TensorFlow Hub 模型
以下预先训练模型可用于使用文本分类 – TensorFlow 算法的迁移学习。
对于任何给定数据集，以下模型在大小、模型参数数量、训练时间和推理延迟方面差异很大。最适合您的使用场景的模型取决于微调数据集的复杂性，以及您对训练时间、推理延迟或模型准确性的任何要求。
| 模型名称 | model_id |
源 |
|---|---|---|
|
BERT Base Uncased |
|
|
|
BERT Base Cased |
|
|
|
BERT Base Multilingual Cased |
|
|
|
Small BERT L-2_H-128_A-2 |
|
|
|
Small BERT L-2_H-256_A-4 |
|
|
|
Small BERT L-2_H-512_A-8 |
|
|
|
Small BERT L-2_H-768_A-12 |
|
|
|
Small BERT L-4_H-128_A-2 |
|
|
|
Small BERT L-4_H-256_A-4 |
|
|
|
Small BERT L-4_H-512_A-8 |
|
|
|
Small BERT L-4_H-768_A-12 |
|
|
|
Small BERT L-6_H-128_A-2 |
|
|
|
Small BERT L-6_H-256_A-4 |
|
|
|
Small BERT L-6_H-512_A-8 |
|
|
|
Small BERT L-6_H-768_A-12 |
|
|
|
Small BERT L-8_H-128_A-2 |
|
|
|
Small BERT L-8_H-256_A-4 |
|
|
|
Small BERT L-8_H-512_A-8 |
|
|
|
Small BERT L-8_H-768_A-12 |
|
|
|
Small BERT L-10_H-128_A-2 |
|
|
|
Small BERT L-10_H-256_A-4 |
|
|
|
Small BERT L-10_H-512_A-8 |
|
|
|
Small BERT L-10_H-768_A-12 |
|
|
|
Small BERT L-12_H-128_A-2 |
|
|
|
Small BERT L-12_H-256_A-4 |
|
|
|
Small BERT L-12_H-512_A-8 |
|
|
|
Small BERT L-12_H-768_A-12 |
|
|
|
BERT Large Uncased |
|
|
|
BERT Large Cased |
|
|
|
BERT Large Uncased Whole Word Masking |
|
|
|
BERT Large Cased Whole Word Masking |
|
|
|
ALBERT Base |
|
|
|
ELECTRA Small++ |
|
|
|
ELECTRA Base |
|
|
|
BERT Base Wikipedia and BooksCorpus |
|
|
|
BERT Base MEDLINE/PubMed |
|
|
|
Talking Heads Base |
|
|
|
Talking Heads Large |
|
