ResourceExhaustedError：在分配具有形状的张量[973771,128]并在/ job：localhost / replica：0 / task：0 /上键入float时，OOM

Question

  

https://tensorflow.google.cn/hub/tf2_saved_model

import tensorflow as tf
import tensorflow_hub as hub
hub_url = "https://hub.tensorflow.google.cn/google/tf2-preview/nnlm-en-dim128/1"
embed = hub.KerasLayer(hub_url)
embeddings = embed(["A long sentence.", "single-word", "http://example.com"])
print(embeddings.shape, embeddings.dtype)

ResourceExhaustedError：分配带有形状的张量[973771,128]并在分配器cpu [Op：RestoreV2]上的/ job：localhost / replica：0 / task：0 / device：CPU：0上键入float时，OOM

请告诉我如何解决，谢谢

Answer 1

当您尝试分配NNLM模块的嵌入矩阵时，您似乎内存不足。它需要近476 MB的RAM。