fanwei-china removed a comment on issue #6931: URL: https://github.com/apache/incubator-tvm/issues/6931#issuecomment-728787606
> ``` > Hi, I was trying to import bert model by tensorflow relay. When converting the StrideSlice op, an error occurred. Could someone help me to solve this? The code is as follow: > ``` > > Traceback (most recent call last): > File "tutorials/frontend/test_nlp.py", line 109, in > shape=shape_dict) > File "/root/.local/lib/python3.6/site-packages/tvm-0.7.dev1-py3.6-linux-x86_64.egg/tvm/relay/frontend/tensorflow.py", line 2742, in from_tensorflow > mod, params = g.from_tensorflow(graph, layout, shape, outputs) > File "/root/.local/lib/python3.6/site-packages/tvm-0.7.dev1-py3.6-linux-x86_64.egg/tvm/relay/frontend/tensorflow.py", line 2372, in from_tensorflow > op = self._convert_operator(node.op, inputs, attr, graph) > File "/root/.local/lib/python3.6/site-packages/tvm-0.7.dev1-py3.6-linux-x86_64.egg/tvm/relay/frontend/tensorflow.py", line 2702, in _convert_operator > sym = convert_map[op_name](inputs, attrs, self._params, self._mod) > File "/root/.local/lib/python3.6/site-packages/tvm-0.7.dev1-py3.6-linux-x86_64.egg/tvm/relay/frontend/tensorflow.py", line 1145, in _impl > out_shape = _infer_shape(out, mod=mod) > File "/root/.local/lib/python3.6/site-packages/tvm-0.7.dev1-py3.6-linux-x86_64.egg/tvm/relay/frontend/common.py", line 478, in infer_shape > out_type = infer_type(inputs, mod=mod) > File "/root/.local/lib/python3.6/site-packages/tvm-0.7.dev1-py3.6-linux-x86_64.egg/tvm/relay/frontend/common.py", line 470, in infer_type > new_mod = IRModule.from_expr(node) > File "/root/.local/lib/python3.6/site-packages/tvm-0.7.dev1-py3.6-linux-x86_64.egg/tvm/ir/module.py", line 226, in from_expr > return _ffi_api.Module_FromExpr(expr, funcs, defs) > File "/root/.local/lib/python3.6/site-packages/tvm-0.7.dev1-py3.6-linux-x86_64.egg/tvm/_ffi/_ctypes/packed_func.py", line 213, in **call** > raise get_last_ffi_error() ---------------------------------------------------------------- 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: us...@infra.apache.org