適用於 Object2Vec 推論的資料格式

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。

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。

下頁說明從 Amazon SageMaker AI Object2Vec 模型取得評分推論的輸入請求和輸出回應格式。

GPU 最佳化：分類或廻歸

由於 GPU 記憶體不足，無論分類/廻歸或 輸出：編碼器內嵌 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分類或廻歸，請指定 INFERENCE_PREFERRED_MODE=classification。以下是使用 4 個 p3.2xlarge 執行個體，最佳化分類/廻歸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': 'classification'},  # only useful with GPU
                              output_path=output_s3_path)

輸入：分類或迴歸請求格式

Content-type: application/json

{
  "instances" : [
    {"in0": [6, 17, 606, 19, 53, 67, 52, 12, 5, 10, 15, 10178, 7, 33, 652, 80, 15, 69, 821, 4], "in1": [16, 21, 13, 45, 14, 9, 80, 59, 164, 4]},
    {"in0": [22, 1016, 32, 13, 25, 11, 5, 64, 573, 45, 5, 80, 15, 67, 21, 7, 9, 107, 4], "in1": [22, 32, 13, 25, 1016, 573, 3252, 4]},
    {"in0": [774, 14, 21, 206], "in1": [21, 366, 125]}
  ]
}

Content-type: application/jsonlines

{"in0": [6, 17, 606, 19, 53, 67, 52, 12, 5, 10, 15, 10178, 7, 33, 652, 80, 15, 69, 821, 4], "in1": [16, 21, 13, 45, 14, 9, 80, 59, 164, 4]}
{"in0": [22, 1016, 32, 13, 25, 11, 5, 64, 573, 45, 5, 80, 15, 67, 21, 7, 9, 107, 4], "in1": [22, 32, 13, 25, 1016, 573, 3252, 4]}
{"in0": [774, 14, 21, 206], "in1": [21, 366, 125]}

若是分類問題，分數向量的長度與 num_classes 對應。若是迴歸問題，長度為 1。

輸出：分類或迴歸回應格式

Accept: application/json

{
    "predictions": [
        {
            "scores": [
                0.6533935070037842,
                0.07582679390907288,
                0.2707797586917877
            ]
        },
        {
            "scores": [
                0.026291321963071823,
                0.6577019095420837,
                0.31600672006607056
            ]
        }
    ]
}

Accept: application/jsonlines

{"scores":[0.195667684078216,0.395351558923721,0.408980727195739]}
{"scores":[0.251988261938095,0.258233487606048,0.489778339862823]}
{"scores":[0.280087798833847,0.368331134319305,0.351581096649169]}

在這兩種分類和迴歸格式中，分數會套用到個別標籤。