Created by: yajiezhu

paddle lite 报错 模型是bi-lstm-crf paddle lite模型 /home/zyj/anaconda3/bin/python3.6 /home/zyj/pythonProgram/PaddleNER/123.py Process finished with exit code 139 (interrupted by signal 11: SIGSEGV) from paddlelite.lite import * import numpy as np config = MobileConfig() config.set_model_from_file('./test.lite_inference.model/model.nb')

(2) 创建predictor

predictor = create_paddle_predictor(config)

(3) 从图片读入数据

image = Image.open('./example.jpg')

resized_image = image.resize((224, 224), Image.BILINEAR)

image_data = np.array(resized_image).flatten().tolist()

image_data = [1, 3, 9, 11, 0, 0, 0]

(4) 设置输入数据

input_tensor = predictor.get_input(0)

input_tensor.resize([1, 3, 224, 224])

input_tensor.set_float_data(image_data)

(5) 执行预测

predictor.run() print('ok')

(6) 得到输出数据

output_tensor = predictor.get_output(0) print(output_tensor)

print(output_tensor.shape())

print(output_tensor.float_data()[:10])