Created by: ghimiredhikura

Hi,

1. I am using https://github.com/PaddlePaddle/X2Paddle for converting caffe models with this command:

x2paddle --framework=caffe --prototxt=deploy.prototxt --weight=deploy.caffemodel --save_dir=pd_model

2. Now in order to get __model__.nb param.nb files, I used model_optimize_tool from https://paddlepaddle.github.io/Paddle-Lite/v2.0.0/model_optimize_tool/. I was expecting __model__.nb param.nb files but got model params files without extension .np.

3. But still tried to run the demo replacing mobilenet __model__nb and param.nb. file in [https://github.com/PaddlePaddle/Paddle-Lite-Demo/tree/master/PaddleLite-armlinux-demo/image_classification_demo/models/mobilenet_v1_for_cpu] with newly generated model params file. This is the error message returned with command bash run.sh armv7hf:

run.sh: line 19:  1273 Segmentation fault      LD_LIBRARY_PATH=$LD_LIBRARY_PATH:${PADDLE_LITE_DIR}/libs/${TARGET_ARCH_ABI} ./image_classification_demo ../models/mobilenet_v1_for_cpu ../labels/synset_words.txt ../images/tabby_cat.jpg ./result.jpg

[Note: Target device is RaspberryPi4B+. ]

Any help will be greatly appreciated.

Thanks.

Best, Deepak