|
板凳
楼主 |
发表于 2019-4-27 15:37:47
|
只看该作者
- rknn = RKNN()
- rknn.config(channel_mean_value='128 128 128 128', reorder_channel='0 1 2')
- rknn.load_tensorflow(tf_pb='./test.pb',
- inputs=['batch:0'],
- outputs=['conv1/bias_add'],
- input_size_list=[[1248, 384, 3]]
- )
我把层缩减到只到Conv1还是出现下面的错误,应该是之间有啥问题。
- UnsupportedOperation Traceback (most recent call last)
- <ipython-input-6-3d55b93dcd29> in <module>()
- 3
- 4 outputs=['conv1/bias_add'],
- ----> 5 input_size_list=[[1248, 384, 3]]
- 6 )
- /usr/local/lib/python3.5/dist-packages/rknn/api/rknn.py in load_tensorflow(self, tf_pb, inputs, input_size_list, outputs, predef_file, mean_values, std_values)
- 60 ret = self.rknn_base.load_tensorflow(tf_pb=tf_pb, inputs=inputs, input_size_list=input_size_list,
- 61 outputs=outputs, predef_file=predef_file, mean_values=mean_values,
- ---> 62 std_values=std_values)
- 63 return ret
- 64
- /usr/local/lib/python3.5/dist-packages/rknn/api/redirect_stdout.cpython-35m-x86_64-linux-gnu.so in rknn.api.redirect_stdout.redirect_stdouter.redirect_stdout.func_wrapper()
- /usr/lib/python3.5/contextlib.py in __enter__(self)
- 57 def __enter__(self):
- 58 try:
- ---> 59 return next(self.gen)
- 60 except StopIteration:
- 61 raise RuntimeError("generator didn't yield") from None
- /usr/local/lib/python3.5/dist-packages/rknn/api/redirect_stdout.cpython-35m-x86_64-linux-gnu.so in stdout_redirector()
- UnsupportedOperation: fileno
|
|