You are viewing a plain text version of this content. The canonical link for it is here.
Posted to commits@tvm.apache.org by "jikechao (via GitHub)" <gi...@apache.org> on 2023/04/29 16:10:43 UTC
[GitHub] [tvm] jikechao opened a new issue, #14745: [Bug][Relay] infer_idx <0 lead to wrong type inferrence
jikechao opened a new issue, #14745:
URL: https://github.com/apache/tvm/issues/14745
For the reshape operator, `target_shape=(1, -1)` is supported. However, in the `InferType`, It crashed and threw `Check failed: infer_idx < 0 (0 vs. 0) : One and only one dim can be inferred`.
Shall we add extra checking to check the dimension of `target_shape` or support inferrence for more than one dims?
### Actual behavior
```
model = relay.build_module.create_executor("vm", mod, tvm.cpu(0), 'llvm', params).evaluate()
File "/workplace/software/tvm/tvm_/python/tvm/relay/backend/interpreter.py", line 171, in evaluate
return self._make_executor()
File "/workplace/software/tvm/tvm_/python/tvm/relay/backend/vm.py", line 219, in _make_executor
self.executable = compile(self.mod, self.target)
File "/workplace/software/tvm/tvm_/python/tvm/relay/backend/vm.py", line 67, in compile
compiler.lower(mod, target, target_host)
File "/workplace/software/tvm/tvm_/python/tvm/relay/backend/vm.py", line 126, in lower
self._lower(mod, raw_targets)
File "/workplace/software/tvm/tvm_/python/tvm/_ffi/_ctypes/packed_func.py", line 237, in __call__
raise get_last_ffi_error()
tvm._ffi.base.TVMError: Traceback (most recent call last):
15: TVMFuncCall
14: tvm::runtime::PackedFuncObj::Extractor<tvm::runtime::PackedFuncSubObj<tvm::relay::vm::VMCompiler::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, tvm::runtime::ObjectPtr<tvm::runtime::Object> const&)::$_0> >::Call(tvm::runtime::PackedFuncObj const*, tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)
13: tvm::relay::vm::VMCompiler::Lower(tvm::IRModule, tvm::runtime::Array<tvm::Target, void> const&)
12: tvm::relay::vm::VMCompiler::LowerImpl(tvm::IRModule)
11: tvm::relay::vm::VMCompiler::OptimizeModuleImpl(tvm::IRModule)
10: tvm::transform::Pass::operator()(tvm::IRModule) const
9: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
8: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
7: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
6: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
5: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
4: tvm::transform::ModulePassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
3: tvm::runtime::PackedFuncObj::Extractor<tvm::runtime::PackedFuncSubObj<tvm::runtime::TypedPackedFunc<tvm::IRModule (tvm::IRModule, tvm::transform::PassContext)>::AssignTypedLambda<tvm::relay::transform::InferType()::$_2>(tvm::relay::transform::InferType()::$_2)::{lambda(tvm::runtime::TVMArgs const&, tvm::runtime::TVMRetValue*)#1}> >::Call(tvm::runtime::PackedFuncObj const*, tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)
2: tvm::relay::TypeInferencer::Infer(tvm::GlobalVar, tvm::relay::Function)
1: tvm::relay::TypeSolver::Solve()
0: _ZN3tvm7runtime6detail
20: TVMFuncCall
19: tvm::runtime::PackedFuncObj::Extractor<tvm::runtime::PackedFuncSubObj<tvm::relay::vm::VMCompiler::GetFunction(std::__cxx11::basic_string<char, std::char_traits<char>, std::allocator<char> > const&, tvm::runtime::ObjectPtr<tvm::runtime::Object> const&)::$_0> >::Call(tvm::runtime::PackedFuncObj const*, tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)
18: tvm::relay::vm::VMCompiler::Lower(tvm::IRModule, tvm::runtime::Array<tvm::Target, void> const&)
17: tvm::relay::vm::VMCompiler::LowerImpl(tvm::IRModule)
16: tvm::relay::vm::VMCompiler::OptimizeModuleImpl(tvm::IRModule)
15: tvm::transform::Pass::operator()(tvm::IRModule) const
14: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
13: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
12: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
11: tvm::transform::SequentialNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
10: tvm::transform::Pass::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
9: tvm::transform::ModulePassNode::operator()(tvm::IRModule, tvm::transform::PassContext const&) const
