Hello,
I’m trying to run the lstm test, but i’m getting an error when calling build in line 85
.
.
net , params = relay.testing.lstm.get_workload(
iterations = iter, num_hidden =hn)
target = tvm.target.cuda()
84 graph, lib, params = relay.build_module.build(
85 net, target, params=params)
Traceback (most recent call last):
File “./lstm_run.py”, line 85, in
net, target, params=params)
File “/afs/csail.mit.edu/u/g/guerdouji_amal/.local/lib/python2.7/site-packages/tvm-0.6.dev0-py2.7-linux-x86_64.egg/tvm/relay/build_module.py”, line 287, in build
graph_json, lowered_funcs, params = graph_gen.codegen(func)
File “/afs/csail.mit.edu/u/g/guerdouji_amal/.local/lib/python2.7/site-packages/tvm-0.6.dev0-py2.7-linux-x86_64.egg/tvm/relay/backend/graph_runtime_codegen.py”, line 419, in codegen
self.storage_device_map = _backend.GraphPlanMemory(func)
File “tvm/_ffi/_cython/./function.pxi”, line 286, in core.FunctionBase.call
File “tvm/_ffi/_cython/./function.pxi”, line 221, in core.FuncCall
File “tvm/_ffi/_cython/./function.pxi”, line 210, in core.FuncCall3
File “tvm/_ffi/_cython/./base.pxi”, line 151, in core.CALL
tvm._ffi.base.TVMError: [18:35:58] /afs/csail.mit.edu/u/g/guerdouji_amal/tvm/src/relay/backend/graph_plan_memory.cc:138: Check failed: ttype
Do you have any idea from where it comes ?