee.Classifier.load(asset_id)
landcover_palette = [
'05450a', '086a10', '54a708', '78d203', '009900',
'c6b044', 'dcd159', 'dade48', 'fbff13', 'b6ff05',
'27ff87', 'c24f44', 'a5a5a5', 'ff6d4c', '69fff8',
'f9ffa4', '1c0dff']
landcoverVisualization = {
'palette': landcover_palette,
'min': 0,
'max': 16,
'format': 'png'
}
Map.addLayer(
landsatComposite.classify(savedClassifier),
landcoverVisualization,
'Upsampled landcover, saved')
Trừ phi có lưu ý khác, nội dung của trang này được cấp phép theo Giấy phép ghi nhận tác giả 4.0 của Creative Commons và các mẫu mã lập trình được cấp phép theo Giấy phép Apache 2.0. Để biết thông tin chi tiết, vui lòng tham khảo Chính sách trang web của Google Developers. Java là nhãn hiệu đã đăng ký của Oracle và/hoặc các đơn vị liên kết với Oracle.
Cập nhật lần gần đây nhất: 2025-07-25 UTC.
[null,null,["Cập nhật lần gần đây nhất: 2025-07-25 UTC."],[[["\u003cp\u003eExports an Earth Engine classifier as an asset for later use.\u003c/p\u003e\n"],["\u003cp\u003eAllows customization of the export task with description, asset ID, and priority settings.\u003c/p\u003e\n"],["\u003cp\u003eProvides code examples in JavaScript and Python demonstrating the export and subsequent use of the saved classifier.\u003c/p\u003e\n"],["\u003cp\u003eUtilizes a Landsat-based composite and MODIS landcover data for training the classifier in the examples.\u003c/p\u003e\n"],["\u003cp\u003eEnables efficient saving and loading of trained classifiers within the Earth Engine platform.\u003c/p\u003e\n"]]],["This content details exporting an `ee.Classifier` as an Earth Engine asset using `Export.classifier.toAsset`. Key actions include: creating a classifier, defining a training dataset using landcover data and Landsat composites, sampling training data, and then training the classifier. The export process involves specifying the `classifier`, `description`, `assetId`, and `priority`. After export, the saved classifier can be loaded and used for classification, then visualized.\n"],null,["# Export.classifier.toAsset\n\n\u003cbr /\u003e\n\nCreates a batch task to export an ee.Classifier as an Earth Engine asset.\n\n\u003cbr /\u003e\n\nOnly supported for ee.Classifier.smileRandomForest, ee.Classifier.smileCart, ee.Classifier.DecisionTree and ee.Classifier.DecisionTreeEnsemble.\n\n| Usage | Returns |\n|---------------------------------------------------------------------------------------|---------|\n| `Export.classifier.toAsset(classifier, `*description* `, `*assetId* `, `*priority*`)` | |\n\n| Argument | Type | Details |\n|---------------|------------------|--------------------------------------------------------------------------------------------------------------------------------------------------|\n| `classifier` | ComputedObject | The classifier to export. |\n| `description` | String, optional | A human-readable name of the task. Defaults to \"myExportClassifierTask\". |\n| `assetId` | String, optional | The destination asset ID. |\n| `priority` | Number, optional | The priority of the task within the project. Higher priority tasks are scheduled sooner. Must be an integer between 0 and 9999. Defaults to 100. |\n\nExamples\n--------\n\n### Code Editor (JavaScript)\n\n```javascript\n// First gather the training data for a random forest classifier.\n// Let's use MCD12Q1 yearly landcover for the labels.\nvar landcover = ee.ImageCollection('MODIS/061/MCD12Q1')\n .filterDate('2022-01-01', '2022-12-31')\n .first()\n .select('LC_Type1');\n// A region of interest for training our classifier.\nvar region = ee.Geometry.BBox(17.33, 36.07, 26.13, 43.28);\n\n// Training features will be based on a Landsat 8 composite.\nvar l8 = ee.ImageCollection('LANDSAT/LC08/C02/T1')\n .filterBounds(region)\n .filterDate('2022-01-01', '2023-01-01');\n\n// Draw the Landsat composite, visualizing true color bands.