Meningkatkan penjelasan untuk klasifikasi gambar AutoML
Tetap teratur dengan koleksi
Simpan dan kategorikan konten berdasarkan preferensi Anda.
Saat menggunakan model gambar AutoML, Anda dapat mengonfigurasi
parameter tertentu untuk meningkatkan kualitas penjelasan Anda.
Metode atribusi fitur
Vertex Explainable AI didasarkan pada varian
nilai Shapley. Karena
nilai Shapley sangat mahal secara komputasi, Vertex Explainable AI hanya memberikan
perkiraan, bukan nilai tepatnya.
Anda dapat mengurangi error perkiraan dan mendapatkan nilai yang mendekati nilai yang tepat dengan
mengubah input berikut:
Meningkatkan jumlah langkah integral atau jumlah jalur.
Meningkatkan langkah
Untuk mengurangi error perkiraan, Anda dapat meningkatkan:
[[["Mudah dipahami","easyToUnderstand","thumb-up"],["Memecahkan masalah saya","solvedMyProblem","thumb-up"],["Lainnya","otherUp","thumb-up"]],[["Sulit dipahami","hardToUnderstand","thumb-down"],["Informasi atau kode contoh salah","incorrectInformationOrSampleCode","thumb-down"],["Informasi/contoh yang saya butuhkan tidak ada","missingTheInformationSamplesINeed","thumb-down"],["Masalah terjemahan","translationIssue","thumb-down"],["Lainnya","otherDown","thumb-down"]],["Terakhir diperbarui pada 2025-08-19 UTC."],[],[],null,["# Improve explanations for AutoML image classification\n\n| **Preview**\n|\n|\n| This feature is subject to the \"Pre-GA Offerings Terms\" in the General Service Terms section\n| of the [Service Specific Terms](/terms/service-terms#1).\n|\n| Pre-GA features are available \"as is\" and might have limited support.\n|\n| For more information, see the\n| [launch stage descriptions](/products#product-launch-stages).\n\nWhen you are working with AutoML image models, you can configure\nspecific parameters to improve your explanations.\n\nThe [Vertex Explainable AI feature attribution\nmethods](/vertex-ai/docs/explainable-ai/overview#compare-methods) are all based on variants of\nShapley values. Because\nShapley values are very computationally expensive, Vertex Explainable AI provides\napproximations instead of the exact values.\n\nYou can reduce the approximation error and get closer to the exact values by\nchanging the following inputs:\n\n- Increasing the number of integral steps or number of paths.\n\n### Increasing steps\n\nTo reduce approximation error, you can increase:\n\n- the **Number of integral steps** in the UI\n\nWhat's next\n-----------\n\n- Explore the [Limitations of Vertex Explainable AI](/vertex-ai/docs/explainable-ai/limitations)."]]
