Skip to contents

Context-manager that enable anomaly detection for the autograd engine.

Source: R/autograd.R
with_detect_anomaly.Rd

This does two things:

Usage

with_detect_anomaly(code)

Arguments

code

Code that will be executed in the detect anomaly context.

Details

  • Running the forward pass with detection enabled will allow the backward pass to print the traceback of the forward operation that created the failing backward function.

  • Any backward computation that generate "nan" value will raise an error.

Warning

This mode should be enabled only for debugging as the different tests will slow down your program execution.

Examples

if (torch_is_installed()) {
x <- torch_randn(2, requires_grad = TRUE)
y <- torch_randn(1)
b <- (x^y)$sum()
y$add_(1)

try({
  b$backward()

  with_detect_anomaly({
    b$backward()
  })
})
}
#> Error in (function (self, inputs, gradient, retain_graph, create_graph)  : 
#>   one of the variables needed for gradient computation has been modified by an inplace operation: [CPUFloatType [1]] is at version 1; expected version 0 instead. Hint: enable anomaly detection to find the operation that failed to compute its gradient, with torch.autograd.set_detect_anomaly(True).
#> Exception raised from unpack at /Users/runner/work/pytorch/pytorch/pytorch/torch/csrc/autograd/saved_variable.cpp:194 (most recent call first):
#> frame #0: c10::Error::Error(c10::SourceLocation, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>>) + 81 (0x103c8fca1 in libc10.dylib)
#> frame #1: c10::detail::torchCheckFail(char const*, char const*, unsigned int, std::__1::basic_string<char, std::__1::char_traits<char>, std::__1::allocator<char>> const&) + 98 (0x103c8e342 in libc10.dylib)
#> frame #2: torch::autograd::SavedVariable::unpack(std::__1::shared_ptr<torch::autograd::Node>) const + 2815 (0x124c92d0f in libtorch_cpu.dylib)
#> frame #3: torch::autograd::generated::PowBackward1::apply(std::__1::vector<at::Tensor, std::__1::allocator<at::Tensor>>&&) + 168 (0x123de5488 in libtorch_cpu.dylib)
#> frame #4: torch::autograd::Node::operator()(std::__1::vector<at::Tensor, std::__1::allocator<at::Tensor>>&&) + 99 (0x124c636c3 in libtorch_cpu.dylib)
#> frame #5: torch::autograd::Engine::evaluate_function(std::__1::shared_ptr<torch::autograd::GraphTask>&, torch::autograd::Node*, torch::autograd::InputBuffer&, std::__1::shared_ptr<torch::autograd::ReadyQueue> const&) + 3401 (0x124c59a89 in libtorch_cpu.dylib)
#> frame #6: torch::autograd::Engine::thread_main(std::__1::shared_ptr<torch::autograd::GraphTask> const&) + 954 (0x124c586da in libtorch_cpu.dylib)
#> frame #7: torch::autograd::Engine::execute_with_graph_task(std::__1::shared_ptr<torch::autograd::GraphTask> const&, std::__1::shared_ptr<torch::autograd::Node>, torch::autograd::InputBuffer&&) + 374 (0x124c62646 in libtorch_cpu.dylib)
#> frame #8: torch::autograd::Engine::execute(std::__1::vector<torch::autograd::Edge, std::__1::allocator<torch::autograd::Edge>> const&, std::__1::vector<at::Tensor, std::__1::allocator<at::Tensor>> const&, bool, bool, bool, std::__1::vector<torch::autograd::Edge, std::__1::allocator<torch::autograd::Edge>> const&) + 2605 (0x124c6068d in libtorch_cpu.dylib)
#> frame #9: torch::autograd::run_backward(std::__1::vector<at::Tensor, std::__1::allocator<at::Tensor>> const&, std::__1::vector<at::Tensor, std::__1::allocator<at::Tensor>> const&, bool, bool, std::__1::vector<at::Tensor, std::__1::allocator<at::Tensor>> const&, bool, bool) + 2129 (0x124c46df1 in libtorch_cpu.dylib)
#> frame #10: torch::autograd::backward(std::__1::vector<at::Tensor, std::__1::allocator<at::Tensor>> const&, std::__1::vector<at::Tensor, std::__1::allocator<at::Tensor>> const&, c10::optional<bool>, bool, std::__1::vector<at::Tensor, std::__1::allocator<at::Tensor>> const&) + 104 (0x124c47408 in libtorch_cpu.dylib)
#> frame #11: torch::autograd::VariableHooks::_backward(at::Tensor const&, c10::ArrayRef<at::Tensor>, c10::optional<at::Tensor> const&, c10::optional<bool>, bool) const + 435 (0x124c989f3 in libtorch_cpu.dylib)
#> frame #12: at::Tensor::_backward(c10::ArrayRef<at::Tensor>, c10::optional<at::Tensor> const&, c10::optional<bool>, bool) const + 75 (0x1215d9eab in libtorch_cpu.dylib)
#> frame #13: _lantern_Tensor__backward_tensor_tensorlist_tensor_bool_bool + 427 (0x106fc1b2b in liblantern.dylib)
#> frame #14: std::__1::__function::__func<cpp_torch_method__backward_self_Tensor_inputs_TensorList(XPtrTorchTensor, XPtrTorchTensorList, XPtrTorchOptionalTensor, XPtrTorchoptional_bool, XPtrTorchbool)::$_1, std::__1::allocator<cpp_torch_method__backward_self_Tensor_inputs_TensorList(XPtrTorchTensor, XPtrTorchTensorList, XPtrTorchOptionalTensor, XPtrTorchoptional_bool, XPtrTorchbool)::$_1>, void ()>::operator()() + 54 (0x10585c136 in torchpkg.so)
#> frame #15: std::__1::packaged_task<void ()>::operator()() + 72 (0x10585a4c8 in torchpkg.so)
#> frame #16: EventLoop<void>::run() + 379 (0x10585a2fb in torchpkg.so)
#> frame #17: void* std::__1::__thread_proxy[abi:v160006]<std::__1::tuple<std::__1::unique_ptr<std::__1::__thread_struct, std::__1::default_delete<std::__1::__thread_struct>>, ThreadPool<void>::ThreadPool(int)::'lambda'()>>(void*) + 50 (0x10585a072 in torchpkg.so)
#> frame #18: _pthread_start + 125 (0x7ff8182431d3 in libsystem_pthread.dylib)
#> frame #19: thread_start + 15 (0x7ff81823ebd3 in libsystem_pthread.dylib)
#>