提交 1ee9fea3 编写于 作者: K kolinwei

change some code style

上级 07536903
......@@ -184,7 +184,7 @@ def run_benchmark(model, args):
]
) # The accuracy is the accumulation of batches, but not the current batch.
accuracy.update(
value=np.array(np.mean(outs[1])),
value=np.array(np.mean(outs[1])),
weight=np.mean(np.array(outs[2])))
iters += 1
num_samples += len(y_data)
......
Markdown is supported
0% .
You are about to add 0 people to the discussion. Proceed with caution.
先完成此消息的编辑!
想要评论请 注册