Hi, guys, i built the tvm 0.6.1 and build the python bind successfully, i was folllowing this (https://gist.github.com/icemelon9/860d3d2c9566d6f69fa8112840dd95c1) to do a bert inference. However, i got this problem:
(tvm) [qizhouhuang@GPU-10-252-192-90 apache-tvm-src-v0.6.1.rc1-incubating]$ python3 test_bert.py MXNet latency for batch 1 and seq length 128: 114.93 ms Traceback (most recent call last):
File “test_bert.py”, line 86, in mod, params = relay.frontend.from_mxnet(model, shape_dict)
File “/opt/cephfs1/asr/users/qizhou.huang/.local/lib/python3.6/site-packages/tvm-0.6.0-py3.6-linux-x86_64.egg/tvm/relay/frontend/mxnet.py”, line 1427, in from_mxnet func = _from_mxnet_impl(sym, shape, dtype, mod)
File “/opt/cephfs1/asr/users/qizhou.huang/.local/lib/python3.6/site-packages/tvm-0.6.0-py3.6-linux-x86_64.egg/tvm/relay/frontend/mxnet.py”, line 1340, in _from_mxnet_impl ‘Operator {} is not supported in frontend MXNet.’.format(op_name))
tvm.error.OpNotImplemented: Operator _contrib_arange_like is not supported in frontend MXNet.
I installed my mxnet using pip install mxnet, it seems the one got installed’s Collecting mxnet Using cached mxnet-1.6.0-py2.py3-none-any.whl (68.7 MB)
could u please help me out,thank you.