Posted here:
https://github.com/apache/incubator-tvm/issues/6404 Using the following script: https://raw.githubusercontent.com/apache/incubator-tvm/v0.6/tutorials/autotvm/tune_relay_x86.py ``` 2020-09-07 10:11:32,985 INFO Benchmarking layout transformation successful. 2020-09-07 10:11:33,053 INFO Start to run PBQP algorithm... 2020-09-07 10:11:33,399 INFO Finished PBQPExecutor run. Got sub-optimal solution. 2020-09-07 10:11:33,404 INFO Writing optimal schedules to mxnet_graph_opt.log successfully. Compile... Traceback (most recent call last): File "convert.py", line 238, in <module> tune_and_evaluate(tuning_option) File "convert.py", line 211, in tune_and_evaluate graph, lib, params = relay.build_module.build(mod, target=target, params=params) File "/home/xyz/Desktop/tvm/tvm_0.6.1/python/tvm/relay/build_module.py", line 244, in build graph_json, mod, params = bld_mod.build(func, target, target_host, params) File "/home/xyz/Desktop/tvm/tvm_0.6.1/python/tvm/relay/build_module.py", line 109, in build self._build(func, target, target_host) File "/home/xyz/Desktop/tvm/tvm_0.6.1/python/tvm/_ffi/_ctypes/function.py", line 207, in __call__ raise get_last_ffi_error() tvm._ffi.base.TVMError: Traceback (most recent call last): [bt] (8) /home/xyz/Desktop/tvm/tvm_0.6.1/build/libtvm.so(tvm::relay::backend::GraphRuntimeCodegen::VisitExpr(tvm::relay::Expr const&)+0x4c5) [0x7f4f10e71b95] [bt] (7) /home/xyz/Desktop/tvm/tvm_0.6.1/build/libtvm.so(tvm::relay::backend::GraphRuntimeCodegen::VisitExpr_(tvm::relay::CallNode const*)+0x703) [0x7f4f10e730b3] [bt] (6) /home/xyz/Desktop/tvm/tvm_0.6.1/build/libtvm.so(tvm::relay::backend::GraphRuntimeCodegen::VisitExpr(tvm::relay::Expr const&)+0x4c5) [0x7f4f10e71b95] [bt] (5) /home/xyz/Desktop/tvm/tvm_0.6.1/build/libtvm.so(tvm::relay::backend::GraphRuntimeCodegen::VisitExpr_(tvm::relay::CallNode const*)+0x533) [0x7f4f10e72ee3] [bt] (4) /home/xyz/Desktop/tvm/tvm_0.6.1/build/libtvm.so(+0x104dda6) [0x7f4f10e4eda6] [bt] (3) /home/xyz/Desktop/tvm/tvm_0.6.1/build/libtvm.so(tvm::relay::CompileEngineImpl::Lower(tvm::relay::CCacheKey const&)+0x10) [0x7f4f10e5b620] [bt] (2) /home/xyz/Desktop/tvm/tvm_0.6.1/build/libtvm.so(tvm::relay::CompileEngineImpl::LowerInternal(tvm::relay::CCacheKey const&)+0x352) [0x7f4f10e5aa72] [bt] (1) /home/xyz/Desktop/tvm/tvm_0.6.1/build/libtvm.so(tvm::relay::ScheduleGetter::Create(tvm::relay::Function const&)+0xad9) [0x7f4f10e57709] [bt] (0) /home/xyz/Desktop/tvm/tvm_0.6.1/build/libtvm.so(+0x11a5b63) [0x7f4f10fa6b63] File "/home/xyz/Desktop/tvm/tvm_0.6.1/python/tvm/_ffi/_ctypes/function.py", line 72, in cfun rv = local_pyfunc(*pyargs) File "/home/xyz/Desktop/tvm/tvm_0.6.1/python/tvm/relay/op/nn/_nn.py", line 584, in schedule_contrib_conv2d_NCHWc return topi.generic.schedule_conv2d_NCHWc(outs) File "<decorator-gen-77>", line 2, in schedule_conv2d_NCHWc File "/home/xyz/Desktop/tvm/tvm_0.6.1/python/tvm/target.py", line 382, in dispatch_func return dispatch_dict[k](*args, **kwargs) File "<decorator-gen-125>", line 2, in config_dispatcher File "/home/xyz/Desktop/tvm/tvm_0.6.1/python/tvm/autotvm/task/dispatcher.py", line 221, in dispatch_func return dispatch_dict[cfg.template_key](cfg, *args, **kwargs) File "/home/xyz/Desktop/tvm/tvm_0.6.1/python/tvm/autotvm/task/topi_integration.py", line 487, in template_call return f(cfg, outs, *args, **kwargs) File "/home/xyz/Desktop/tvm/tvm_0.6.1/topi/python/topi/x86/conv2d.py", line 431, in _schedule_conv2d_NCHWc traverse(outs[0].op) File "/home/xyz/Desktop/tvm/tvm_0.6.1/topi/python/topi/x86/conv2d.py", line 408, in traverse traverse(tensor.op) File "/home/xyz/Desktop/tvm/tvm_0.6.1/topi/python/topi/x86/conv2d.py", line 408, in traverse traverse(tensor.op) File "/home/xyz/Desktop/tvm/tvm_0.6.1/topi/python/topi/x86/conv2d.py", line 408, in traverse traverse(tensor.op) File "/home/xyz/Desktop/tvm/tvm_0.6.1/topi/python/topi/x86/conv2d.py", line 427, in traverse conv2d_avx_common._schedule_conv_NCHWc(*args) File "/home/xyz/Desktop/tvm/tvm_0.6.1/topi/python/topi/x86/conv2d_avx_common.py", line 159, in _schedule_conv_NCHWc reg_n, unroll_kw = cfg["tile_ow"].size[-1], cfg["unroll_kw"].val File "/home/xyz/Desktop/tvm/tvm_0.6.1/python/tvm/autotvm/task/space.py", line 808, in __getitem__ return self._entity_map[name] KeyError: 'unroll_kw' ``` --- [Visit Topic](https://discuss.tvm.apache.org/t/keyerror-unroll-kw-while-auto-tuning/7828/1) to respond. You are receiving this because you enabled mailing list mode. To unsubscribe from these emails, [click here](https://discuss.tvm.apache.org/email/unsubscribe/dd354c4f6f189de7633e6b70702e2527947060f1f29ebe25d849226b04b25abe).
