keras2ncnn过程中的错误总结

1、getops使用，参见我的博客：

https://blog.csdn.net/weixin_41770169/article/details/85695457

 

2、不支持的层

(tensorflow) bash-3.2$ python /Users/xuqiong/PycharmProjects/keras2ncnn/Keras2NCNN.py -i /Users/xuqiong/PycharmProjects/keras2ncnn/ssrnet_3_3_3_64.h5

Traceback (most recent call last):

  File "/Users/xuqiong/PycharmProjects/keras2ncnn/Keras2NCNN.py", line 392, in <module>

    text_net, binary_weights = k2n_converter.convert()

  File "/Users/xuqiong/PycharmProjects/keras2ncnn/Keras2NCNN.py", line 370, in convert

    layer_ncnn_lst = self._dump_layer_weights(layer)

  File "/Users/xuqiong/PycharmProjects/keras2ncnn/Keras2NCNN.py", line 339, in _dump_layer_weights

    raise ValueError("non supported layer:{}".format(layer_name))

ValueError: non supported layer:t

猜测是h5文件中不含有结构，只有权重信息。因此，先将纯权值的模型改成结构+权值。

 

3、模型保存为：结构+权值

https://blog.csdn.net/weixin_41770169/article/details/85697281

https://blog.csdn.net/weixin_41770169/article/details/85705489

 

4、再次运行keras2ncnn

还是步骤2同样的问题，跟进去后发现，如下网址给的脚本有很多问题，由于项目第一周期时间紧，决定放弃直接从keras转ncnn。而是改成keras改成caffe，再转ncnn。

https://github.com/yanghanxy/Keras2NCNN