8: tvm::runtime::PackedFuncObj::Extractor<tvm::runtime::PackedFuncSubObj<tvm::runtime::TypedPackedFunc<tvm::IRModule (tvm::IRModule, tvm::transform::PassContext)>::AssignTypedLambda<tvm::relay::transform::InferType()::$_2>(tvm::relay::transform::InferType()::$_2)::{lambda(tvm::runtime::TVMArgs const&, tvm::runtime::TVMRetValue*)#1}> >::Call(tvm::runtime::PackedFuncObj const*, tvm::runtime::TVMArgs, tvm::runtime::TVMRetValue*)
7: tvm::relay::TypeInferencer::Infer(tvm::GlobalVar, tvm::relay::Function)
6: tvm::relay::TypeSolver::Solve()
5: tvm::TypedEnvFunc<bool (tvm::runtime::Array<tvm::Type, void> const&, int, tvm::Attrs const&, tvm::TypeReporter const&)>::operator()(tvm::runtime::Array<tvm::Type, void> const&, int, tvm::Attrs const&, tvm::TypeReporter const&) const
4: _ZN3tvm7runtime13Pac
3: tvm::runtime::TypedPackedFunc<bool (tvm::runtime::Array<tvm::Type, void> const&, int, tvm::Attrs const&, tvm::TypeReporter const&)>::AssignTypedLambda<bool (*)(tvm::runtime::Array<tvm::Type, void> const&, int, tvm::Attrs const&, tvm::TypeReporter const&)>(bool (*)(tvm::runtime::Array<tvm::Type, void> const&, int, tvm::Attrs const&, tvm::TypeReporter const&))::{lambda(tvm::runtime::TVMArgs const&, tvm::runtime::TVMRetValue*)#1}::operator()(tvm::runtime::TVMArgs const&, tvm::runtime::TVMRetValue*) const
2: tvm::relay::ReshapeRel(tvm::runtime::Array<tvm::Type, void> const&, int, tvm::Attrs const&, tvm::TypeReporter const&)
1: tvm::relay::InferNewShape(tvm::runtime::Array<tvm::PrimExpr, void> const&, tvm::Attrs const&, bool)
0: _ZN3tvm7runtime6detail
File "/workplace/software/tvm/tvm_/src/relay/analysis/type_solver.cc", line 643
TVMError:
---------------------------------------------------------------
An error occurred during the execution of TVM.
For more information, please see: https://tvm.apache.org/docs/errors.html
---------------------------------------------------------------
Check failed: (false) is false: [15:36:43] /workplace/software/tvm/tvm_/src/relay/op/tensor/transform.cc:651:
---------------------------------------------------------------
An error occurred during the execution of TVM.
For more information, please see: https://tvm.apache.org/docs/errors.html
---------------------------------------------------------------
Check failed: infer_idx < 0 (0 vs. 0) : One and only one dim can be inferred
```
### Expected behavior
### Reproducable example
```
import tvm
import tvm.relay as relay
from tensorflow import keras
from tensorflow.keras import layers, models
input_shape = (3, 2, 4)
x = layers.Input(shape=input_shape[1:], dtype='float32')
layer = keras.layers.Reshape(target_shape=(1, -1))
layer.set_weights(layer.get_weights())
y = layer(x)
model = models.Model(x, y)
mod, params = relay.frontend.from_keras(model, {'input_1': input_shape})
print(mod)
with tvm.transform.PassContext(opt_level=3):
model = relay.build_module.create_executor("vm", mod, tvm.cpu(0), 'llvm', params).evaluate() # crash
```
Triage
* relay
--
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.
To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [tvm] n-moussa commented on issue #14745: [Bug][Relay] infer_idx <0 lead to wrong type inferrence
Posted by "n-moussa (via GitHub)" <gi...@apache.org>.
n-moussa commented on issue #14745:
URL: https://github.com/apache/tvm/issues/14745#issuecomment-1663602711
Hi, I'm getting the same issue, is there a potential workaround ?
Thanks
--
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.
To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
Re: [I] [Bug][Relay] infer_idx <0 lead to wrong type inferrence [tvm]
Posted by "tqchen (via GitHub)" <gi...@apache.org>.
tqchen closed issue #14745: [Bug][Relay] infer_idx <0 lead to wrong type inferrence
URL: https://github.com/apache/tvm/issues/14745
--
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.
To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org
[GitHub] [tvm] jikechao commented on issue #14745: [Bug][Relay] infer_idx <0 lead to wrong type inferrence
Posted by "jikechao (via GitHub)" <gi...@apache.org>.
jikechao commented on issue #14745:
URL: https://github.com/apache/tvm/issues/14745#issuecomment-1664869921
@n-moussa. You can change the dynamic target_shape value (e.g., '-1') to static in the Reshape layer of the DL model. This is a workaround to avoid such bug.
--
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.
To unsubscribe, e-mail: commits-unsubscribe@tvm.apache.org
For queries about this service, please contact Infrastructure at:
users@infra.apache.org