Terjemahan disediakan oleh mesin penerjemah. Jika konten terjemahan yang diberikan bertentangan dengan versi bahasa Inggris aslinya, utamakan versi bahasa Inggris.
# Model Khusus Tugas
JumpStart mendukung model khusus tugas di lima belas jenis masalah paling populer. Dari jenis masalah yang didukung, tipe terkait Visi dan NLP berjumlah tiga belas. Ada delapan jenis masalah yang mendukung pelatihan tambahan dan fine-tuning. Untuk informasi selengkapnya tentang pelatihan tambahan dan penyetelan hiper-parameter, lihat Penyetelan Model Otomatis [SageMaker AI](https://docs.aws.amazon.com/sagemaker/latest/dg/automatic-model-tuning.html). JumpStart juga mendukung empat algoritma populer untuk pemodelan data tabular.
Anda dapat mencari dan menelusuri model dari halaman JumpStart arahan di Studio atau Studio Classic. Saat Anda memilih model, halaman detail model memberikan informasi tentang model, dan Anda dapat melatih dan menerapkan model Anda dalam beberapa langkah. Bagian deskripsi menjelaskan apa yang dapat Anda lakukan dengan model, jenis input dan output yang diharapkan, dan tipe data yang diperlukan untuk menyempurnakan model Anda.
[Anda juga dapat menggunakan model secara terprogram dengan Python SageMaker SDK.](https://sagemaker.readthedocs.io/en/stable/overview.html#use-prebuilt-models-with-sagemaker-jumpstart) Untuk daftar semua model yang tersedia, lihat [Tabel Model yang JumpStart Tersedia](https://sagemaker.readthedocs.io/en/v2.132.0/doc_utils/pretrainedmodels.html).
Daftar jenis masalah dan tautan ke contoh notebook Jupyter mereka dirangkum dalam tabel berikut.
| Jenis masalah | Mendukung inferensi dengan model pra-terlatih | Dapat dilatih pada kumpulan data khusus | Kerangka kerja yang didukung | Contoh Notebook |
| --- | --- | --- | --- | --- |
| Klasifikasi gambar | Ya | Ya | PyTorch, TensorFlow | [Pengantar JumpStart - Klasifikasi Gambar](https://github.com/aws/amazon-sagemaker-examples/blob/main/introduction_to_amazon_algorithms/jumpstart_image_classification/Amazon_JumpStart_Image_Classification.ipynb) |
| Deteksi objek | Ya | Ya | PyTorch, TensorFlow, MXNet | [Pengantar JumpStart - Deteksi Objek](https://github.com/aws/amazon-sagemaker-examples/blob/main/introduction_to_amazon_algorithms/jumpstart_object_detection/Amazon_JumpStart_Object_Detection.ipynb) |
| Segmentasi semantik | Ya | Ya | MXNet | [Pengantar JumpStart - Segmentasi Semantik](https://github.com/aws/amazon-sagemaker-examples/blob/main/introduction_to_amazon_algorithms/jumpstart_semantic_segmentation/Amazon_JumpStart_Semantic_Segmentation.ipynb) |
| Segmentasi contoh | Ya | Ya | MXNet | [Pengantar JumpStart - Segmentasi Instance](https://github.com/aws/amazon-sagemaker-examples/blob/main/introduction_to_amazon_algorithms/jumpstart_instance_segmentation/Amazon_JumpStart_Instance_Segmentation.ipynb) |
| Penyematan gambar | Ya | Tidak | TensorFlow, MXNet | [Pengantar JumpStart - Penyematan Gambar](https://github.com/aws/amazon-sagemaker-examples/blob/main/introduction_to_amazon_algorithms/jumpstart_image_embedding/Amazon_JumpStart_Image_Embedding.ipynb) |
| Klasifikasi teks | Ya | Ya | TensorFlow | [Pengantar JumpStart - Klasifikasi Teks](https://github.com/aws/amazon-sagemaker-examples/blob/main/introduction_to_amazon_algorithms/jumpstart_text_classification/Amazon_JumpStart_Text_Classification.ipynb) |
| Klasifikasi pasangan kalimat | Ya | Ya | TensorFlow, Hugging Face | [Pengantar JumpStart - Klasifikasi Pasangan Kalimat](https://github.com/aws/amazon-sagemaker-examples/blob/main/introduction_to_amazon_algorithms/jumpstart_sentence_pair_classification/Amazon_JumpStart_Sentence_Pair_Classification.ipynb) |
