1、getops使用，參見我的部落格：

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

2、不支援的層

(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

猜測是h5檔案中不含有結構，只有權重資訊。因此，先將純權值的模型改成結構+權值。

3、模型儲存為：結構+權值

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

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

4、再次執行keras2ncnn

還是步驟2同樣的問題，跟進去後發現，如下網址給的指令碼有很多問題，由於專案第一週期時間緊，決定放棄直接從keras轉ncnn。而是改成keras改成caffe，再轉ncnn。

https://github.com/yanghanxy/Keras2NCNN