system info:
cpu:J1900 x86_64
install tvm with LLVM 8.0
mxnet==1.5.0
gluoncv==0.4.0
detailed description:
I am new in tvm, and I install tvm followed install doc.It’s installed fine.When I run this code https://docs.tvm.ai/tutorials/frontend/deploy_ssd_gluoncv.html#deploy-single-shot-multibox-detector-ssd-model,I got a error as follow：
mxnet/python/mxnet/gluon/block.py:1146: UserWarning: Cannot decide type for the following arguments. Consider providing them as input:
data: None
input_sym_arg_type = in_param.infer_type()[0]
[18:29:12] /home/yt/AIbox/tvm/src/schedule/bound.cc:110: not in feed graph consumer = hybrid(hybrid_nms, 0x574aa00)
[18:29:12] /home/yt/AIbox/tvm/src/arithmetic/int_set.cc:540: cannot evaluate set type Load
[18:29:12] /home/yt/AIbox/tvm/src/arithmetic/int_set.cc:540: cannot evaluate set type Load
[18:29:12] /home/yt/AIbox/tvm/src/schedule/bound.cc:110: not in feed graph consumer = hybrid(hybrid_nms, 0x574aa00)
[18:29:12] /home/yt/AIbox/tvm/src/arithmetic/int_set.cc:540: cannot evaluate set type Load
[18:29:12] /home/yt/AIbox/tvm/src/arithmetic/int_set.cc:540: cannot evaluate set type Load
Traceback (most recent call last):
File “deploy_ssd_gluoncv.py”, line 95, in
class_IDs, scores, bounding_boxs = run(graph, lib, params, ctx)
File “deploy_ssd_gluoncv.py”, line 85, in run
m.run()
File “/home/yt/AIbox/tvm/python/tvm/contrib/graph_runtime.py”, line 151, in run
self._run()
File “/home/yt/AIbox/tvm/python/tvm/_ffi/_ctypes/function.py”, line 190, in call
raise get_last_ffi_error()
tvm._ffi.base.TVMError: Traceback (most recent call last):
[bt] (8) /home/yt/AIbox/tvm/build/libtvm.so(TVMFuncCall+0x61) [0x7f3dbcd5e511]
[bt] (7) /home/yt/AIbox/tvm/build/libtvm.so(+0xd0e8f7) [0x7f3dbcdaa8f7]
[bt] (6) /home/yt/AIbox/tvm/build/libtvm.so(+0xd10597) [0x7f3dbcdac597]
[bt] (5) /home/yt/AIbox/tvm/build/libtvm.so(+0xcc6681) [0x7f3dbcd62681]
[bt] (4) [0x7f3d74c06f7b]
[bt] (3) [0x7f3d74c0762a]
[bt] (2) /home/yt/AIbox/tvm/build/libtvm.so(TVMBackendGetFuncFromEnv+0x60) [0x7f3dbcd5e420]
[bt] (1) /home/yt/AIbox/tvm/build/libtvm.so(tvm::runtime::ModuleNode::GetFuncFromEnv(std::_cxx11::basic_string<char, std::char_traits, std::allocator > const&)+0x321) [0x7f3dbcd587d1]
[bt] (0) /home/yt/AIbox/tvm/build/libtvm.so(+0x538de2) [0x7f3dbc5d4de2]
File “/home/yt/AIbox/tvm/src/runtime/module.cc”, line 92
File “/home/yt/AIbox/tvm/src/runtime/module_util.cc”, line 54
TVMError: Check failed: ret == 0 (-1 vs. 0) : Check failed: f != nullptr: Cannot find function tvm.contrib.sort.argsort in the imported modules or global registry
terminate called after throwing an instance of ‘dmlc::Error’
what(): [18:30:17] /home/yt/AIbox/tvm/src/runtime/workspace_pool.cc:97: Check failed: allocated.size() == 1 (4 vs. 1) :
it will be thanks for any reply!