CoinCheung commented on issue #4566: [Relay/Topi][Op] Added native DepthToSpace and SpaceToDepth Operators URL: https://github.com/apache/incubator-tvm/pull/4566#issuecomment-576125748 Hi, Does tvm fully support the op of depth_to_space now ? I got the error message in my code that I do not know whether it is associated with this operator: ``` Traceback (most recent call last): File "run_onnx.py", line 88, in <module> graph, lib, params = compile_model() File "run_onnx.py", line 53, in compile_model mod, params = relay.frontend.from_onnx(model, shape_dict, dtype='float32', opset=11) File "/root/build/tvm/python/tvm/relay/frontend/onnx.py", line 1586, in from_onnx mod, params = g.from_onnx(graph, opset) File "/root/build/tvm/python/tvm/relay/frontend/onnx.py", line 1414, in from_onnx op = self._convert_operator(op_name, inputs, attr, opset) File "/root/build/tvm/python/tvm/relay/frontend/onnx.py", line 1514, in _convert_operator sym = convert_map[op_name](inputs, attrs, self._params) File "/root/build/tvm/python/tvm/relay/frontend/onnx.py", line 574, in _impl_v11 return _op.nn.depth_to_space(inputs[0], block_size, mode=mode) File "/root/build/tvm/python/tvm/relay/op/nn/nn.py", line 2374, in depth_to_space return _make.depth_to_space(data, block_size, layout, mode) File "tvm/_ffi/_cython/./function.pxi", line 304, in tvm._ffi._cy3.core.FunctionBase.__call__ File "tvm/_ffi/_cython/./function.pxi", line 248, in tvm._ffi._cy3.core.FuncCall File "tvm/_ffi/_cython/./function.pxi", line 172, in tvm._ffi._cy3.core.make_arg TypeError: Don't know how to handle type <class 'bytes'> ```
---------------------------------------------------------------- This is an automated message from the Apache Git Service. To respond to the message, please log on to GitHub and use the URL above to go to the specific comment. For queries about this service, please contact Infrastructure at: [email protected] With regards, Apache Git Services
