报错解决:ResourceExhaustedError: OOM when allocating tensor with shape[1,36864,36864]
运行代码报错:Hint: If you want to see a list of allocated tensors when OOM happens, add report_tensor_allocations_upon_oom to RunOptions for current allocatio [Op:__inference_predict_function_5604]百度看到有人说显存不够,减小batchsize,然后我减小到1还是不行,最后发现是我文件开头加的三行代码(见下图)的问