protossw512 发表于 2019-4-27 08:14
贴下你的log?
rknn不是所有的tf operation都支持的,Unsupported Operation就是告诉你哪个op在你的pb里面 ...
- 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]]
- )
复制代码
- 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
复制代码
zhangzj 发表于 2019-4-28 08:42
不像是op不支持的报错,你把verbose打开,详细过程信息发出来看看
- D save dump info to: ./test.log
- D import clients finished
- E Catch exception when loading tensorflow model: ./test.pb!
- T Traceback (most recent call last):
- T File "rknn/api/rknn_base.py", line 132, in rknn.api.rknn_base.RKNNBase.load_tensorflow
- T File "rknn/base/RKNNlib/converter/convert_tf.py", line 95, in rknn.base.RKNNlib.converter.convert_tf.convert_tf.__init__
- T File "rknn/base/RKNNlib/converter/tensorflowloader.py", line 52, in rknn.base.RKNNlib.converter.tensorflowloader.TF_Graph_Preprocess.__init__
- T File "rknn/base/RKNNlib/converter/tensor_util.py", line 6, in rknn.base.RKNNlib.converter.tensor_util.TensorLabelOperator.tensor_label_split
- T ValueError: too many values to unpack (expected 2)
复制代码
- D Try match BiasAdd conv1/bias_add
- I Match convolution_biasadd [['conv1/bias_add', 'conv1/biases', 'conv1/convolution', 'conv1/kernels']] [['BiasAdd', 'Conv', 'C', 'C_1']] to [['convolution']]
- D Try match QueueDequeueManyV2 batch
- W Not match node batch QueueDequeueManyV2
- E Catch exception when loading tensorflow model: ./test.pb!
- T Traceback (most recent call last):
- T File "rknn/api/rknn_base.py", line 180, in rknn.api.rknn_base.RKNNBase.load_tensorflow
- T File "rknn/base/RKNNlib/converter/convert_tf.py", line 565, in rknn.base.RKNNlib.converter.convert_tf.convert_tf.match_paragraph_and_param
- T File "rknn/base/RKNNlib/converter/convert_tf.py", line 464, in rknn.base.RKNNlib.converter.convert_tf.convert_tf._tf_push_ready_node
- T TypeError: 'NoneType' object is not iterable
复制代码
欢迎光临 Toybrick (https://t.rock-chips.com/) | Powered by Discuz! X3.3 |