未验证 提交 1aef8141 编写于 作者: H huzhiqiang 提交者: GitHub

[Doc]Update python doc #3932

上级 d341fccb
...@@ -86,19 +86,28 @@ config.set_model_from_file(/YOU_MODEL_PATH/mobilenet_v1_opt.nb) ...@@ -86,19 +86,28 @@ config.set_model_from_file(/YOU_MODEL_PATH/mobilenet_v1_opt.nb)
predictor = create_paddle_predictor(config) predictor = create_paddle_predictor(config)
``` ```
(3) 设置输入数据 (3) 从图片读入数据
```python
image = Image.open('./example.jpg')
resized_image = image.resize((224, 224), Image.BILINEAR)
image_data = np.array(resized_image).flatten().tolist()
```
(4) 设置输入数据
```python ```python
input_tensor = predictor.get_input(0) input_tensor = predictor.get_input(0)
input_tensor.resize([1, 3, 224, 224]) input_tensor.resize([1, 3, 224, 224])
input_tensor.set_float_data([1.] * 3 * 224 * 224) input_tensor.set_float_data(image_data)
``` ```
(4) 执行预测 (5) 执行预测
```python ```python
predictor.run() predictor.run()
``` ```
(5) 得到输出数据 (6) 得到输出数据
```python ```python
output_tensor = predictor.get_output(0) output_tensor = predictor.get_output(0)
print(output_tensor.shape()) print(output_tensor.shape())
......
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