Tetap teratur dengan koleksi
Simpan dan kategorikan konten berdasarkan preferensi Anda.
Jika Anda adalah developer ML berpengalaman dan library TensorFlow Lite
yang sudah di-build sebelumnya tidak sesuai dengan kebutuhan, Anda dapat menggunakan build
TensorFlow Lite kustom dengan ML Kit. Misalnya, Anda dapat menambahkan ops kustom.
[[["Mudah dipahami","easyToUnderstand","thumb-up"],["Memecahkan masalah saya","solvedMyProblem","thumb-up"],["Lainnya","otherUp","thumb-up"]],[["Informasi yang saya butuhkan tidak ada","missingTheInformationINeed","thumb-down"],["Terlalu rumit/langkahnya terlalu banyak","tooComplicatedTooManySteps","thumb-down"],["Sudah usang","outOfDate","thumb-down"],["Masalah terjemahan","translationIssue","thumb-down"],["Masalah kode / contoh","samplesCodeIssue","thumb-down"],["Lainnya","otherDown","thumb-down"]],["Terakhir diperbarui pada 2025-09-06 UTC."],[],[],null,["\u003cbr /\u003e\n\nIf you're an experienced ML developer and the pre-built TensorFlow Lite\nlibrary doesn't meet your needs, you can use a custom\n[TensorFlow Lite](//www.tensorflow.org/mobile/tflite/) build with ML Kit. For\nexample, you may want to add custom ops.\n\nPrerequisites\n\n- A working [TensorFlow Lite](https://github.com/tensorflow/tensorflow/blob/master/tensorflow/lite/README.md#building-tensorflow-lite-and-the-demo-app-from-source) build environment\n\nBundling a custom TensorFlow Lite for Android\n\nBuild the Tensorflow Lite AAR: \n\n```\nbazel build --cxxopt='--std=c++11' -c opt \\\n --fat_apk_cpu=x86,x86_64,arm64-v8a,armeabi-v7a \\\n //tensorflow/lite/java:tensorflow-lite\n```\n\nThis will generate an AAR file in `bazel-genfiles/tensorflow/lite/java/`.\nPublish the custom Tensorflow Lite AAR to your local\n[Maven](https://maven.apache.org/download.cgi) repository: \n\n```\nmvn install:install-file -Dfile=bazel-genfiles/tensorflow/lite/java/tensorflow-lite.aar -DgroupId=org.tensorflow \\\n -DartifactId=tensorflow-lite -Dversion=0.1.100 -Dpackaging=aar\n```\n\nFinally, in your app `build.gradle`, override Tensorflow Lite with your custom\nversion: \n\n implementation 'org.tensorflow:tensorflow-lite:0.1.100'"]]
