本文為英文版的機器翻譯版本，如內容有任何歧義或不一致之處，概以英文版為準。

# 適用於 Object2Vec 的編碼器內嵌
<a name="object2vec-encoder-embeddings"></a>

以下頁面列出從 Amazon SageMaker AI Object2Vec 模型取得編碼器內嵌推論的輸入請求和輸出回應格式。

## GPU 最佳化：編碼器內嵌
<a name="object2vec-inference-gpu-optimize-encoder-embeddings"></a>

內嵌是指從離散物件 (例如單字) 對應至實數向量。

由於 GPU 記憶體不足，無論 [適用於 Object2Vec 推論的資料格式](object2vec-inference-formats.md) 或編碼器內嵌的推論網路是否載入 GPU，都會指定要最佳化 `INFERENCE_PREFERRED_MODE` 環境變數。如果大部分的推論是用於編碼器內嵌，請指定 `INFERENCE_PREFERRED_MODE=embedding`。以下是使用 4 個 p3.2xlarge 執行個體，最佳化編碼器內嵌推論的批次轉換範例：

```
transformer = o2v.transformer(instance_count=4,
                              instance_type="ml.p2.xlarge",
                              max_concurrent_transforms=2,
                              max_payload=1,  # 1MB
                              strategy='MultiRecord',
                              env={'INFERENCE_PREFERRED_MODE': 'embedding'},  # only useful with GPU
                              output_path=output_s3_path)
```

## 輸入：編碼器內嵌
<a name="object2vec-in-encoder-embeddings-data"></a>

Content-type: application/json; infer\$1max\$1seqlens=<FWD-LENGTH>,<BCK-LENGTH>

其中，<FWD-LENGTH> 和 <BCK-LENGTH> 是範圍 [1,5000] 的整數，定義正向和反向編碼器的最大序列長度。

```
{
  "instances" : [
    {"in0": [6, 17, 606, 19, 53, 67, 52, 12, 5, 10, 15, 10178, 7, 33, 652, 80, 15, 69, 821, 4]},
    {"in0": [22, 1016, 32, 13, 25, 11, 5, 64, 573, 45, 5, 80, 15, 67, 21, 7, 9, 107, 4]},
    {"in0": [774, 14, 21, 206]}
  ]
}
```

Content-type: application/jsonlines; infer\$1max\$1seqlens=<FWD-LENGTH>,<BCK-LENGTH>

其中，<FWD-LENGTH> 和 <BCK-LENGTH> 是範圍 [1,5000] 的整數，定義正向和反向編碼器的最大序列長度。

```
{"in0": [6, 17, 606, 19, 53, 67, 52, 12, 5, 10, 15, 10178, 7, 33, 652, 80, 15, 69, 821, 4]}
{"in0": [22, 1016, 32, 13, 25, 11, 5, 64, 573, 45, 5, 80, 15, 67, 21, 7, 9, 107, 4]}
{"in0": [774, 14, 21, 206]}
```

在這兩種格式中，您只要指定 `“in0”` 或 `“in1.”` 其中一個輸入類型。推論服務即會為每個執行個體調用對應的編碼器，並輸出內嵌。

## 輸出：編碼器內嵌
<a name="object2vec-out-encoder-embeddings-data"></a>

Content-type: application/json

```
{
  "predictions": [
    {"embeddings":[0.057368703186511,0.030703511089086,0.099890425801277,0.063688032329082,0.026327300816774,0.003637571120634,0.021305780857801,0.004316598642617,0.0,0.003397724591195,0.0,0.000378780066967,0.0,0.0,0.0,0.007419463712722]},
    {"embeddings":[0.150190666317939,0.05145975202322,0.098204270005226,0.064249359071254,0.056249320507049,0.01513972133398,0.047553978860378,0.0,0.0,0.011533712036907,0.011472506448626,0.010696629062294,0.0,0.0,0.0,0.008508535102009]}
  ]
}
```

Content-type: application/jsonlines

```
{"embeddings":[0.057368703186511,0.030703511089086,0.099890425801277,0.063688032329082,0.026327300816774,0.003637571120634,0.021305780857801,0.004316598642617,0.0,0.003397724591195,0.0,0.000378780066967,0.0,0.0,0.0,0.007419463712722]}
{"embeddings":[0.150190666317939,0.05145975202322,0.098204270005226,0.064249359071254,0.056249320507049,0.01513972133398,0.047553978860378,0.0,0.0,0.011533712036907,0.011472506448626,0.010696629062294,0.0,0.0,0.0,0.008508535102009]}
```

推論服務輸出的內嵌向量長度等於您在訓練時指定的下列其中一個超參數值：`enc0_token_embedding_dim`、`enc1_token_embedding_dim` 或 `enc_dim`。