\nvar landsatComposite = ee.Algorithms.Landsat.simpleComposite({\n collection: l8,\n asFloat: true\n});\nMap.addLayer(landsatComposite, {\n min: 0,\n max: 0.3,\n bands: ['B3', 'B2', 'B1']\n}, 'Landsat composite');\n\n// Make a training dataset by sampling the stacked images.\nvar training = landcover.addBands(landsatComposite).sample({\n region: region,\n scale: 30,\n // With export to Classifier we can bump this higher to say 10,000.\n numPixels: 1000\n});\n\nvar classifier = ee.Classifier.smileRandomForest({\n // We can also increase the number of trees higher to ~100 if needed.\n numberOfTrees: 3\n}).train({features: training, classProperty: 'LC_Type1'});\n\n// Create an export classifier task to run.\nvar assetId = 'projects/\u003cproject-name\u003e/assets/\u003casset-name\u003e'; // \u003c\u003e modify these\nExport.classifier.toAsset({\n classifier: classifier,\n description: 'classifier_export',\n assetId: assetId\n});\n\n// Load the classifier after the export finishes and visualize.\nvar savedClassifier = ee.Classifier.load(assetId)\nvar landcoverPalette = '05450a,086a10,54a708,78d203,009900,c6b044,dcd159,' +\n 'dade48,fbff13,b6ff05,27ff87,c24f44,a5a5a5,ff6d4c,69fff8,f9ffa4,1c0dff';\nvar landcoverVisualization = {\n palette: landcoverPalette,\n min: 0,\n max: 16,\n format: 'png'\n};\nMap.addLayer(\n landsatComposite.classify(savedClassifier),\n landcoverVisualization,\n 'Upsampled landcover, saved');\n```\nPython setup\n\nSee the [Python Environment](/earth-engine/guides/python_install) page for information on the Python API and using\n`geemap` for interactive development. \n\n```python\nimport ee\nimport geemap.core as geemap\n```\n\n### Colab (Python)\n\n```python\n# First gather the training data for a random forest classifier.\n# Let's use MCD12Q1 yearly landcover for the labels.\nlandcover = (ee.ImageCollection('MODIS/061/MCD12Q1')\n .filterDate('2022-01-01', '2022-12-31')\n .first()\n .select('LC_Type1'))\n\n# A region of interest for training our classifier.\nregion = ee.Geometry.BBox(17.33, 36.07, 26.13, 43.28)\n\n# Training features will be based on a Landsat 8 composite.\nl8 = (ee.ImageCollection('LANDSAT/LC08/C02/T1')\n .filterBounds(region)\n .filterDate('2022-01-01', '2023-01-01'))\n\n# Draw the Landsat composite, visualizing true color bands.\nlandsatComposite = ee.Algorithms.Landsat.simpleComposite(\n collection=l8, asFloat=True)\n\nMap = geemap.Map()\nMap # Render the map in the notebook.\nMap.addLayer(landsatComposite, {\n 'min': 0,\n 'max': 0.3,\n 'bands': ['B3', 'B2', 'B1']\n}, 'Landsat composite')\n\n# Make a training dataset by sampling the stacked images.\ntraining = landcover.addBands(landsatComposite).sample(\n region=region,\n scale=30,\n # With export to Classifier we can bump this higher to say 10,000.\n numPixels=1000\n)\n\n# We can also increase the number of trees higher to ~100 if needed.\nclassifier = ee.Classifier.smileRandomForest(\n numberOfTrees=3).train(features=training, classProperty='LC_Type1')\n\n# Create an export classifier task to run.\nasset_id = 'projects/\u003cproject-name\u003e/assets/\u003casset-name\u003e' # \u003c\u003e modify these\nee.batch.Export.classifier.toAsset(\n classifier=classifier,\n description='classifier_export',\n assetId=asset_id\n)\n\n# Load the classifier after the export finishes and visualize.\nsavedClassifier = ee.Classifier.load(asset_id)\nlandcover_palette = [\n '05450a', '086a10', '54a708', '78d203', '009900',\n 'c6b044', 'dcd159', 'dade48', 'fbff13', 'b6ff05',\n '27ff87', 'c24f44', 'a5a5a5', 'ff6d4c', '69fff8',\n 'f9ffa4', '1c0dff']\nlandcoverVisualization = {\n 'palette': landcover_palette,\n 'min': 0,\n 'max': 16,\n 'format': 'png'\n}\nMap.addLayer(\n landsatComposite.classify(savedClassifier),\n landcoverVisualization,\n 'Upsampled landcover, saved')\n```"]]