请韩佬有空帮我瞅瞅这两个OP，SeparableConv2D 和 BilinearUpsampling

[xiongzhu666]

环境：tf2.1，keras2.3 from tensorflow.keras.models import load_model model = load_model("./SOD.h5", custom_objects={'BilinearUpsampling': BilinearUpsampling}, compile=False) 运行预测没有问题。

使用你的仓库，在转换过程中遇到问题： [ERROR] Operator SeparableConv2D not support. 使用另外一个老哥的仓库（https://github.com/azeme1/keras2ncnn）遇到问题： ValueError: Unknown layer: BilinearUpsampling

附上模型文件 SOD.zip

[MarsTechHAN]

SeparableConv2D is support now, but seems like there is other op not supported yet.

[ERROR] Operator Cropping2D not support.
=========================================
{'name': 'cropping2d_1', 'trainable': True, 'dtype': 'float32', 'cropping': [[1, 0], [1, 0]], 'data_format': 'channels_last'}
=========================================

[MarsTechHAN]

Fixed 27cc153b8b79d2b4c8097eb959851bf465a6d4f2