| Menjawab pertanyaan | Ya | Ya | PyTorch, Hugging Face | [Pengantar JumpStart — Menjawab Pertanyaan](https://github.com/aws/amazon-sagemaker-examples/blob/main/introduction_to_amazon_algorithms/jumpstart_question_answering/Amazon_JumpStart_Question_Answering.ipynb) |
| Pengakuan entitas bernama | Ya | Tidak | Hugging Face | [Pengantar JumpStart - Pengakuan Entitas Bernama](https://github.com/aws/amazon-sagemaker-examples/blob/main/introduction_to_amazon_algorithms/jumpstart_named_entity_recognition/Amazon_JumpStart_Named_Entity_Recognition.ipynb) |
| Ringkasan teks | Ya | Tidak | Hugging Face | [Pengantar JumpStart - Ringkasan Teks](https://github.com/aws/amazon-sagemaker-examples/blob/main/introduction_to_amazon_algorithms/jumpstart_text_summarization/Amazon_JumpStart_Text_Summarization.ipynb) |
| Pembuatan teks | Ya | Tidak | Hugging Face | [Pengantar JumpStart - Pembuatan Teks](https://github.com/aws/amazon-sagemaker-examples/blob/main/introduction_to_amazon_algorithms/jumpstart_text_generation/Amazon_JumpStart_Text_Generation.ipynb) |
| Terjemahan mesin | Ya | Tidak | Hugging Face | [Pengantar JumpStart - Terjemahan Mesin](https://github.com/aws/amazon-sagemaker-examples/blob/main/introduction_to_amazon_algorithms/jumpstart_machine_translation/Amazon_JumpStart_Machine_Translation.ipynb) |
| Penyematan teks | Ya | Tidak | TensorFlow, MXNet | [Pengantar JumpStart - Penyematan Teks](https://github.com/aws/amazon-sagemaker-examples/blob/main/introduction_to_amazon_algorithms/jumpstart_text_embedding/Amazon_JumpStart_Text_Embedding.ipynb) |
| Klasifikasi tabel | Ya | Ya | LightGBM,,, AutoGluon -Tabular CatBoost XGBoost,, Pembelajar Linear TabTransformer | [Pengantar JumpStart - Klasifikasi Tabular - LightGBM, CatBoost](https://github.com/aws/amazon-sagemaker-examples/blob/main/introduction_to_amazon_algorithms/lightgbm_catboost_tabular/Amazon_Tabular_Classification_LightGBM_CatBoost.ipynb)
[Pengantar JumpStart - Klasifikasi Tabular - XGBoost, Pembelajar Linier](https://github.com/aws/amazon-sagemaker-examples/blob/main/introduction_to_amazon_algorithms/xgboost_linear_learner_tabular/Amazon_Tabular_Classification_XGBoost_LinearLearner.ipynb)
[Pengantar JumpStart - Klasifikasi Tabular - Peserta AutoGluon](https://github.com/aws/amazon-sagemaker-examples/blob/main/introduction_to_amazon_algorithms/autogluon_tabular/Amazon_Tabular_Classification_AutoGluon.ipynb)
[Pengantar JumpStart - Klasifikasi Tabular - Peserta TabTransformer](https://github.com/aws/amazon-sagemaker-examples/blob/main/introduction_to_amazon_algorithms/tabtransformer_tabular/Amazon_Tabular_Classification_TabTransformer.ipynb) |
| Regresi tabel | Ya | Ya | LightGBM,,, AutoGluon -Tabular CatBoost XGBoost,, Pembelajar Linear TabTransformer | [Pengantar JumpStart - Regresi Tabular - LightGBM, CatBoost](https://github.com/aws/amazon-sagemaker-examples/blob/main/introduction_to_amazon_algorithms/lightgbm_catboost_tabular/Amazon_Tabular_Regression_LightGBM_CatBoost.ipynb)
[Pengantar JumpStart - Regresi Tabular -, Pembelajar Linier XGBoost](https://github.com/aws/amazon-sagemaker-examples/blob/main/introduction_to_amazon_algorithms/xgboost_linear_learner_tabular/Amazon_Tabular_Regression_XGBoost_LinearLearner.ipynb)
[Pengantar JumpStart — Regresi Tabular - Peserta AutoGluon ](https://github.com/aws/amazon-sagemaker-examples/blob/main/introduction_to_amazon_algorithms/autogluon_tabular/Amazon_Tabular_Regression_AutoGluon.ipynb)
[Pengantar JumpStart — Regresi Tabular - Peserta TabTransformer](https://github.com/aws/amazon-sagemaker-examples/blob/main/introduction_to_amazon_algorithms/tabtransformer_tabular/Amazon_Tabular_Regression_TabTransformer.ipynb) |