Created by: monk1337

I am using this code to extract the embeddings for my dataset. It's quite slow and running on CPU only. I am able to use TensorFlow and PyTorch with GPU. How I can enable GPU for ERNIE?

import numpy as np
import paddle.fluid.dygraph as D
from ernie.tokenizing_ernie import ErnieTokenizer
from ernie.modeling_ernie import ErnieModel

D.guard().__enter__() # activate paddle `dygrpah` mode

model = ErnieModel.from_pretrained('ernie-1.0')    # Try to get pretrained model from server, make sure you have network connection
model.eval()
tokenizer = ErnieTokenizer.from_pretrained('ernie-1.0')

ids, _ = tokenizer.encode('hello world')
ids = D.to_variable(np.expand_dims(ids, 0))  # insert extra `batch` dimension
pooled, encoded = model(ids)                 # eager execution
print(pooled.numpy())                        # convert  results to numpy

To verify the gpu I ran this script :

python3 -c 'import paddle.fluid as f;f.install_check.run_check()'

Output is

Running Verify Fluid Program ... 
Your Paddle Fluid works well on SINGLE GPU or CPU.
W0831 20:17:07.630717 23699 build_strategy.cc:170] fusion_group is not enabled for Windows/MacOS now, and only effective when running with CUDA GPU.
W0831 20:17:07.653642 23699 fuse_all_reduce_op_pass.cc:74] Find all_reduce operators: 2. To make the speed faster, some all_reduce ops are fused during training, af
ter fusion, the number of all_reduce ops is 1.
Your Paddle Fluid works well on MUTIPLE GPU or CPU.
Your Paddle Fluid is installed successfully! Let's start deep Learning with Paddle Fluid now