提交 16347d3e 编写于 作者: W wangmeng28

Fix var name in SE-RexNeXt

上级 f2f6daa2
......@@ -145,9 +145,9 @@ def train(learning_rate, batch_size, num_passes, model_save_dir='model'):
test_accuracy.reset(exe)
for data in test_reader():
out, acc = exe.run(inference_program,
feed=feeder.feed(data),
fetch_list=[avg_cost] + test_accuracy.metrics)
loss, acc = exe.run(inference_program,
feed=feeder.feed(data),
fetch_list=[avg_cost] + test_accuracy.metrics)
test_pass_acc = test_accuracy.eval(exe)
print("End pass {0}, train_acc {1}, test_acc {2}".format(
pass_id, pass_acc, test_pass_acc))
......
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