未验证 提交 537a0d4c 编写于 作者: C Coke 提交者: GitHub

Update infer.py

上级 f5dc9ead
......@@ -6,9 +6,13 @@ x = paddle.layer.data(name='x', type=paddle.data_type.dense_vector(2))
y_predict = paddle.layer.fc(input=x, size=1, act=paddle.activation.Linear())
# loading the model which generated by training
with open('hello_params_pass_90.tar', 'r') as f:
with open('params_pass_90.tar', 'r') as f:
parameters = paddle.parameters.Parameters.from_tar(f)
i = [[[1, 2]]]
# Input multiple sets of data,Output the infer result in a array.
i = [[[1, 2]], [[3, 4]], [[5, 6]]]
print paddle.infer(output_layer=y_predict, parameters=parameters, input=i)
# Will print:
# [[ -3.24491572]
# [ -6.94668722]
# [-10.64845848]]
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